Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix bug for autoslim #511

Merged
merged 2 commits into from
Apr 17, 2023
Merged

fix bug for autoslim #511

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8f4ea90
fix bug for autoslim
Apr 17, 2023
3fd05e1
delete resnet50 for dmcp
Apr 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions configs/nas/mmcls/autoslim/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,11 +60,11 @@ CUDA_VISIBLE_DEVICES=0 PORT=29500 ./tools/dist_test.sh \

### Subnet retrain

| Supernet | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download | Subnet | Remark |
| :----------------- | :-------: | -------: | :-------: | :-------: | :---------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------: |
| MobileNet v2(x1.5) | 6.5 | 0.53 | 74.23 | 91.74 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.53M_acc-74.23_20211222-e5208bbd.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.53M_acc-74.23_20211222-e5208bbd_channel_cfg.yaml) | official channel cfg |
| MobileNet v2(x1.5) | 5.77 | 0.32 | 72.73 | 90.83 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.32M_acc-72.73_20211222-b5b0b33c.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.32M_acc-72.73_20211222-b5b0b33c_channel_cfg.yaml) | official channel cfg |
| MobileNet v2(x1.5) | 4.13 | 0.22 | 71.39 | 90.08 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.22M_acc-71.39_20211222-43117c7b.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.22M_acc-71.39_20211222-43117c7b_channel_cfg.yaml) | official channel cfg |
| Supernet | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download | Subnet | Remark |
| :----------------- | :-------: | -------: | :-------: | :-------: | :---------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------: |
| MobileNet v2(x1.5) | 6.5 | 0.53 | 74.23 | 91.74 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v1/autoslim/autoslim_mbv2_subnet_8xb256_in1k_flops-530M_acc-74.23_20220715-aa8754fe.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.53M_acc-74.23_20211222-e5208bbd_channel_cfg.yaml) | official channel cfg |
| MobileNet v2(x1.5) | 5.77 | 0.32 | 72.73 | 90.83 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v1/autoslim/autoslim_mbv2_subnet_8xb256_in1k_flops-320M_acc-72.73_20220715-9aa8f8ae.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.32M_acc-72.73_20211222-b5b0b33c_channel_cfg.yaml) | official channel cfg |
| MobileNet v2(x1.5) | 4.13 | 0.22 | 71.39 | 90.08 | [config](./autoslim_mbv2_subnet_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmrazor/v1/autoslim/autoslim_mbv2_subnet_8xb256_in1k_flops-220M_acc-71.4_20220715-9c288f3b.pth) \| [log](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1kautoslim_mbv2_subnet_8xb256_in1k_paper_channel_cfg.log.json) | [channel](https://download.openmmlab.com/mmrazor/v0.1/pruning/autoslim/autoslim_mbv2_subnet_8xb256_in1k/autoslim_mbv2_subnet_8xb256_in1k_flops-0.22M_acc-71.39_20211222-43117c7b_channel_cfg.yaml) | official channel cfg |

Note that we ran the official code and the Top-1 Acc of the models with official
channel cfg are 73.8%, 72.5% and 71.1%. And there are 3 differences between our
Expand Down
17 changes: 10 additions & 7 deletions configs/pruning/mmcls/dmcp/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,14 +30,17 @@ GPUS=32 sh tools/slurm_train.sh $PARTITION $JOB_NAME \

