TypeError: Incompatible types: <dtype: 'resource'> vs. int64. Value is 0

[MARUIHAN123]

请问这个是什么错误？

[yizt]

@MARUIHAN123 您好，需要复现错误才能解决问题，麻烦说一下运行环境，版本信息，代码改动，数据集等等，保证能够重现错误

[MARUIHAN123]

python3.7. tensorflow1.14.0 keras 2.3.1 我是用的自己的数据集。数据集是按照voc的格式做的。麻烦您帮我看一下。谢谢
WARNING:tensorflow:Model failed to serialize as JSON. Ignoring... ('Not JSON Serializable:', b'\n\x04Mean\x12\x04Mean\x1a\x12rpn_bbox_loss/Mean\x1a\x05Const*\x0f\n\tkeep_dims\x12\x02(\x01*\n\n\x04Tidx\x12\x020\x03*\x07\n\x01T\x12\x020\x01')
Epoch 1/80
Traceback (most recent call last):
File "/home/multiai4/Ruihan/face_mask_detection/train.py", line 133, in
main(arguments)
File "/home/multiai4/Ruihan/face_mask_detection/train.py", line 125, in main
callbacks=get_call_back())
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 1433, in fit_generator
steps_name='steps_per_epoch')
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 264, in model_iteration
batch_outs = batch_function(*batch_data)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 1174, in train_on_batch
self._make_train_function()
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 2219, in _make_train_function
params=self._collected_trainable_weights, loss=self.total_loss)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/optimizers.py", line 183, in get_updates
grads = self.get_gradients(loss, params)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/optimizers.py", line 91, in get_gradients
grads = K.gradients(loss, params)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3494, in gradients
loss, variables, colocate_gradients_with_ops=True)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 158, in gradients
unconnected_gradients)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/ops/gradients_util.py", line 720, in _GradientsHelper
out_grads[i] = loop_state.ZerosLike(op, i)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 1231, in ZerosLike
result = constant_op.constant(0, shape=shape.dims, dtype=val.dtype)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py", line 246, in constant
allow_broadcast=True)
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py", line 284, in _constant_impl
allow_broadcast=allow_broadcast))
File "/home/multiai4/.conda/envs/ruihan3.7/lib/python3.7/site-packages/tensorflow/python/framework/tensor_util.py", line 501, in make_tensor_proto
(dtype, nparray.dtype, values))
TypeError: Incompatible types: <dtype: 'resource'> vs. int64. Value is 0

Process finished with exit code 1

[MARUIHAN123]

这个问题已经解决，谢谢