pytorch_hand_classifier

pytorch_hand_classifier copied to clipboard

在utils文件夹里的trainer.py里, self.train.model()是不是应该放在 ``` def _train_one_epoch(self): for step, (data, label) in enumerate(self.train_data): ``` 的后面

halacrcrc

images文件夹和模型文件夹链接失效

1

如题

halacrcrc

Google colab平台运行项目时出现共享内存不足

1

由于自己的笔记本无GPU加速，所以将此项目运行在Google colab平台上。colab提供免费的GPU，但是运行时发现 共享内存不足，不知道有没有其他同学遇到此问题？ ``` 2018-07-28 12:48:24 [INFO]: Start training epoch 1 ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm). Traceback (most recent...

jsuyanyong

你好啊，我在运行classifier_train.py的时候遇到这个问题，我想知道你在运行这个程序的时候的环境是什么。我的是windows,10，pytorch=1.0.0，torchvision=0.2.1，python=3.5.6和python=3.6.9，cuda=9.0，我百度出来是由于pytorch版本或python版本或cuda版本不匹配，所以我想知道是不是版本问题。谢谢。 Hello, I encountered this problem when running classifier_train.py. I want to know what is the environment when you run this program. My environment is windows, 10, pytorch=1.0.0, torchvision=0.2.1, python=3.5.6...

gabriel-zly

Traceback (most recent call last): File "D:\workspace\pytorch_hand_classify\pytorch_hand_classifier\classifier_test.py", line 18, in tester = Tester(model, params) File "D:\workspace\pytorch_hand_classify\pytorch_hand_classifier\utils\Tester.py", line 34, in __init__ self._load_ckpt(ckpt) File "D:\workspace\pytorch_hand_classify\pytorch_hand_classifier\utils\Tester.py", line 67, in _load_ckpt self.model.load_state_dict(torch.load(ckpt)) File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\serialization.py",...

pyxiaoming

I printed the loss for each step. Why does the loss change greatly when each epoch starts? The first two epoch suddenly increase, and the latter is suddenly reduced.

lixiangamy

I have trained 50 epochs and found that it can improve further. How can T make it continue to train on the basis of these 50 epochs？Thank you！

Jayne5190704