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

Add native PyTorch EfficientNet B1 and B2 weights. Not quite where I want them, but hitting the brick wall and moving on to other projects...

Browse Source
This commit is contained in:
Ross Wightman 2019-06-24 13:12:04 -07:00
parent a0275cfa2f
commit 13c19e213d
2 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -78,6 +78,16 @@ I've leveraged the training scripts in this repository to train a few of the mod
| spnasnet_100 | 74.084 (25.916) | 91.818 (8.182) | 4.42M | bilinear | | spnasnet_100 | 74.084 (25.916) | 91.818 (8.182) | 4.42M | bilinear |
| seresnet18 | 71.742 (28.258) | 90.334 (9.666) | 11.8M | bicubic | | seresnet18 | 71.742 (28.258) | 90.334 (9.666) | 11.8M | bicubic |
#### @ 240x240
|Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling |
|---|---|---|---|---|
| efficientnet_b1 | 78.692 (21.308) | 94.086 (5.914) | 7.79M | bicubic |
#### @ 260x260
|Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling |
|---|---|---|---|---|
| efficientnet_b2 | 79.668 (20.332) | 94.634 (5.366) | 9.11M | bicubic |
### Ported Weights ### Ported Weights
#### @ 224x224 #### @ 224x224

12
timm/models/gen_efficientnet.py
View File

@ -81,15 +81,17 @@ default_cfgs = {
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b0-d6904d92.pth', url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b0-d6904d92.pth',
interpolation='bicubic'), interpolation='bicubic'),
'efficientnet_b1': _cfg( 'efficientnet_b1': _cfg(
url='', input_size=(3, 240, 240), pool_size=(8, 8)), url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b1-533bc792.pth',
input_size=(3, 240, 240), pool_size=(8, 8), interpolation='bicubic', crop_pct=0.882),
'efficientnet_b2': _cfg( 'efficientnet_b2': _cfg(
url='', input_size=(3, 260, 260), pool_size=(9, 9)), url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnet_b2-d4105846.pth',
input_size=(3, 260, 260), pool_size=(9, 9), interpolation='bicubic', crop_pct=0.890),
'efficientnet_b3': _cfg( 'efficientnet_b3': _cfg(
url='', input_size=(3, 300, 300), pool_size=(10, 10)), url='', input_size=(3, 300, 300), pool_size=(10, 10), crop_pct=0.904),
'efficientnet_b4': _cfg( 'efficientnet_b4': _cfg(
url='', input_size=(3, 380, 380), pool_size=(12, 12)), url='', input_size=(3, 380, 380), pool_size=(12, 12), crop_pct=0.922),
'efficientnet_b5': _cfg( 'efficientnet_b5': _cfg(
url='', input_size=(3, 456, 456), pool_size=(15, 15)), url='', input_size=(3, 456, 456), pool_size=(15, 15), crop_pct=0.934),
'tf_efficientnet_b0': _cfg( 'tf_efficientnet_b0': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_b0-0af12548.pth', url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_b0-0af12548.pth',
input_size=(3, 224, 224), interpolation='bicubic'), input_size=(3, 224, 224), interpolation='bicubic'),