Created by: dhlrd

oidv5 目标检测模型，直接推理的时候报错： Traceback (most recent call last): File "tools/infer.py", line 271, in main() File "tools/infer.py", line 131, in main test_fetches = model.test(feed_vars) File "/Users/admin/projects/PaddleDetection/ppdet/modeling/architectures/cascade_rcnn_cls_aware.py", line 184, in test return self.build(feed_vars, 'test') File "/Users/admin/projects/PaddleDetection/ppdet/modeling/architectures/cascade_rcnn_cls_aware.py", line 88, in build body_feats = self.backbone(im) File "/Users/admin/projects/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 432, in call res = self.layer_warp(res, i) File "/Users/admin/projects/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 383, in layer_warp nonlocal_name + '_{}'.format(i), int(dim_in / 2) ) File "/Users/admin/projects/PaddleDetection/ppdet/modeling/backbones/nonlocal_helper.py", line 152, in add_space_nonlocal conv = space_nonlocal(input, dim_in, dim_out, prefix, dim_inner) File "/Users/admin/projects/PaddleDetection/ppdet/modeling/backbones/nonlocal_helper.py", line 101, in space_nonlocal t_re = fluid.layers.reshape(t, shape=list(theta_shape), actual_shape=theta_shape_op ) File "/Users/admin/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 8976, in reshape attrs["shape"] = get_attr_shape(shape) File "/Users/admin/anaconda3/envs/paddle/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 8949, in get_attr_shape "be -1. But received shape[%d] is also -1." % dim_idx)

Only one dimension value of 'shape' in reshape can be -1. But received shape[2] is also -1.

应该是配置参数不正确，怎么修改？

我使用的cpu版本的paddle，Mac OS 系统

谢谢