pytorch-beginner

pytorch-beginner copied to clipboard

关于pytorch的gpu加速问题

1

为什么我使用了.cuda()将model和Variable放到gpu但gpu并不进行加速运算

zhangtaiyu

Accuracies are all zeros. Need to convert torch tensor to float line 68: running_acc += num_correct.data[0] -->running_acc += num_correct.data[0].float() line 98: eval_acc += num_correct.data[0] --> eval_acc += num_correct.data[0].float()

icemiliang

if I set batch_size=32 it returns "Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)" but when I set batch_size=10(

LostBirdx

A puzzle about the model in chapter 2.

1

The model in chapter 2 should be multilayer perceptron instead of logistic regression, since which can only be used in two classfication problem. How about changing the model to softmax...

xzhws

In 02 Logistic Regression, all accuracies are zero. Need to convert torch tensor to float. line 68: running_acc += num_correct.data[0] --> running_acc += num_correct.data[0].float() line 98: eval_acc += num_correct.data[0] -->...

icemiliang

文件：05-Recurrent Neural Network/recurrent_network.py 例如：line 86 if i % 300 == 0: print('[{}/{}] Loss: {:.6f}, Acc: {:.6f}'.format( epoch + 1, num_epoches, running_loss / (batch_size * i), running_acc / (batch_size * i)))...

wenfengzCN

when i run the code of number 4,it embraces a error: AttributeError: 'Cnn' object has no attribute 'named_parameters'

Jason08

issues about GAN

1

@L1aoXingyu 你好，GAN网络的训练判别器的时候不是要把生成器固定住吗？但是，代码中并没有哪一步把生成器的参数固定住。这样在训练判别器的时候，生成器的参数也会进行梯度更新的吧？

978749951

Hi, I think that there is a few mistakes in the simple and convolutional autoencoders : - The displayed loss is the loss on the last image of the epoch...

Jeanselme

shouldn't loss have add(-1) here?

1

https://github.com/L1aoXingyu/pytorch-beginner/blob/61db1de8a2528ab50cd64b50af2268a8b3bc01a4/08-AutoEncoder/Variational_autoencoder.py#L87

mirachakshu