Tensorflow: TF 2.1rc1로 훈련 된 모델을 TFLite로 변환하는 중에 오류가 발생했습니다.

시스템 정보

• OS 플랫폼 및 배포 (예 : Linux Ubuntu 16.04) : Windows 10
• (소스 또는 바이너리)에서 설치된 TensorFlow : conda
• TensorFlow 버전 (또는 소스의 경우 github SHA) : 2.1.0-rc1

tflite_convert의 텍스트 출력 제공

(dl4cv) D:\development\tensorflow\ANPR\output\rmsprop>tflite_convert --keras_model_file=clpr-model.h5 --enable_select_tf_ops --output_file=model.tflite
2019-12-27 14:09:27.630637: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.summary API due to missing TensorBoard installation.
2019-12-27 14:09:29.765186: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2019-12-27 14:09:29.788663: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2070 computeCapability: 7.5
coreClock: 1.83GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 417.29GiB/s
2019-12-27 14:09:29.797947: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2019-12-27 14:09:29.807131: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2019-12-27 14:09:29.815002: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2019-12-27 14:09:29.823010: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2019-12-27 14:09:29.830529: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2019-12-27 14:09:29.838455: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2019-12-27 14:09:29.850408: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-27 14:09:29.855640: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2019-12-27 14:09:29.859642: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-12-27 14:09:29.865715: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2070 computeCapability: 7.5
coreClock: 1.83GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 417.29GiB/s
2019-12-27 14:09:29.874362: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2019-12-27 14:09:29.878508: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2019-12-27 14:09:29.882420: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2019-12-27 14:09:29.886489: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2019-12-27 14:09:29.890738: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2019-12-27 14:09:29.894738: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2019-12-27 14:09:29.898962: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-27 14:09:29.903241: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2019-12-27 14:09:30.584878: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-27 14:09:30.589782: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2019-12-27 14:09:30.592385: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2019-12-27 14:09:30.595864: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6271 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2070, pci bus id: 0000:01:00.0, compute capability: 7.5)
WARNING:tensorflow:No training configuration found in save file: the model was *not* compiled. Compile it manually.
W1227 14:09:33.236038 28348 hdf5_format.py:177] No training configuration found in save file: the model was *not* compiled. Compile it manually.
2019-12-27 14:09:33.443668: I tensorflow/core/grappler/devices.cc:55] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1
2019-12-27 14:09:33.450829: I tensorflow/core/grappler/clusters/single_machine.cc:356] Starting new session
2019-12-27 14:09:33.467462: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2070 computeCapability: 7.5
coreClock: 1.83GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 417.29GiB/s
2019-12-27 14:09:33.478633: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2019-12-27 14:09:33.483411: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2019-12-27 14:09:33.487932: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2019-12-27 14:09:33.492763: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2019-12-27 14:09:33.498057: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2019-12-27 14:09:33.502602: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2019-12-27 14:09:33.508437: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-27 14:09:33.513114: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2019-12-27 14:09:33.516838: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-27 14:09:33.521102: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2019-12-27 14:09:33.524027: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2019-12-27 14:09:33.529383: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6271 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2070, pci bus id: 0000:01:00.0, compute capability: 7.5)
2019-12-27 14:09:33.597411: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: graph_to_optimize
2019-12-27 14:09:33.603519: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: Graph size after: 380 nodes (0), 484 edges (0), time = 17.869ms.
2019-12-27 14:09:33.610268: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: Graph size after: 380 nodes (0), 484 edges (0), time = 4.152ms.
2019-12-27 14:09:33.615867: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_backward_gru_1_while_cond_2105
2019-12-27 14:09:33.621215: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.626682: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.631716: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_forward_gru_while_body_1602
2019-12-27 14:09:33.637805: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.643095: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.647759: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_forward_gru_1_while_cond_1941
2019-12-27 14:09:33.653473: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.658111: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.663563: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_backward_gru_1_while_body_2106
2019-12-27 14:09:33.668843: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.674032: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.679432: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_backward_gru_while_body_1766
2019-12-27 14:09:33.685071: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.690795: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.695366: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_forward_gru_while_cond_1601
2019-12-27 14:09:33.701130: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.705783: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.710792: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_forward_gru_1_while_body_1942
2019-12-27 14:09:33.717048: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0.001ms.
2019-12-27 14:09:33.721844: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.726940: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_backward_gru_while_cond_1765
2019-12-27 14:09:33.732340: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:33.737188: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   function_optimizer: function_optimizer did nothing. time = 0ms.
2019-12-27 14:09:34.924139: I tensorflow/core/grappler/devices.cc:55] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1
2019-12-27 14:09:34.931432: I tensorflow/core/grappler/clusters/single_machine.cc:356] Starting new session
2019-12-27 14:09:34.941771: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2070 computeCapability: 7.5
coreClock: 1.83GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 417.29GiB/s
2019-12-27 14:09:34.952985: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2019-12-27 14:09:34.957078: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2019-12-27 14:09:34.962751: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2019-12-27 14:09:34.967762: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2019-12-27 14:09:34.973494: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2019-12-27 14:09:34.977944: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2019-12-27 14:09:34.983289: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-27 14:09:34.987946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2019-12-27 14:09:34.992126: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-27 14:09:34.996303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2019-12-27 14:09:34.999665: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2019-12-27 14:09:35.004366: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6271 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2070, pci bus id: 0000:01:00.0, compute capability: 7.5)
2019-12-27 14:09:35.521865: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: graph_to_optimize
2019-12-27 14:09:35.526582: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 226 nodes (-16), 276 edges (-28), time = 227.782ms.
2019-12-27 14:09:35.532999: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 226 nodes (0), 276 edges (0), time = 111.153ms.
2019-12-27 14:09:35.538097: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_backward_gru_1_while_body_2106_frozen
2019-12-27 14:09:35.545175: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (-1), 79 edges (0), time = 2.335ms.
2019-12-27 14:09:35.550989: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (0), 79 edges (0), time = 0.737ms.
2019-12-27 14:09:35.556165: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_backward_gru_1_while_cond_2105_frozen
2019-12-27 14:09:35.562428: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.306ms.
2019-12-27 14:09:35.567480: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.176ms.
2019-12-27 14:09:35.573582: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_forward_gru_1_while_cond_1941_frozen
