RAD-NeRF
RAD-NeRF copied to clipboard
ashawkey
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
I tried a command line down below: `python test.py --pose data/obama/obama.json --ckpt pretrained/obama_eo.pth --aud data/obama/trump_eo.npy --workspace trial_obama/ -O --torso` ``` Namespace(H=450, O=True, W=450, amb_dim=2, asr=False, asr_model='cpierse/wav2vec2-large-xlsr-53-esperanto', asr_play=False, asr_save_feats=False, asr_wav='', att=2,...
Looking in indexes: https://mirrors.aliyun.com/pypi/simple Processing ./freqencoder Preparing metadata (setup.py) ... done Building wheels for collected packages: freqencoder Building wheel for freqencoder (setup.py) ... error error: subprocess-exited-with-error × python setup.py bdist_wheel...
when I run the project in colab, the error's occurred in the process:(It's the error message) ``` Processing ./freqencoder Preparing metadata (setup.py) ... done Building wheels for collected packages: freqencoder...
Does anyone know how to generate a video by just inputting audio when reasoning?
你好，想请教一下，为何我训练的视频背景会抖动很厉害 训练命令：python main.py data/May/ --workspace trial_May/ -O --iters 200000 以下是训练参数：    下面是模型训练完的测试结果 https://github.com/ashawkey/RAD-NeRF/assets/11584869/fc3fb595-3c93-4bee-be6b-41b0721bff0f
>python main.py data/vrhm/ --workspace trial_vrhm/ -O --iters 200000 WARNING:tensorflow:From e:\python310\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. Namespace(path='data/vrhm/', O=True, test=False, test_train=False, data_range=[0, -1], workspace='trial_vrhm/', seed=0, iters=200000, lr=0.005, lr_net=0.0005,...
I saw in the document that you can use --preload 2 to make the training faster, but when I run it with a server with 3090 and 80G memory, it...
