Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Could you tell me where to download "omnidata_dpt_depth_v2.ckpt"? #15

Closed
MnKnight1 opened this issue Dec 18, 2023 · 3 comments
Closed

Comments

@MnKnight1
Copy link

I see that I have to download omnidata_dpt_depth_v2.ckpt in GaussianEditor-master/threestudio/utils/dpt.py
Because of the server network, I had to load it locally and could not download it online,could you tell me where to download "omnidata_dpt_depth_v2.ckpt"?Is it same as https://github.com/ashawkey/stable-dreamfusion/blob/5550b91862a3af7842bb04875b7f1211e5095a63/readme.md?plain=1#L68

         if self.mode == "depth":
            path = ".cache/dpt/omnidata_dpt_depth_v2.ckpt"
            self.model = DPTDepthModel(backbone="vitb_rn50_384")
            self.aug = transforms.Compose(
                [
                    transforms.Resize((384, 384)),
                    transforms.Normalize(mean=0.5, std=0.5),
                ]
            )
        elif self.mode == "normal":
            path = ".cache/dpt/omnidata_dpt_normal_v2.ckpt"
            self.model = DPTDepthModel(backbone="vitb_rn50_384", num_channels=3)
            self.aug = transforms.Compose(
                [
                    transforms.Resize((384, 384)),
                ]
            )
@zhanghongyong123456
Copy link

I see that I have to download omnidata_dpt_depth_v2.ckpt in GaussianEditor-master/threestudio/utils/dpt.py Because of the server network, I had to load it locally and could not download it online,could you tell me where to download "omnidata_dpt_depth_v2.ckpt"?Is it same as https://github.com/ashawkey/stable-dreamfusion/blob/5550b91862a3af7842bb04875b7f1211e5095a63/readme.md?plain=1#L68

         if self.mode == "depth":
            path = ".cache/dpt/omnidata_dpt_depth_v2.ckpt"
            self.model = DPTDepthModel(backbone="vitb_rn50_384")
            self.aug = transforms.Compose(
                [
                    transforms.Resize((384, 384)),
                    transforms.Normalize(mean=0.5, std=0.5),
                ]
            )
        elif self.mode == "normal":
            path = ".cache/dpt/omnidata_dpt_normal_v2.ckpt"
            self.model = DPTDepthModel(backbone="vitb_rn50_384", num_channels=3)
            self.aug = transforms.Compose(
                [
                    transforms.Resize((384, 384)),
                ]
            )

you can download https://huggingface.co/camenduru/PeRF/tree/main

@heheyas
Copy link
Collaborator

heheyas commented Dec 20, 2023

Check #10 for manually downloading the weight for the depth estimator.

Reference

@MnKnight1
Copy link
Author

Thank you for your help!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants