Rui Shi

icon company Shanghai Jiao Tong University icon location Shanghai, China icon location M.S. student at Shanghai Jiao Tong University. Computer Vision & Graphics.

Results 4 comments of Rui Shi

Not good result on DTU dataset

> I use you code on DTU dataset, however, the generated meshes are different from ground truth meshes. Would I need to change the default config or change the parameters...

why i can't get glossy results when training using blender images?

> > Hi, > > It's very hard for me to judge what could be problematic in your case without any visuals. > > Can you try the following things...

Create a custom class like PathMNIST with custom data.

Certainly. You can modify the dataset class in [`dataset.py`](https://github.com/MedMNIST/MedMNIST/blob/main/medmnist/dataset.py) as you will.

Training Settings for MedMNIST Experiments

The results can be reproduced by default. Just like `python train_and_eval_pytorch.py --data_flag pathmnist` for three-channel datasets, or `python train_and_eval_pytorch.py --data_flag breastmnist --as_rgb` for single-channel ones.