BugNet
BugNet
> 可以检查模型文件大小是否正常，当git lfs clone过程存在异常时，可能出现文件下载不完整的问题。 请问我需要下载链接中的全部权重文件，还是仅需下载readme中列出的如下权重文件呢？ ``` ./pretrained_weights/ |-- image_encoder | |-- config.json | `-- pytorch_model.bin |-- sd-vae-ft-mse | |-- config.json | |-- diffusion_pytorch_model.bin | `-- diffusion_pytorch_model.safetensors |-- stable-diffusion-v1-5 | |--...
问题已经解决，似乎是环境配置的问题。
我也遇到了同样的问题，推理结果为噪声。 https://github.com/Zejun-Yang/AniPortrait/assets/41713524/3612163f-e866-44de-bab3-650782dd5bb5 log如下： ``` python -m scripts.pose2vid --config ./configs/prompts/animation.yaml -W 512 -H 512 Some weights of the model checkpoint were not used when initializing UNet2DConditionModel: ['conv_norm_out.weight, conv_norm_out.bias, conv_out.weight, conv_out.bias'] WARNING:...
> solo_solo_pose1_512x512_3_1438_noaudio.mp4 > 我们复现了您反馈的问题。 触发条件没有正确加载我们预训练权重，导致模型参数跟我们的任务不匹配。 您可以重新下载我们的预训练模型，并确保其位于正确路径下，详情参考README.md。 https://huggingface.co/ZJYang/AniPortrait/tree/main 感谢您的回复，请问复现的这段视频是哪部分模型参数没有加载正确呢？我参考了本repo中的预训练模型目录，我的目录如下，看上去和您给的readme一致： 
> May be the max value of sampe_idx is len(dataset_len) - 1? Yes. Randint function chooses from [0, dataset_len], which includes idx==dataset_len, thus causing the problem.
I've also encountered the problem. I suggest you check if the data are properly normalized and try adding layernorms before calculating attention scores.
> May I ask how did you normalize it, I normalized the vertex values to [0,1] using max-min. Did you end up getting good results? Besides raw data normalization, you...
> Besides raw data normalization, you could try adding nn.layernorm in the original faceformer network before the transformer decoder layer, or simply passing norm_first=True to faceformer.decoder_layer during initiliaztion. I haven't...