Я новичок в tenorflow и пытаюсь запустить cnn с tenorflow 2.0 в pycharm при возникновении ошибки.
Using TensorFlow backend.
2020-04-02 20:35:17.989883: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2020-04-02 20:35:37.611976: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2020-04-02 20:35:38.570439: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1050 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.62
pciBusID: 0000:01:00.0
2020-04-02 20:35:38.570792: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2020-04-02 20:35:38.571551: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2020-04-02 20:35:38.571898: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2020-04-02 20:35:38.573877: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1050 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.62
pciBusID: 0000:01:00.0
2020-04-02 20:35:38.574108: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2020-04-02 20:35:38.574853: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2020-04-02 20:35:38.676185: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-04-02 20:35:38.676369: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2020-04-02 20:35:38.676469: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2020-04-02 20:35:38.677257: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3076 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1050 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
2020-04-02 20:35:38.857325: F tensorflow/stream_executor/cuda/cuda_driver.cc:175] Check failed: err == cudaSuccess || err == cudaErrorInvalidValue Unexpected CUDA error: invalid argument
Версия cuda и cudatoolkit - 10.1 и версия cudnn 7.6.5. Пожалуйста, помогите