Weijian Deng

Thank you very much for sharing the wonderful code! I meet a question when running the code: while I can get a similar accuracy on Segmentation (43.5 on mIoU) using...

COCO Setup

6

Thank you for your attention! Please download the datasets for coco classification setup in [here](https://anu365-my.sharepoint.com/:u:/g/personal/u6854640_anu_edu_au/EVwMYZdEYodCtRtGeiVR1doBUnExqoYJGOrvLzwFw28j_w?e=9GS2zN). The zip file contains two parts. **The first part** is coco datasets: 1) a training...

**[Pretrained MNIST model](https://drive.google.com/file/d/1-_M2FAY8stVhfo6uQv6bpdn-6yBEMLfp/view?usp=sharing)** **USPS** **[DATASET](https://drive.google.com/file/d/1Bo6KlZbNEk-pNae9JI2uWAeVtgxmWKPS/view?usp=sharing)** ``` class USPS(data.Dataset): def __init__(self, root, train=True, transform=None, target_transform=None): super(USPS, self).__init__() self.root = root self.transform = transform self.target_transform = target_transform filename = 'usps.bz2' if train...

Hello! Have you tried your method on other tasks, e.g., object detection, image classification? THX.

Data process

4

Thank you for your nice work! I might missed something so I met an issue with the data process: First case: I use `--data_format colmap` to load my own data...