Я использую make_image_classifier с --tfhub_module https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4, и все в порядке, но когда я пытаюсь использовать любой из модулей efficien tnet, я получаю ту же ошибку:
2020-02-24 19:03:41.932066: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-02-24 19:03:41.936842: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
I0224 19:03:43.789840 10872 resolver.py:79] Using C:\Users\Asus\AppData\Local\Temp\tfhub_modules to cache modules.
I0224 19:03:43.795793 10872 resolver.py:400] Downloading TF-Hub Module 'https://tfhub.dev/google/efficientnet/b3/feature-vector/1'.
I0224 19:03:49.385545 10872 resolver.py:122] Downloaded https://tfhub.dev/google/efficientnet/b3/feature-vector/1, Total size: 44.06MB
I0224 19:03:49.397364 10872 resolver.py:415] Downloaded TF-Hub Module 'https://tfhub.dev/google/efficientnet/b3/feature-vector/1'.
2020-02-24 19:03:50.063444: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2020-02-24 19:03:50.092602: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce GTX 1050 Ti computeCapability: 6.1
coreClock: 1.62GHz coreCount: 6 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 104.43GiB/s
2020-02-24 19:03:50.102233: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-02-24 19:03:50.110926: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2020-02-24 19:03:50.122096: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2020-02-24 19:03:50.127976: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2020-02-24 19:03:50.136916: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2020-02-24 19:03:50.146614: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2020-02-24 19:03:50.151887: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudnn64_7.dll'; dlerror: cudnn64_7.dll not found
2020-02-24 19:03:50.159499: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1592] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2020-02-24 19:03:50.175108: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2020-02-24 19:03:50.181765: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-02-24 19:03:50.186824: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]
WARNING:tensorflow:From c:\program files\python37\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1786: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
W0224 19:03:50.490510 10872 deprecation.py:506] From c:\program files\python37\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1786: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
Traceback (most recent call last):
File "c:\program files\python37\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "c:\program files\python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Program Files\Python37\Scripts\make_image_classifier.exe\__main__.py", line 9, in <module>
File "c:\program files\python37\lib\site-packages\tensorflow_hub\tools\make_image_classifier\make_image_classifier.py", line 212, in run_main
app.run(main)
File "c:\program files\python37\lib\site-packages\absl\app.py", line 299, in run
_run_main(main, args)
File "c:\program files\python37\lib\site-packages\absl\app.py", line 250, in _run_main
sys.exit(main(argv))
File "c:\program files\python37\lib\site-packages\tensorflow_hub\tools\make_image_classifier\make_image_classifier.py", line 163, in main
FLAGS.tfhub_module, image_dir, hparams, FLAGS.image_size)
File "c:\program files\python37\lib\site-packages\tensorflow_hub\tools\make_image_classifier\make_image_classifier_lib.py", line 228, in make_image_classifier
image_size = _image_size_for_module(module_layer, requested_image_size)
File "c:\program files\python37\lib\site-packages\tensorflow_hub\tools\make_image_classifier\make_image_classifier_lib.py", line 144, in _image_size_for_module
module_layer._func.__call__ # pylint:disable=protected-access
AttributeError: 'AutoTrackable' object has no attribute '__call__'
Что мне делать чтобы обработать эту ошибку и использовать более точную эффективность tnet