TypeError: can't pickle dict_values objects
Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.
See @{tf.nn.softmax_cross_entropy_with_logits_v2}.
N:\Anaconda3\install\envs\zhouying2\lib\site-packages\tensorflow\python\ops\gradients_impl.py:100: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
2020-04-11 11:23:00.226436: I T:\src\github\tensorflow\tensorflow\core\platform\cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
creating index...
index created!
2020-04-11 11:45:29.830021: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1306] Invalid argument: TypeError: can't pickle dict_values objects
Traceback (most recent call last):
File "N:\Anaconda3\install\envs\zhouying2\lib\site-packages\tensorflow\python\ops\script_ops.py", line 158, in __call__
ret = func(*args)
File "N:\Anaconda3\install\envs\zhouying2\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\metrics\coco_evaluation.py", line 358, in first_value_func
self._metrics = self.evaluate()
File "N:\Anaconda3\install\envs\zhouying2\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\metrics\coco_evaluation.py", line 207, in evaluate
self._detection_boxes_list)
File "N:\Anaconda3\install\envs\zhouying2\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\metrics\coco_tools.py", line 118, in LoadAnnotations
results.dataset['categories'] = copy.deepcopy(self.dataset['categories'])
File "N:\Anaconda3\install\envs\zhouying2\lib\copy.py", line 169, in deepcopy
rv = reductor(4)
TypeError: can't pickle dict_values objects
F:\TensorflowProject\ObjectDetection\models-1.12.0\research\object_detection\metrics
coco_tools.py 118行
#results.dataset['categories'] = copy.deepcopy(self.dataset['categories'])
results.dataset['categories'] = copy.deepcopy(list(self.dataset['categories']))
