Can not load saved BlazePose model. about pinto_model_zoo HOT 4 CLOSED

$ python3

Python 3.6.9 (default, Jul 17 2020, 12:50:27) 
[GCC 8.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.

>>> import tensorflow as tf
2020-08-15 13:59:29.183339: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1

>>> tf.__version__
'2.3.0'

>>> imported = tf.saved_model.load('saved_model_pose_detection')

2020-08-15 13:59:47.500567: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2020-08-15 13:59:47.515226: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.515729: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: 
pciBusID: 0000:01:00.0 name: GeForce GTX 1070 with Max-Q Design computeCapability: 6.1
coreClock: 1.2655GHz coreCount: 16 deviceMemorySize: 7.93GiB deviceMemoryBandwidth: 238.66GiB/s
2020-08-15 13:59:47.515749: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-08-15 13:59:47.516876: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-08-15 13:59:47.517969: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-08-15 13:59:47.518149: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-08-15 13:59:47.519280: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-08-15 13:59:47.519932: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-08-15 13:59:47.522420: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7
2020-08-15 13:59:47.522520: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.523062: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.523530: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0
2020-08-15 13:59:47.523739: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-08-15 13:59:47.549960: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2199995000 Hz
2020-08-15 13:59:47.551139: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x82d3780 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-08-15 13:59:47.551159: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-08-15 13:59:47.597910: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.598558: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x833f190 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-08-15 13:59:47.598575: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): GeForce GTX 1070 with Max-Q Design, Compute Capability 6.1
2020-08-15 13:59:47.598817: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.599346: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: 
pciBusID: 0000:01:00.0 name: GeForce GTX 1070 with Max-Q Design computeCapability: 6.1
coreClock: 1.2655GHz coreCount: 16 deviceMemorySize: 7.93GiB deviceMemoryBandwidth: 238.66GiB/s
2020-08-15 13:59:47.599367: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-08-15 13:59:47.599384: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-08-15 13:59:47.599394: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-08-15 13:59:47.599405: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-08-15 13:59:47.599434: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-08-15 13:59:47.599462: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-08-15 13:59:47.599509: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7
2020-08-15 13:59:47.599582: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.600075: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:47.600540: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0
2020-08-15 13:59:47.600559: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-08-15 13:59:48.052606: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-08-15 13:59:48.052637: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263]      0 
2020-08-15 13:59:48.052643: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0:   N 
2020-08-15 13:59:48.052835: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:48.053397: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-08-15 13:59:48.053911: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7025 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
>>>