Skip to content

update performance info #822

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

Open
chenyang23333 wants to merge 5 commits into
base: main
Choose a base branch
from
Open

update performance info #822

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
0efefc9
update performance info (#819)
chenyang23333 Apr 3, 2025
a618777
update mindcv version
Apr 3, 2025
4559528
fix jit bug
Apr 3, 2025
8975035
update performance data 2
Apr 7, 2025
c0d49d2
update ckpt
Apr 9, 2025
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
4 changes: 1 addition & 3 deletions .github/workflows/publish.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,14 +18,12 @@ jobs:
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.8"
python-version: "3.9"

- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements/dev.txt
pip install "Pillow==9.1.1"
pip install "mindspore>=1.8,<=1.10"
pip install build twine
- name: Build package
run: |
Expand Down
13 changes: 3 additions & 10 deletions configs/bit/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,16 +69,9 @@ Our reproduced model performance on ImageNet-1K is reported as follows.

Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.

*coming soon*

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.


| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ------------ | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
| bit_resnet50 | 25.55 | 8 | 32 | 224x224 | O2 | 146s | 74.52 | 3413.33 | 76.81 | 93.17 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/bit/bit_resnet50_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/bit/BiT_resnet50-1e4795a4.ckpt) |


| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
| ----------- | ----- | ---------- | ---------- |-----------| ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- | -------- | -------- |
| bit | 8 | 32 | 224x224 | O2 | 171s | 60.48 | 4232.80 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/bit/bit_resnet50_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/bit/BiT_resnet50-77dcaf0f-910v2.ckpt) | 76.72 | 93.25 |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
Expand Down
9 changes: 3 additions & 6 deletions configs/cmt/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,13 +67,10 @@ Our reproduced model performance on ImageNet-1K is reported as follows.

Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.

*coming soon*
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | -------- | -------- |
| cmt | 8 | 128 | 224x224 | O2 | 1210s | 324.95 | 3151.25 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/cmt/cmt_small_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/cmt/cmt_small-6858ee22.ckpt) | 83.15 | 96.48 |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| cmt_small | 26.09 | 8 | 128 | 224x224 | O2 | 1268s | 500.64 | 2048.01 | 83.24 | 96.41 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/cmt/cmt_small_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/cmt/cmt_small-6858ee22.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
Expand Down
14 changes: 3 additions & 11 deletions configs/coat/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,17 +63,9 @@ Our reproduced model performance on ImageNet-1K is reported as follows.

Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.

*coming soon*


Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.




| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| coat_tiny | 5.50 | 8 | 32 | 224x224 | O2 | 543s | 254.95 | 1003.92 | 79.67 | 94.88 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_tiny_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/coat/coat_tiny-071cb792.ckpt) |
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------- | -------- | -------- |
| coat | 8 | 32 | 224x224 | O2 | 644s | 373.00 | 686.33 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_lite_tiny_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/coat/coat_tiny-dcca16b1-910v2.ckpt) | 79.27 | 94.29 |



Expand Down
7 changes: 0 additions & 7 deletions configs/convit/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,13 +80,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- |
| convit_tiny | 5.71 | 8 | 256 | 224x224 | O2 | 153s | 226.51 | 9022.03 | 73.79 | 91.70 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convit/convit_tiny_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/convit/convit_tiny-1961717e-910v2.ckpt) |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------- |
| convit_tiny | 5.71 | 8 | 256 | 224x224 | O2 | 133s | 231.62 | 8827.59 | 73.66 | 91.72 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convit/convit_tiny_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/convit/convit_tiny-e31023f2.ckpt) |


### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

Expand Down
6 changes: 0 additions & 6 deletions configs/convnext/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,12 +78,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
| ------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| convnext_tiny | 28.59 | 8 | 16 | 224x224 | O2 | 137s | 48.7 | 2612.24 | 81.28 | 95.61 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convnext/convnext_tiny_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/convnext/convnext_tiny-db11dc82-910v2.ckpt) |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
| convnext_tiny | 28.59 | 8 | 16 | 224x224 | O2 | 127s | 66.79 | 1910.45 | 81.91 | 95.79 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convnext/convnext_tiny_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/convnext/convnext_tiny-ae5ff8d7.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

Expand Down
6 changes: 0 additions & 6 deletions configs/convnextv2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,12 +77,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
| --------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
| convnextv2_tiny | 28.64 | 8 | 128 | 224x224 | O2 | 268s | 257.2 | 3984.44 | 82.39 | 95.95 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convnextv2/convnextv2_tiny_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/convnextv2/convnextv2_tiny-a35b79ce-910v2.ckpt) |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| --------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| convnextv2_tiny | 28.64 | 8 | 128 | 224x224 | O2 | 237s | 400.20 | 2560.00 | 82.43 | 95.98 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/convnextv2/convnextv2_tiny_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/convnextv2/convnextv2_tiny-d441ba2c.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

Expand Down
6 changes: 0 additions & 6 deletions configs/crossvit/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,12 +73,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- |
| crossvit_9 | 8.55 | 8 | 256 | 240x240 | O2 | 221s | 514.36 | 3984.44 | 73.38 | 91.51 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/crossvit/crossvit_9_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/crossvit/crossvit_9-32c69c96-910v2.ckpt) |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| crossvit_9 | 8.55 | 8 | 256 | 240x240 | O2 | 206s | 550.79 | 3719.30 | 73.56 | 91.79 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/crossvit/crossvit_9_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_9-e74c8e18.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

Expand Down
6 changes: 0 additions & 6 deletions configs/densenet/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,12 +82,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
| densenet121 | 8.06 | 8 | 32 | 224x224 | O2 | 300s | 47,34 | 5446.81 | 75.67 | 92.77 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/densenet/densenet_121_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/densenet/densenet121-bf4ab27f-910v2.ckpt) |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.

| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| densenet121 | 8.06 | 8 | 32 | 224x224 | O2 | 191s | 43.28 | 5914.97 | 75.64 | 92.84 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/densenet/densenet_121_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/densenet/densenet121-120_5004_Ascend.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

Expand Down
10 changes: 3 additions & 7 deletions configs/dpn/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,14 +75,10 @@ Our reproduced model performance on ImageNet-1K is reported as follows.

Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.

*coming soon*
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | -------- | -------- |
| dpn | 8 | 32 | 224x224 | O2 | 336s | 76.23 | 3358.26 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/dpn/dpn131_ascend.yaml) | [weights](https://download-mindspore.osinfra.cn/toolkits/mindcv/dpn/dpn131-47f084b3.ckpt) | 76.00 | 92.45 |

Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.


| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
| dpn92 | 37.79 | 8 | 32 | 224x224 | O2 | 293s | 78.22 | 3272.82 | 79.46 | 94.49 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/dpn/dpn92_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/dpn/dpn92-e3e0fca.ckpt) |

### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
Expand Down
Loading