2019-12-27 14:09:35.579766: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.262ms.
2019-12-27 14:09:35.584544: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.175ms.
2019-12-27 14:09:35.590845: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_1_forward_gru_1_while_body_1942_frozen
2019-12-27 14:09:35.597525: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (-1), 79 edges (0), time = 1.396ms.
2019-12-27 14:09:35.602989: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (0), 79 edges (0), time = 0.698ms.
2019-12-27 14:09:35.609327: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_backward_gru_while_cond_1765_frozen
2019-12-27 14:09:35.614684: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.274ms.
2019-12-27 14:09:35.621170: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.216ms.
2019-12-27 14:09:35.626793: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_backward_gru_while_body_1766_frozen
2019-12-27 14:09:35.632917: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (-1), 79 edges (0), time = 1.417ms.
2019-12-27 14:09:35.639119: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (0), 79 edges (0), time = 0.711ms.
2019-12-27 14:09:35.645066: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_forward_gru_while_body_1602_frozen
2019-12-27 14:09:35.652559: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (-1), 79 edges (0), time = 1.349ms.
2019-12-27 14:09:35.658901: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 60 nodes (0), 79 edges (0), time = 0.749ms.
2019-12-27 14:09:35.665589: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:814] Optimization results for grappler item: model_bidirectional_forward_gru_while_cond_1601_frozen
2019-12-27 14:09:35.673058: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.295ms.
2019-12-27 14:09:35.680300: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:816]   constant_folding: Graph size after: 14 nodes (0), 4 edges (0), time = 0.138ms.
Traceback (most recent call last):
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\Andreas\Anaconda3\envs\dl4cv\Scripts\tflite_convert.exe\__main__.py", line 7, in <module>
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\tflite_convert.py", line 594, in main
    app.run(main=run_main, argv=sys.argv[:1])
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\absl\app.py", line 299, in run
    _run_main(main, args)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\absl\app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\tflite_convert.py", line 577, in run_main
    _convert_tf2_model(tflite_flags)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\tflite_convert.py", line 235, in _convert_tf2_model
    tflite_model = converter.convert()
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\lite.py", line 464, in convert
    **converter_kwargs)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\convert.py", line 457, in toco_convert_impl
    enable_mlir_converter=enable_mlir_converter)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\python\convert.py", line 203, in toco_convert_protos
    raise ConverterError("See console for info.\n%s\n%s\n" % (stdout, stderr))
tensorflow.lite.python.convert.ConverterError: See console for info.
2019-12-27 14:09:36.318110: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.
WARNING:root:Limited tf.summary API due to missing TensorBoard installation.
2019-12-27 14:09:39.097723: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-12-27 14:09:39.107524: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2019-12-27 14:09:39.163607: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1555] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2070 computeCapability: 7.5
coreClock: 1.83GHz coreCount: 36 deviceMemorySize: 8.00GiB deviceMemoryBandwidth: 417.29GiB/s
2019-12-27 14:09:39.164452: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2019-12-27 14:09:39.206090: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_10.dll
2019-12-27 14:09:39.249003: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_10.dll
2019-12-27 14:09:39.256358: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_10.dll
2019-12-27 14:09:39.307626: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_10.dll
2019-12-27 14:09:39.326748: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_10.dll
2019-12-27 14:09:39.414022: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2019-12-27 14:09:39.414730: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1697] Adding visible gpu devices: 0
2019-12-27 14:09:42.459316: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1096] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-12-27 14:09:42.459514: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102]      0
2019-12-27 14:09:42.459628: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] 0:   N
2019-12-27 14:09:42.460800: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1241] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2903 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2070, pci bus id: 0000:01:00.0, compute capability: 7.5)
2019-12-27 14:09:42.536530: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListFromTensor
2019-12-27 14:09:42.536727: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.536928: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListFromTensor
2019-12-27 14:09:42.537124: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.537289: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListReserve
2019-12-27 14:09:42.537455: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.537616: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListReserve
2019-12-27 14:09:42.537804: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.537974: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: While
2019-12-27 14:09:42.538136: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.538282: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.538438: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: While
2019-12-27 14:09:42.538586: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.538734: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.538884: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListStack
2019-12-27 14:09:42.539041: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListStack
2019-12-27 14:09:42.539238: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListFromTensor
2019-12-27 14:09:42.539398: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.539579: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListFromTensor
2019-12-27 14:09:42.539737: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.539879: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListReserve
2019-12-27 14:09:42.540034: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.540195: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListReserve
2019-12-27 14:09:42.540357: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.540515: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: While
2019-12-27 14:09:42.540692: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.540861: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.541036: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: While
2019-12-27 14:09:42.541193: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.541338: I tensorflow/lite/toco/import_tensorflow.cc:193] Unsupported data type in placeholder op: 21
2019-12-27 14:09:42.541488: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListStack
2019-12-27 14:09:42.541642: I tensorflow/lite/toco/import_tensorflow.cc:659] Converting unsupported operation: TensorListStack
2019-12-27 14:09:42.550428: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before Removing unused ops: 98 operators, 264 arrays (0 quantized)
2019-12-27 14:09:42.555345: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before general graph transformations: 98 operators, 264 arrays (0 quantized)
2019-12-27 14:09:42.562862: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] After general graph transformations pass 1: 62 operators, 194 arrays (0 quantized)
2019-12-27 14:09:42.564023: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] After general graph transformations pass 2: 60 operators, 192 arrays (0 quantized)
2019-12-27 14:09:42.565092: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] After general graph transformations pass 3: 58 operators, 188 arrays (0 quantized)
2019-12-27 14:09:42.566092: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before Group bidirectional sequence lstm/rnn: 58 operators, 188 arrays (0 quantized)
2019-12-27 14:09:42.566900: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before dequantization graph transformations: 58 operators, 188 arrays (0 quantized)
2019-12-27 14:09:42.567646: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before Identify nearest upsample.: 58 operators, 188 arrays (0 quantized)
2019-12-27 14:09:42.569453: I tensorflow/lite/toco/allocate_transient_arrays.cc:345] Total transient array allocated size: 655360 bytes, theoretical optimal value: 655360 bytes.
2019-12-27 14:09:42.569852: I tensorflow/lite/toco/toco_tooling.cc:471] Number of parameters: 4121949
2019-12-27 14:09:42.575404: E tensorflow/lite/toco/toco_tooling.cc:498] We are continually in the process of adding support to TensorFlow Lite for more ops. It would be helpful if you could inform us of how this conversion went by opening a github issue at https://github.com/tensorflow/tensorflow/issues/new?template=40-tflite-op-request.md
 and pasting the following:

