mmpretrain

mmpretrain copied to clipboard

Update regnet.py

6

## Motivation In the example comment to print out the different layers of outputs, we need to indicate the `out_indices` to (0,1,2,3) to see all backbone layers output as the...

timothylimyl

Dummy forward

2

We should add `forward_dummy` to query flops by mmcv (https://github.com/open-mmlab/mmcv/blob/master/mmcv/cnn/utils/flops_counter.py#L38). Althugh we already have `extract_feat`, but it's not sync with mmdetection(https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/detectors/single_stage.py#L48). we should sync both projects since many people may...

twmht

**This is a PR for mmcls 1.x** ## Motivation upodate dataset tutorial(en/zh_CN). ## Checklist **Before PR**: - [ ] Pre-commit or other linting tools are used to fix the potential...

Ezra-Yu

[Feature]: Support mmclassification with MLU

2

## Motivation Support training and distributed-training on MLU device. ## Modification Add MLUDataParallel and MLUDistributedDataParallel support to model wrapper. Add MLU device to sync_random_seed. ## BC-breaking (Optional) Only Support MLU...

Qiza-lyhm

[Feature] Support EfficientFormer

1

## Motivation Support EfficientFormer, [Arxiv](https://arxiv.org/abs/2206.01191) | [Github](https://github.com/snap-research/EfficientFormer) ## Use cases (Optional) ``` Example: >>> from mmcls.models import EfficientFormer >>> import torch >>> inputs = torch.rand((1, 3, 224, 224)) >>> #...

Ezra-Yu

Add support of EdgeNeXt

2

#930 Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not...

tonysy

train problem

3

推荐使用英语模板 General question，以便你的问题帮助更多人。 ### 首先确认以下内容 - 我已经查询了相关的 issue，但没有找到需要的帮助。 - 我已经阅读了相关文档，但仍不知道如何解决。 ### 描述你遇到的问题 ValueError: num_samples should be a positive integer value, but got num_samples= 0 ### 相关信息 1. `pip list |...

cj17SUI

[Feature] MultiheadAttentionPooling

5

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

chagmgang

Why is the performance of CSPNet much higher than that of the paper？

1


ioir123ju

Roadmap of MMClassification

22

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here. You can either: 1. Suggest a new...

hellock