HuanYu

Hi, if you install xformers by pip install -U xformers --index-url https://download.pytorch.org/whl/cu118 it'll install xformers for torch2.2.0+cu118,so you may need to update your torch to this version.

大佬，请问能向你要一份数据集(或者是数据集格式)参考一下吗？感谢您，我的邮箱[email protected]

> my real case:  [wizard.zip](https://github.com/VAST-AI-Research/TripoSR/files/14494149/wizard.zip) > > very good! this is sota, only one, I tried 100+ open-source! 您好，这是你的输入图像吗？我下载查看了你的模型，贴图部分并没有这么精细，还是说贴图部分有能够提高的方法？

> ```python > from network import TSR > print('=========Model Class initialized========>>>>>>') > # print("======torch.__version__=======>>>>>>>", torch.__version__) > model = TSR(radius=0.87, valid_thresh=0.01, num_samples_per_ray=128, img_size=512, depth=12, embed_dim=768, num_layers=16, num_channels=1024, cross_attention_dim=768) > # #...

> @FisherYuuri 我在修改，我发上来的版本还是支持对原始的checkpoint的加载。就是类和变量名字没有变化。 我的代码相对简洁一点。 期待大佬的新修改！You are the real hero！

same question