MagicSource

icnet error (icnet return tuple but not write that logic)

14

Hi, icnet returned a tuple when training.... but when calculating loss, it directly get size from tuple and got this error: ``` Traceback (most recent call last): File "train.py", line...

ICNet evaluation mean-IOU not increasing still exist

1

Hi, I previous opened an issue about ICNet evaluation mean-iou, it seems stopped at 0.25 approximately. ``` 5it [00:01, 2.34it/s]WARN: resizing labels yielded fewer classes 250it [00:23, 10.78it/s] Overall Acc:...

Error for cuda and cpu

8

``` /pytorch-seq2seq/seq2seq/models/EncoderRNN.py", line 68, in forward embedded = self.embedding(input_var) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 479, in __call__ result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/sparse.py", line 113, in forward self.norm_type, self.scale_grad_by_freq, self.sparse) File "/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py",...

unable to train biaobei

1

``` mandarin-tts/mtts/models/layers.py", line 91, in forward output = output.permute(1, 2, 0, 3).contiguous().view(sz_b, len_q, -1) # b x lq x (n*dv) RuntimeError: cannot reshape tensor of 0 elements into shape [0,...

when will the source code release?

3

when will the source code release?

why not using git push your code?

5

release via zip file is not a wise solution.

How to fitting on BFM07 front face model?

1

Hi, I have a mesh generated from deep3dface reconstruction model. It has texture and a BFM07 face, I want fitting it to FLAME and using the same texture on flame...

Does fitting like smplifyx still needed for TCMR?

13

https://github.com/vchoutas/smplify-x Like smplify-x, it will using a traning loop to fitting the shape, does it still needed such a step for TCMR since it already output 3d keypoints and shape....

what's the difference between Regressor and HMR?

1

what's the difference between Regressor and HMR? they seems output same thing.

Hi, I try to run tracking with localization but it crashed, so I run it using static, however, here is the result:  As you can see, the result are...