fighting!

Results 19 issues of fighting!

I add some code in ddpm to freeze crossattention layer like following: ``` if without_crossattn: for m in self.modules(): if isinstance(m, CrossAttention): for para in m.parameters(): para.requires_grad=False ``` and I...

你好, 看了你的代码后,发现逻辑很清晰? 但是有点疑惑的是 好像代码中并没有体现 paper 3.3 节中的Differentiable Formula的求导过程? 是不需要使用到这一步吗,因为我只看到了你用adam 优化器在优化template 的 intersection 点.

I am confused about first_layer_sine_init, where you set W~uniform(-1/n,1/n). As we know, input is X-uniform(-1,1) so has var[x] = (2^2/12)=1/3. and after FC layer, var[sin(30*Wx+b)] = 30^2*n*(1/3)*(c^2/3) =1? so how...

Hi, thanks for your great work. There are some questions I feel confused. First, you said' New objects can be given to the model by providing the path to the...

Thanks for your great job. When I run your code to fit my video. there has some problem, in train_one_epoch() I debug it and find the bug happened when self._num_faces_per_mesh.unique()...

bug

Thanks for your API. When I run your code ``` python3 scripts/start_xserver.py start ``` in my docker environment. I have following error: parse_vt_settings: Cannot open /dev/tty0 (No such file or...

Hi, congrats on Free3D, great work! I saw your paper does not demonstrate the details about pseudo-3DAttention, such as the channel of the Linear Project Layer.

Thanks for your work! I predict long sleeve cloth from your code, but only predict short sleeve type from upper-clothed class? Dose upper-clothed only support the short-sleeve category?