chizhanyuefeng / action_recognition_tf Goto Github PK

python train_c3d_network.py
2020-05-10 10:27:29.673651: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 10:27:29.673683: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 10:27:29.673694: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.

2020-05-10 10:27:29.673701: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 10:27:29.673709: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 10:27:29.766191: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-05-10 10:27:29.766453: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 0 with properties:
name: GeForce GTX 1650
major: 7 minor: 5 memoryClockRate (GHz) 1.74
pciBusID 0000:01:00.0
Total memory: 3.81GiB
Free memory: 3.61GiB
2020-05-10 10:27:29.766471: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0
2020-05-10 10:27:29.766478: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y
2020-05-10 10:27:29.766487: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1650, pci bus id: 0000:01:00.0)
Killed

python test_c3d_network.py
2020-05-10 11:09:10.013742: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 11:09:10.013774: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 11:09:10.013784: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 11:09:10.013792: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 11:09:10.013799: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2020-05-10 11:09:10.659758: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-05-10 11:09:10.660012: I tensorflow/core/common_runtime/gpu/gpu_device.cc:955] Found device 0 with properties:
name: GeForce GTX 1650
major: 7 minor: 5 memoryClockRate (GHz) 1.74
pciBusID 0000:01:00.0
Total memory: 3.81GiB
Free memory: 3.61GiB
2020-05-10 11:09:10.660027: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0
2020-05-10 11:09:10.660032: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y
2020-05-10 11:09:10.660040: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1650, pci bus id: 0000:01:00.0)
Killed
我一运行，进程就被杀死，是硬件问题，还是需要修改代码呢？怎么修改呢，谢谢

你好，我想依照你的网络结构复现实验。由于你还未提供 .model文件，我按照一般方法写了网络，由于输入是[batch, 16,112,112,3], 可是我不知道weight的shape如何来写？谢谢

thanks for your code.Now,I have run the utils folders,the next should I run the train_c3d_network.py? but there is no pretrain model,how could i get it

您好，谢谢您的代码分享，请教一下，您在做视频动作识别的时候都是用哪些训练数据的，除了C3d神经网络模型，您还有什么可以推荐的?
谢谢。

您好，我想重复一下您这个项目，能上传一下.model文件吗，我是新手小白，没有这个文件跑不通了，拜托了