Du Ang

Figure out CGAN's condition label

1

Hi @kozistr, Thanks for your great work! In your CGAN implementation, you feed G and D with the same real label from the dataset as the condition.However, I have a...

Hi there, I used the `torch.utils.tensorboard` to watch the weight/grad when training the DCGAN example on MNIST dataset. In the DCGAN example, we use the normal distribution to initialize both...

Change Softmax to LogSoftmax to use NLLLoss.

1

Fix #3. From [here](http://pytorch.org/docs/master/nn.html#torch.nn.Softmax), it is `LogSoftmax` should be used for `NLLLoss`, instead of `Softmax`. > This module doesn’t work directly with NLLLoss, which expects the Log to be computed...

Hi, @pesser, thanks for your work! According to [here](https://github.com/CompVis/vunet/blob/master/models.py#L139), it seems that you don't use `cn` in the `enc_up` pass, which is different from the net in your paper. Could...

如何从训练好的 PyTorch 模型中提取一幅图像的特征？

6

在计算 perceptual loss 的时候，需要从一个训练好的 VGG16 或者 VGG19 的中间层提取出待测图像的特征并进行比较。在 PyTorch 中，已经训练好的网络模型很可能是通过 `nn.Sequetial` 来定义的，中间层的名字未知，该如何进行提取？ How to extract the features of an image from a trained model in PyTorch? https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119 VGG16 Features ```...

计算机中浮点数的阶码为什么用”移码“表示？

2

浮点数的表示为： |+/-|----exp----|------------frac--------------| 分为符号位、阶码（exp）、尾数（frac）三部分，其中阶码部分采用了移码（即符号位也取反的补码） float_num = +/- 1.frac * 2^exp 例如，7.0 = 1.75 * 2^2，对应的二进制码为：`01000000111000000000000000000000`。

Python 导包机制？

1

总结 Python 导包机制。 注意下划线开头的“匿名包”问题。

```C++ #include using namespace std; class Sample { public: int v; Sample() {}; Sample(int n) : v(n) {} Sample(Sample &x) { v = 2 + x.v; } }; Sample PrintAndDouble(Sample...