ZJYang

在https://github.com/ultralytics/yolov5下得到的onnx模型的输出结果是(1, 3, 80, 80, 85)，请问是哪个环节出现问题了

已经获得输出正确的onnx模型了，十分感谢您的帮助！！！需要用您提供的yolov5框架来转换模型，而不是官方的yolov5。 另外，您可以在README中修改一下开头部分的表述，可以参考如下： 2.Export ONNX Model git clone https://github.com/linghu8812/yolov5.git run export_onnx.py in https://github.com/linghu8812/yolov5/models to generate yolov5s.onnx and so on. attention, do not convert the model by using https://github.com/ultralytics/yolov5, otherwise you may...

I deal with this problem in the following way: 1. define the venv path in webui-user.bat, such as 'set VENV_DIR=D:\Anaconda3\envs\torch', this is the path of your conda environment with torch....

We recommend you to use fp16.

看起来应该是输入视频2fe655a671ecb61f93d54d6ad2729951.mp4中存在一些帧无法检测到人脸，我们会尽快修复这一bug。感谢提出！

https://github.com/Zejun-Yang/AniPortrait/blob/4de88f12a24cff107e7bce19194a0e9e05dab2be/scripts/generate_ref_pose.py#L60 已修复，可更新代码。

You can check with the following steps: 1. make sure pretrained_model/wav2vec2-base-960h/config.json is complete 2. make ure pretrained_model/wav2vec2-base-960h is complete, or you can manual download wav2vec2-base-960h 3. update the veision of...

You can try to refer to our dataset processing code (scripts/preprocess_dataset.py).

报错发生在加载模型权重的位置。运行代码前需要手动下载我们的[模型权重](https://huggingface.co/ZJYang/AniPortrait/tree/main)以及其他依赖模型，具体可参考https://github.com/Zejun-Yang/AniPortrait?tab=readme-ov-file#download-weights

为了确保代码顺利运行，请完整下载[stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)并拷贝到pretrained_model路径下。如果内存不足，您也可以根据代码实际调用文件情况，删除该文件夹下非必要的参数文件。 Please download all the pre-trained model files according to [README](https://github.com/Zejun-Yang/AniPortrait?tab=readme-ov-file#download-weights). So that you can address the model loading issue. Also, the command of 'git lfs pull' is used to...