Skip to content

Commit 823059a

Browse files
author
Yang
committed
update performance info
add some coming soon info add some coming soon info add some coming soon info add some coming soon info
1 parent 78cd43a commit 823059a

File tree

49 files changed

+40
-377
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

49 files changed

+40
-377
lines changed

‎configs/bit/README.md‎

Lines changed: 3 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -69,16 +69,9 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
6969

7070
Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
7171

72-
*coming soon*
73-
74-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
75-
76-
77-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
78-
| ------------ | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
79-
| 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) |
80-
81-
72+
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
73+
| ----------- | ----- | ---------- | ---------- |-----------| ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- | -------- | -------- |
74+
| 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 |
8275

8376
### Notes
8477
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

‎configs/cmt/README.md‎

Lines changed: 3 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -67,13 +67,10 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
6767

6868
Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
6969

70-
*coming soon*
70+
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
71+
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | -------- | -------- |
72+
| 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 |
7173

72-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
73-
74-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
75-
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
76-
| 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) |
7774

7875
### Notes
7976
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

‎configs/coat/README.md‎

Lines changed: 3 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -63,17 +63,9 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
6363

6464
Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
6565

66-
*coming soon*
67-
68-
69-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
70-
71-
72-
73-
74-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
75-
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
76-
| 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) |
66+
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
67+
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------- | -------- | -------- |
68+
| 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 |
7769

7870

7971

‎configs/convit/README.md‎

Lines changed: 0 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -80,13 +80,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
8080
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------- |
8181
| 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) |
8282

83-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
84-
85-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
86-
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------- |
87-
| 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) |
88-
89-
9083
### Notes
9184
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
9285

‎configs/convnext/README.md‎

Lines changed: 0 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -78,12 +78,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
7878
| ------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
7979
| 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) |
8080

81-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
82-
83-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
84-
| ------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ---------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
85-
| 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) |
86-
8781
### Notes
8882
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
8983

‎configs/convnextv2/README.md‎

Lines changed: 0 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -77,12 +77,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
7777
| --------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
7878
| 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) |
7979

80-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
81-
82-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
83-
| --------------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | -------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
84-
| 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) |
85-
8680
### Notes
8781
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
8882

‎configs/crossvit/README.md‎

Lines changed: 0 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -73,12 +73,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
7373
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- |
7474
| 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) |
7575

76-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
77-
78-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
79-
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
80-
| 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) |
81-
8276
### Notes
8377
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
8478

‎configs/densenet/README.md‎

Lines changed: 0 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -82,12 +82,6 @@ Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
8282
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
8383
| 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) |
8484

85-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
86-
87-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
88-
| ----------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
89-
| 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) |
90-
9185
### Notes
9286
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
9387

‎configs/dpn/README.md‎

Lines changed: 3 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -75,14 +75,10 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
7575

7676
Experiments are tested on ascend 910* with mindspore 2.5.0 graph mode.
7777

78-
*coming soon*
78+
| model name | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | recipe | weight | acc@top1 | acc@top5 |
79+
| ----------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | -------- | -------- |
80+
| 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 |
7981

80-
Experiments are tested on ascend 910 with mindspore 2.5.0 graph mode.
81-
82-
83-
| model name | params(M) | cards | batch size | resolution | jit level | graph compile | ms/step | img/s | acc@top1 | acc@top5 | recipe | weight |
84-
| ---------- | --------- | ----- | ---------- | ---------- | --------- | ------------- | ------- | ------- | -------- | -------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------- |
85-
| 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) |
8682

8783
### Notes
8884
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.

0 commit comments

Comments
 (0)