Comments (2)
- 12 min per epoch sounds fast compared to my 2-3 GPU setups :) but yes, compared to ResNets they are suprisingly slow given how much smaller they are
- So far, my best results usually come in after 300-400 epochs with this model family and this training scheme, if you start seeing the validation loss and error definitively stop moving downwards (or start moving upwards) before this your hparams could use adjustment
- Being 3-4 pts from the end result at 80-100 epochs isn't out of the ordinary, the last 2/3 to 3/4 of the training is a pretty slow and boring grind
- I would raise your batch size, try and get into the 128-256 per GPU range. Synchronized BN is not enable by default (and I wouldn't bother enabling it) so the BN stats are only from one of your GPU, not the total.
- Enable AMP mixed precision training (
--amp
and install APEX), this will also speed things up on a volta or turing card and allow you to target a larger batch / GPU if you can't hit the range above running at FP32. - your ema decay should be similar to mine with your GPU batch of 32, if you get it up to 128-256 per-GPU, try 0.999 to 0.998 range
- turn the color jitter way down as mentioned in other issues about this ... I've used .05-.07, but if you wanted to follow the original, they didn't appear to have any color augmentation enabled until their recent 'AutoAugment' training scheme was used
- make sure the
#kwargs['drop_connect_rate'] = 0.2
line in the gen_efficientnet.py for the model you're using is uncommented, I have no cmd line arg for this yet since it's specific to these models - you don't need so many workers per GPU (
-j 8
), if you've got lots and lots of cores, sure, but otherwise 4-6 is usually fine
I'm going to close this issue as we don't need multiple hparam threads open, but please update this issue or another if you find something that works
from pytorch-image-models.
This is very helpful!! I'll try them out and let you know if it still can't reproduce. Thanks again.
from pytorch-image-models.
Related Issues (20)
- By using timm.create, how to download weights from url instead of HF? HOT 2
- DropPath Implementation HOT 2
- [BUG] Changing patch size does not work with CLIP/OpenCLIP ViT HOT 1
- provide the pretrained model of cs3darknet_focus_s.c2ns_in1k
- [BUG] Scheduler implicitly do not change lr HOT 1
- ModelEmaV3 update doesn't copy model to the same device before averaging the weights HOT 1
- [BUG] Issue converting any of the maxvit models to tensorrt HOT 4
- [FEATURE] `features_only` method for ViT networks HOT 10
- [BUG] AttributeError: module 'torch._C' has no attribute 'set_grad_enabled'
- Pytorch classification vit_model.py Class PatchEmbed forward function features size could have some problems? HOT 2
- [BUG] Broken hrnet instantiation HOT 1
- Output dimension of FocalNet models does not match label dimension of ImageNet-22K-MS HOT 4
- [BUG] Issue title...UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed. This is not an error, but may impair performance. HOT 1
- [BUG] list_pretrained returns more models than list_models HOT 1
- [BUG] Mismatch in Swin Transformer pretrained weights mapping. HOT 2
- i want to load data not only .tar file but also .tar.gz HOT 1
- [BUG] There is the error in timm/train.py when i use the Webdataset (timm/imagent-w21-wds in huggingface) with class map HOT 9
- Rotary embeddings do not work properly in eva02_base_patch14_448.mim_in22k_ft_in1k HOT 3
- Missing features on "timm" package from pypi HOT 1
- [FEATURE] ImageNet1k weights for ViT Huge?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-image-models.