### 1.Classification

| Dataset | Supernet | Flops(M) | Top-1 (%) | Top-5 (%) | config | Download | Remark |
| :------: | :---------: | :-------------: | :-------: | :-------: | :----------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------: |
| ImageNet | ResNet50 | 4.09G(Supernet) | 77.46 | 93.55 | - | - | - |
| Dataset | Supernet | Flops(M) | Top-1 (%) | Top-5 (%) | config | Download | Remark |
| :------: | :---------: | :------------: | :-------: | :-------: | :------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------: |
| ImageNet | MobilenetV2 | 319M(Supernet) | 72.30 | 90.42 | - | - | - |
| ImageNet | MobilenetV2 | 209M(Subnet) | 71.94 | 90.05 | [config](./dmcp_mbv2_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/DMCP_MBV2_200M.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/dmcp_mobilenetv2_supernet_32xb64_target_flops_200m_20230129_184919.log) | [arch](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/DMCP_MBV2_200M.json) |
| ImageNet | MobilenetV2 | 102M(Subnet) | 67.22 | 88.61 | [config](./dmcp_mbv2_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/100M/DMCP_MBV2_100M.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/100M/dmcp_mobilenetv2_supernet_32xb64_target_flops_100m_20230129_184919.log) | [arch\*](./DMCP_MBV2_100M.json) |

<!-- The result of Resnet50 has bugs. -->

<!-- | ImageNet | ResNet50 | 4.09G(Supernet) | 77.46 | 93.55 | - | - | - |
| ImageNet | ResNet50 | 2.07G(Subnet) | 76.11 | 93.01 | [config](./dmcp_resnet50_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/2G/DMCP_R50_2G.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/2G/dmcp_resnet50_supernet_32xb64_target_flops_2g_20230129_112944.log) | [arch\*](./DMCP_R50_2G.json) |
| ImageNet | ResNet50 | 1.05G(Subnet) | 74.12 | 92.33 | [config](./dmcp_resnet50_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/DMCP_R50_1G.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/dmcp_resnet50_supernet_32xb64_target_flops_1g_20230107_223552.log) | [arch](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/DMCP_R50_1G.json) |
| ImageNet | MobilenetV2 | 319M(Supernet) | 72.30 | 90.42 | - | - | - |
| ImageNet | MobilenetV2 | 209M(Subnet) | 71.94 | 90.05 | [config](./dmcp_mbv2_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/DMCP_MBV2_200M.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/dmcp_mobilenetv2_supernet_32xb64_target_flops_200m_20230129_184919.log) | [arch](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/200M/DMCP_MBV2_200M.json) |
| ImageNet | MobilenetV2 | 102M(Subnet) | 67.22 | 88.61 | [config](./dmcp_mbv2_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/100M/DMCP_MBV2_100M.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/mobilenetv2/100M/dmcp_mobilenetv2_supernet_32xb64_target_flops_100m_20230129_184919.log) | [arch\*](./DMCP_MBV2_100M.json) |
| ImageNet | ResNet50 | 1.05G(Subnet) | 74.12 | 92.33 | [config](./dmcp_resnet50_subnet_32xb64.py) | [model](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/DMCP_R50_1G.pth) / [log](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/dmcp_resnet50_supernet_32xb64_target_flops_1g_20230107_223552.log) | [arch](https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/1G/DMCP_R50_1G.json) | -->

**Note**

Expand Down
18 changes: 9 additions & 9 deletions configs/pruning/mmcls/dmcp/metafile.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
Models:
- Name: dmcp_resnet50_subnet_32xb64
In Collection: DMCP
Config: configs/pruning/mmcls/dmcp/dmcp_resnet50_subnet_32xb64.py
Weights: https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/2G/DMCP_R50_2G.pth
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 76.11
# - Name: dmcp_resnet50_subnet_32xb64
# In Collection: DMCP
# Config: configs/pruning/mmcls/dmcp/dmcp_resnet50_subnet_32xb64.py
# Weights: https://download.openmmlab.com/mmrazor/v1/pruning/dmcp/resnet50/2G/DMCP_R50_2G.pth
# Results:
# - Task: Image Classification
# Dataset: ImageNet-1k
# Metrics:
# Top 1 Accuracy: 76.11
- Name: dmcp_mbv2_subnet_32xb64
In Collection: DMCP
Config: configs/pruning/mmcls/dmcp/dmcp_mbv2_subnet_32xb64.py
Expand Down
Loading