Created by: sukkyusun1

I successfully done trainning with VOC and datatset.

i have tried to my custom data

but have problem lacking memory.

so i tried to resize my image

!ResizeImage target_size: 608

the original size of image is 4496,3000,3 and 2592,1728,3

ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

but following error occured

/home/sk/anaconda3/envs/paddle/bin/python3.7 /home/sk/PaddleDetection/tools/train.py -c /home/sk/PaddleDetection/configs/ppyolo/ppyolo.yml -o pretrain_weights=https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar finetune_exclude_pretrained_paramas=['cls_score','bbox_pred'] --eval
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/ops.py:327
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:145
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:84
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:176
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:184
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:370
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:372
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:194: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  loss_cls = fluid.layers.elementwise_mul(loss_cls, tobj, axis=0)
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:197
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:198
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:200
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:145
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:84
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:176
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:184
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:370
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:372
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:194: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  loss_cls = fluid.layers.elementwise_mul(loss_cls, tobj, axis=0)
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:197
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:198
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:200
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:145
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:162
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:164
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:168
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:170
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:84
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:176
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:209: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  pw = fluid.layers.elementwise_mul(exp_dw, anchor_w) / \
/home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:211: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  ph = fluid.layers.elementwise_mul(exp_dh, anchor_h) / \
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:219
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:220
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:221
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:222
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:102
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:104
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:106
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/iou_loss.py:107
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:184
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:370
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:372
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:194: DeprecationWarning: API "paddle.fluid.layers.nn.elementwise_mul" is deprecated since 2.0.0, and may be removed in future versions. Use "paddle.multiply" instead.
  loss_cls = fluid.layers.elementwise_mul(loss_cls, tobj, axis=0)
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:197
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:198
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/losses/yolo_loss.py:200
The behavior of expression A + B has been unified with elementwise_add(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_add(X, Y, axis=0) instead of A + B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
2020-08-13 19:01:45,385-INFO: If regularizer of a Parameter has been set by 'fluid.ParamAttr' or 'fluid.WeightNormParamAttr' already. The Regularization[L2Decay, regularization_coeff=0.000500] in Optimizer will not take effect, and it will only be applied to other Parameters!
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/anchor_heads/iou_aware.py:64
The behavior of expression A * B has been unified with elementwise_mul(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_mul(X, Y, axis=0) instead of A * B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:276: UserWarning: /home/sk/PaddleDetection/ppdet/modeling/anchor_heads/iou_aware.py:40
The behavior of expression A / B has been unified with elementwise_div(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_div(X, Y, axis=0) instead of A / B. This transitional warning will be dropped in the future.
  op_type, op_type, EXPRESSION_MAP[method_name]))
2020-08-13 19:01:48,287-INFO: places would be ommited when DataLoader is not iterable
W0813 19:01:48.348649 11530 device_context.cc:268] Please NOTE: device: 0, CUDA Capability: 75, Driver API Version: 10.1, Runtime API Version: 10.0
W0813 19:01:48.351380 11530 device_context.cc:276] device: 0, cuDNN Version: 7.6.
/home/sk/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/io.py:2116: UserWarning: This list is not set, Because of Paramerter not found in program. There are: fc_0.w_0 fc_0.b_0
  format(" ".join(unused_para_list)))
2020-08-13 19:01:52,857-INFO: places would be ommited when DataLoader is not iterable
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:299: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  status = self._base[start:end].tostring().decode()
/home/sk/PaddleDetection/ppdet/data/shared_queue/sharedmemory.py:253: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  header_str = self._base[0:self.s_allocator_header].tostring()
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:89: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
  if isinstance(item, collections.Sequence) and len(item) == 0:
/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:55,847-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (2592,1728,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (2592,1728,3)

/home/sk/PaddleDetection/ppdet/data/parallel_map.py:243: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  .format(sample.errmsg))
2020-08-13 19:01:55,866-WARNING: recv endsignal from outq with errmsg[consumer[consumer-3b0-7] failed to map with error:[could not broadcast input array from shape (608,608,3) into shape (2592,1728,3)]]
/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:56,320-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:56,638-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (2592,1728,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (2592,1728,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:56,809-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:56,863-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:57,325-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:57,443-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)

/home/sk/PaddleDetection/ppdet/data/reader.py:50: DeprecationWarning: The 'warn' method is deprecated, use 'warning' instead
  format(f, e, str(stack_info)))
2020-08-13 19:01:57,544-WARNING: fail to map op [RandomExpand_2dd3d4] with error: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3) and stack:
Traceback (most recent call last):
  File "/home/sk/PaddleDetection/ppdet/data/reader.py", line 46, in __call__
    data = f(data, ctx)
  File "/home/sk/PaddleDetection/ppdet/data/transform/operators.py", line 1753, in __call__
    canvas[y:y + height, x:x + width, :] = img.astype(np.uint8)
ValueError: could not broadcast input array from shape (608,608,3) into shape (4496,3000,3)