alvinwan / hand-tracking-pong Goto Github PK

I have got below error with frozen output frame. How can I solve that?

loading frozen model for worker
loading frozen model for worker
====== loading HAND frozen graph into memory
====== loading HAND frozen graph into memory
2019-02-22 16:38:22.927844: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-22 16:38:22.932218: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-22 16:38:23.066414: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-02-22 16:38:23.066776: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1060 with Max-Q Design major: 6 minor: 1 memoryClockRate(GHz): 1.48
pciBusID: 0000:01:00.0
totalMemory: 5.94GiB freeMemory: 5.28GiB
2019-02-22 16:38:23.066791: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-02-22 16:38:23.070518: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-02-22 16:38:23.070836: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1060 with Max-Q Design major: 6 minor: 1 memoryClockRate(GHz): 1.48
pciBusID: 0000:01:00.0
totalMemory: 5.94GiB freeMemory: 298.81MiB
2019-02-22 16:38:23.070850: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
====== Hand Inference graph loaded.
2019-02-22 16:38:23.078431: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
====== Hand Inference graph loaded.
2019-02-22 16:38:23.123254: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-02-22 16:38:24.927430: E tensorflow/stream_executor/cuda/cuda_dnn.cc:385] could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR
2019-02-22 16:38:24.927461: E tensorflow/stream_executor/cuda/cuda_dnn.cc:352] could not destroy cudnn handle: CUDNN_STATUS_BAD_PARAM
2019-02-22 16:38:24.927482: F tensorflow/core/kernels/conv_ops.cc:667] Check failed: stream->parent()->GetConvolveAlgorithms( conv_parameters.ShouldIncludeWinogradNonfusedAlgo(), &algorithms)
loading frozen model for worker
====== loading HAND frozen graph into memory
2019-02-22 16:38:25.729278: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-02-22 16:38:25.804346: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-02-22 16:38:25.804760: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1060 with Max-Q Design major: 6 minor: 1 memoryClockRate(GHz): 1.48
pciBusID: 0000:01:00.0
totalMemory: 5.94GiB freeMemory: 5.04GiB
2019-02-22 16:38:25.804775: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
====== Hand Inference graph loaded.
2019-02-22 16:38:25.857719: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1060 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)