Duan Zhichao

我遇到了同样的问题，现在已经解决了。我在hf上分享了代码，希望有所帮助。 https://huggingface.co/datasets/THUDM/ImageRewardDB/discussions/3

Hi, @LucioSunj @Bearick. Is this issue still occurring? Everything is working fine on my end. I can't reproduce your issue, and I can't deduce the possible cause from the information...

@yifanlu0227 Thanks for your comment, this can be a solution when meeting this problem. I did find some discussions about `importlib` in the torchhub community, but I am unable to...

Since some operations in the network involve splitting into patches and up/down sampling, you need to ensure that the input's width and height are divisible by 28. > First, the...

> 1. should i use fine-tuning or train from scratch. > 2. Is the absence of any GT normals or GT semantic masks ok? > 3. Would i get worse...

Hi, @oywenjun11 1. All dataset classes inherit from [`BaseDataset`](https://github.com/YvanYin/Metric3D/blob/34afafe58d9543f13c01b65222255dab53333838/training/mono/datasets/__base_dataset__.py#L77). You can check how it loads data and inherit from it to implement your own `Dataset` class. If you do this,...

Hi, @oywenjun11 1. Synthetic data is also okay; 2. The model weights will not increase during training; they should always remain constant; 3. I will contact you via email for...

Hi! @DaDaDaBiuBiu > Could not download the pretrained checkpoints in _data_server_info/pretrained_weight.py_, is there any links on cloudstor? `data_server_info/pretrained_weight.py` indicates the path of backbone's pretrained weights. You can download it from...

see https://lilianweng.github.io/posts/2021-07-11-diffusion-models/#reverse-diffusion-process