Some of the operators in the model are not supported by the standard TensorFlow Lite runtime. If those are native TensorFlow operators, you might be able to use the extended runtime by passing --enable_select_tf_ops, or by setting target_ops=TFLITE_BUILTINS,SELECT_TF_OPS when calling tf.lite.TFLiteConverter(). Otherwise, if you have a custom implementation for them you can disable this error with --allow_custom_ops, or by setting allow_custom_ops=True when calling tf.lite.TFLiteConverter(). Here is a list of builtin operators you are using: CONCATENATION, CONV_2D, DEPTHWISE_CONV_2D, FILL, FULLY_CONNECTED, MAX_POOL_2D, PACK, RESHAPE, REVERSE_V2, SHAPE, SOFTMAX, STRIDED_SLICE, TRANSPOSE. Here is a list of operators for which you will need custom implementations: TensorListFromTensor, TensorListReserve, TensorListStack, While.
Traceback (most recent call last):
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\Andreas\Anaconda3\envs\dl4cv\Scripts\toco_from_protos.exe\__main__.py", line 7, in <module>
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\toco\python\toco_from_protos.py", line 93, in main
    app.run(main=execute, argv=[sys.argv[0]] + unparsed)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\python\platform\app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\absl\app.py", line 299, in run
    _run_main(main, args)
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\absl\app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "c:\users\andreas\anaconda3\envs\dl4cv\lib\site-packages\tensorflow_core\lite\toco\python\toco_from_protos.py", line 56, in execute
    enable_mlir_converter)
Exception: We are continually in the process of adding support to TensorFlow Lite for more ops. It would be helpful if you could inform us of how this conversion went by opening a github issue at https://github.com/tensorflow/tensorflow/issues/new?template=40-tflite-op-request.md
 and pasting the following:

