mirrors
/
mmpretrain
mirror of https://github.com/open-mmlab/mmpretrain.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update checkpoint path of ResNet-50 on CUB dataset

pull/759/head
mzr1996 2022-03-31 10:21:02 +08:00
parent 349ec86801
commit f0ee5dcb2a
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
configs/resnet/README.md
View File

@ -19,7 +19,7 @@ The pre-trained models on ImageNet-21k are used to fine-tune, and therefore don'
| Model | resolution | Params(M) | Flops(G) | Download |
|:---------------:|:-----------:|:---------:|:---------:|:--------:|
| ResNet-50-mill | 224x224 | 86.74 | 15.14 | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_mill_3rdparty_in21k_20220307-bdb3a68b.pth)|
| ResNet-50-mill | 224x224 | 86.74 | 15.14 | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth)|
*The "mill" means using the mutil-label pretrain weight from [ImageNet-21K Pretraining for the Masses](https://github.com/Alibaba-MIIL/ImageNet21K).*
@ -69,7 +69,7 @@ The pre-trained models on ImageNet-21k are used to fine-tune, and therefore don'
| Model | Pretrain | resolution | Params(M) | Flops(G) | Top-1 (%) | Config | Download |
|:---------------------:|:------------:|:---------:|:---------:|:--------:|:---------:|:---------:|:---------:|
| ResNet-50 | [ImageNet-21k-mill](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_mill_3rdparty_in21k_20220307-bdb3a68b.pth) | 448x448 | 23.92 | 16.48 | 88.45 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb8_cub.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.log.json) |
| ResNet-50 | [ImageNet-21k-mill](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth) | 448x448 | 23.92 | 16.48 | 88.45 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_8xb8_cub.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth) | [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.log.json) |
## Citation

2
configs/resnet/metafile.yml
View File

@ -385,6 +385,6 @@ Models:
Metrics:
Top 1 Accuracy: 88.45
Task: Image Classification
Pretrain: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_mill_3rdparty_in21k_20220307-bdb3a68b.pth
Pretrain: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth
Config: configs/resnet/resnet50_8xb8_cub.py

2
configs/resnet/resnet50_8xb8_cub.py
View File

@ -4,7 +4,7 @@ _base_ = [
]
# use pre-train weight converted from https://github.com/Alibaba-MIIL/ImageNet21K # noqa
checkpoint = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_mill_3rdparty_in21k_20220307-bdb3a68b.pth' # noqa
checkpoint = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth' # noqa
model = dict(
type='ImageClassifier',