Created by: greatyang

ubuntu 16.04 paddle 1.7.2 GPU: Nvidia V100 16GB python:3.7

aistudio@jupyter-78894-555912:~/work/models/PaddleCV/human_pose_estimation$ python test_squidtap.py  --dataset 'coco' --checkpoint 'output/simplebase-coco/0'
-----------  Configuration Arguments -----------
batch_size: 32
checkpoint: output/simplebase-coco/0
dataset: coco
flip_test: True
kp_dim: 7
shift_heatmap: True
use_gpu: True
------------------------------------------------
W0730 09:13:04.981681  4680 device_context.cc:237] Please NOTE: device: 0, CUDA Capability: 70, Driver API Version: 9.2, Runtime API Version: 9.0
W0730 09:13:04.986066  4680 device_context.cc:245] device: 0, cuDNN Version: 7.3.
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
=> classes: ['__background__', 'bottle']
=> num_images: 138
generating coco gt_db...
=> num db: 138
=> num selected db: 138
Processing batch #0
Traceback (most recent call last):
  File "test_squidtap.py", line 131, in <module>
    test(args)
  File "test_squidtap.py", line 102, in test
    feed=feeder.feed(data))
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/data_feeder.py", line 323, in feed
    "len(feed_list) (%d)") % (len(each_sample), len(converter))
AssertionError: The number of fields in data (7) does not match len(feed_list) (2)