인프런 커뮤니티 질문&답변

2000/2000 [==============================] - ETA: 0s - loss: 0.2448 - accuracy: 0.9157

Epoch 1: loss improved from inf to 0.24480, saving model to saved_model_isbi_2012\unet_model.h5

Traceback (most recent call last):

File "train_isbi_2012.py", line 180, in <module>

app.run(main)

File "D:\anaconda\envs\tfunet\lib\site-packages\absl\app.py", line 308, in run

runmain(main, args)

File "D:\anaconda\envs\tfunet\lib\site-packages\absl\app.py", line 254, in runmain

sys.exit(main(argv))

File "train_isbi_2012.py", line 177, in main

callbacks=[model_checkpoint_callback, tensorboard_callback, custom_callback])

File "D:\anaconda\envs\tfunet\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler

raise e.with_traceback(filtered_tb) from None

File "D:\anaconda\envs\tfunet\lib\site-packages\keras\saving\legacy\save.py", line 155, in save_model

"Saving the model to HDF5 format requires the model to be a "

NotImplementedError: Saving the model to HDF5 format requires the model to be a Functional model or a Sequential model. It does not work for subclassed models, because such models are defined via the body of a Python method, which isn't safely serializable. Consider saving to the Tensorflow SavedModel format (by setting save_format="tf") or using save_weights.

2024-05-05 07:43:59.819913: W tensorflow/core/kernels/data/generator_dataset_op.cc:108] Error occurred when finalizing GeneratorDataset iterator: FAILED_PRECONDITION: Python interpreter state is not initialized. The process may be terminated.

[[{{node PyFunc}}]]

이런문제가 뜨고 사진 5장도 저장안되고 save 폴더 안에도 저장되는게 없는데요 인터넷을 찾아봐도 무슨 문제인지 나오질 않아서 물어봐요 ㅜ(밑에 다른사람이 비슷한사례가 있어 바꿔보았는데 이렇게 뜨네요)

2000/2000 [==============================] - ETA: 0s - loss: 0.2294 - accuracy: 0.9116

Epoch 1: loss improved from inf to 0.22941, saving model to unet_model.h5

Traceback (most recent call last):

File "C:\Users\Administrator\Desktop\UNET-tf2-main\train_isbi_2012.py", line 180, in <module>

app.run(main)

File "D:\anaconda\envs\tfunet\lib\site-packages\absl\app.py", line 308, in run

runmain(main, args)

File "D:\anaconda\envs\tfunet\lib\site-packages\absl\app.py", line 254, in runmain

sys.exit(main(argv))

File "C:\Users\Administrator\Desktop\UNET-tf2-main\train_isbi_2012.py", line 177, in main

callbacks=[model_checkpoint_callback, tensorboard_callback, custom_callback])

File "D:\anaconda\envs\tfunet\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler

raise e.with_traceback(filtered_tb) from None

File "D:\anaconda\envs\tfunet\lib\site-packages\keras\saving\legacy\save.py", line 155, in save_model

"Saving the model to HDF5 format requires the model to be a "

NotImplementedError: Saving the model to HDF5 format requires the model to be a Functional model or a Sequential model. It does not work for subclassed models, because such models are defined via the body of a Python method, which isn't safely serializable. Consider saving to the Tensorflow SavedModel format (by setting save_format="tf") or using save_weights.

2024-05-05 14:39:03.225178: W tensorflow/core/kernels/data/generator_dataset_op.cc:108] Error occurred when finalizing GeneratorDataset iterator: FAILED_PRECONDITION: Python interpreter state is not initialized. The process may be terminated.

[[{{node PyFunc}}]]

Process finished with exit code 1