AI Enthusiast

Thanks for your nice work that makes me excited. I am fascinated your project and have been doing related work recently. When do you release the code?

Thanks for your nice work. I have a question: If I want to imitate the expression, head and body movement at the same time (Given a source full-body image, a...

Convert onnx multi-layer LSTM bug

7

**Describe the bug** Hello, I can convert one-layer LSTM and multilayer LSTMs to tensorflow. However, the results between onnx and onnx-tf are not equal when using multi-layer LSTM, while the...

imageio.mimread() has read over 256000000B of image data

5

Thanks for your nice work! I met a problem while I'm training on the TED dataset (Two 32G GPUs). ```python File "Thin-Plate-Spline-Motion-Model/train.py", line 55, in train for x in dataloader:...

Hello, I have a question...

1

Hi, Sun Sining: I want to ask you a question in the line 103 of local/gen_tfreords.py. The line "labels = np.concatenate((s1_abs * np.cos(mix_angle - s1_angle), s2_abs * np.cos(mix_angle - s2_angle)),...

Does anyone implement the training code of this project?

2

It's a pretty good work. Thank author for sharing code. Does anyone implement the training code of this project? Can you share it?

Given input size: (192x2x2). Calculated output size: (192x0x0). Output size is too small

9

Hello, thanks for your nice work. When I run the code on my video, there is a problem appearing. ```bash ~/MyCode/RAD_NeRF$ python main.py data/person_video1_25fps_512x512/ --workspace person_video1/ -O --iters 250000 --finetune_lips...

indices_.reshape(indices_.shape[0], 1024, -1, indices_.shape[2]) error in run_nerf_deform.py

8

Nice work! Thanks your sharing code. When I rendering.sh one video, there is a problem in this line: ``` try: indices_ = indices_.reshape(indices_.shape[0], 1024, -1, indices_.shape[2]) except: pdb.set_trace() ``` I...

使用最新的代码，并开启 sequence_parallel_size，有报错如下： ```bash ModuleNotFoundError: No module named 'torch.distributed.device_mesh' ``` 请问需要安装torch最低版本哪个？