mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Ross Wightman 2019-04-21 16:49:00 -07:00 committed by GitHub
parent bc264269c9
commit 1cf3ea0467
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -29,7 +29,12 @@ I've included a few of my favourite models, but this is not an exhaustive collec
* PNasNet (from [Cadene](https://github.com/Cadene/pretrained-models.pytorch))
* DPN (from [me](https://github.com/rwightman/pytorch-dpn-pretrained), weights hosted by Cadene)
* DPN-68, DPN-68b, DPN-92, DPN-98, DPN-131, DPN-107
* My generic MobileNet (GenMobileNet) - A generic model that implements many of the mobile optimized architecture search derived models that utilize similar DepthwiseSeparable, InvertedResidual, etc blocks
* MNASNet B1, A1 (Squeeze-Excite), and Small
* MobileNet-V1
* MobileNet-V2
* ChamNet (details hard to find, currently an educated guess)
* FBNet-C (TODO A/B variants)
## Features
Several (less common) features that I often utilize in my projects are included. Many of their additions are the reason why I maintain my own set of models, instead of using others' via PIP:
* All models have a common default configuration interface and API for
@ -58,7 +63,7 @@ I've leveraged the training scripts in this repository to train a few of the mod
## TODO
A number of additions planned in the future for various projects, incl
* Select some parameter efficient models for mobile/embedded applications
* Find optimal training hyperparams and create/port pretraiend weights for the generic MobileNet variants
* Do a model performance (speed + accuracy) benchmarking across all models (make runable as script)
* More training experiments
* Make folder/file layout compat with usage as a module