Some of the operators in the model are not supported by the standard TensorFlow Lite runtime. If those are native TensorFlow operators, you might be able to use the extended runtime by passing --enable_select_tf_ops, or by setting target_ops=TFLITE_BUILTINS,SELECT_TF_OPS when calling tf.lite.TFLiteConverter(). Otherwise, if you have a custom implementation for them you can disable this error with --allow_custom_ops, or by setting allow_custom_ops=True when calling tf.lite.TFLiteConverter(). Here is a list of builtin operators you are using: CONCATENATION, CONV_2D, DEPTHWISE_CONV_2D, FILL, FULLY_CONNECTED, MAX_POOL_2D, PACK, RESHAPE, REVERSE_V2, SHAPE, SOFTMAX, STRIDED_SLICE, TRANSPOSE. Here is a list of operators for which you will need custom implementations: TensorListFromTensor, TensorListReserve, TensorListStack, While.

또한 가능하면 GraphDef 또는 모델에 대한 링크를 포함하십시오.

모델 다운로드

기타 정보 / 로그

문제 진단에 도움이되는 로그 또는 소스 코드를 포함하십시오. 역 추적을 포함하는 경우 전체 역 추적을 포함하십시오. 큰 로그와 파일을 첨부해야합니다.

GitHub 프로젝트

모델 아키텍처 :

class OCR:
    <strong i="14">@staticmethod</strong>
    def build(input_size, pool_size, output_size):
        conv_filters = 16
        kernel_size = (3, 3)
        time_dense_size = 32
        rnn_size = 512

        input_data = Input(name="input", shape=input_size)

        cnn = Conv2D(conv_filters, kernel_size, padding='same', kernel_initializer='he_normal')(input_data)
        cnn = BatchNormalization()(cnn)
        cnn = Activation('relu')(cnn)
        cnn = MaxPooling2D(pool_size=(pool_size, pool_size))(cnn)

        cnn = Conv2D(conv_filters, kernel_size, padding='same', kernel_initializer='he_normal')(cnn)
        cnn = BatchNormalization()(cnn)
        cnn = Activation('relu')(cnn)
        cnn = MaxPooling2D(pool_size=(pool_size, pool_size))(cnn)

        # CNN to RNN
        shape = cnn.get_shape()
        bgru = Reshape((shape[1], shape[2] * shape[3]))(cnn)

        bgru = Bidirectional(GRU(units=rnn_size, return_sequences=True, dropout=0.5))(bgru)
        bgru = TimeDistributed(Dense(units=time_dense_size))(bgru)

        bgru = Bidirectional(GRU(units=rnn_size, return_sequences=True, dropout=0.5))(bgru)
        output_data = TimeDistributed(Dense(units=output_size, activation="softmax"))(bgru)

        return input_data, output_data