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 2021-02-16 10:27:41 -08:00 committed by GitHub
parent 9de2ec5e44
commit 361fd0fc40
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -7,7 +7,7 @@
* AGC w/ default clipping factor `--clip-grad .01 --clip-mode agc`
* PyTorch global norm of 1.0 (old behaviour, always norm), `--clip-grad 1.0`
* PyTorch value clipping of 10, `--clip-grad 10. --clip-mode value`
* AGC performance is definitely sensitive to the clipping factor. More experimentation needed to determine good values for smaller batch sizes and optimizers besides those in paper. So far I've found .001-.005 is necessary for stable RMSProp training.
* AGC performance is definitely sensitive to the clipping factor. More experimentation needed to determine good values for smaller batch sizes and optimizers besides those in paper. So far I've found .001-.005 is necessary for stable RMSProp training w/ NFNet/NF-ResNet.
### Feb 12, 2021
* Update Normalization-Free nets to include new NFNet-F (https://arxiv.org/abs/2102.06171) model defs