DJW c16313bb6a 第一次提交 | 9 månader sedan | |
---|---|---|
.. | ||
README.md | 9 månader sedan | |
retinanet_timm-efficientnet-b1_fpn_1x_coco.py | 9 månader sedan | |
retinanet_timm-tv-resnet50_fpn_1x_coco.py | 9 månader sedan |
PyTorch Image Models (timm
) is a collection of image models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts that aim to pull together a wide variety of SOTA models with ability to reproduce ImageNet training results.
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
---|---|---|---|---|---|---|---|
R-50 | pytorch | 1x | config | ||||
EfficientNet-B1 | - | 1x | config |
MMDetection supports timm backbones via TIMMBackbone
, a wrapper class in MMClassification.
Thus, you need to install mmcls
in addition to timm.
If you have already installed requirements for mmdet, run
pip install 'dataclasses; python_version<"3.7"'
pip install timm
pip install 'mmcls>=0.20.0'
See this document for the details of MMClassification installation.
backbone out_channels
and backbone out_strides
in your log, and modify model.neck.in_channels
and model.backbone.out_indices
if necessary.features_only=True
, add custom_hooks = []
to your config to disable NumClassCheckHook
.@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/rwightman/pytorch-image-models}}
}