We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
使用pnnx命令行分别对pt和onnx模型进行转换,
通过查看params文件,发现的确存在unsqueeze操作,但是在torch原模型中,已经将unsqueeze转换为tensor[None,:]或torch.stack();但是在params的文件中依然存在unsqueeze操作。
Activity