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

docs: renew READMEs, add ms/step data to forms and remove development… #812

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+710 −1,228
Open

docs: renew READMEs, add ms/step data to forms and remove development… #812

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 0 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,7 +217,6 @@ We provide the following jupyter notebook tutorials to help users learn to use M
- [Finetune a pretrained model on custom datasets](docs/en/tutorials/finetune.md)
- [Customize your model]() //coming soon
- [Optimizing performance for vision transformer]() //coming soon
- [Deployment demo](docs/en/tutorials/deployment.md)

## Model List

Expand Down
2 changes: 1 addition & 1 deletion README_CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,7 +121,7 @@ python infer.py --model=swin_tiny --image_path='./dog.jpg'

```shell
# 分布式训练
# 假设你有4张GPU或者NPU卡
# 假设你有4张NPU卡
msrun --bind_core=True --worker_num 4 python train.py --distribute \
--model densenet121 --dataset imagenet --data_dir ./datasets/imagenet
```
Expand Down
200 changes: 101 additions & 99 deletions benchmark_results.md
View file
Open in desktop

Large diffs are not rendered by default.

15 changes: 9 additions & 6 deletions configs/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,17 +33,20 @@ Please follow the outline structure and **table format** shown in [densenet/READ

<div align="center">

| Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
|--------------|----------|-----------|-----------|------------|-----------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------|
| densenet_121 | D910x8-G | 75.64 | 92.84 | 8.06 | [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) |
| model | top-1 (%) | top-5 (%) | params (M) | batch size | cards | ms/step | jit_level | recipe | download |
| ----------- | --------- | --------- | ---------- | ---------- | ----- | ------- | --------- | --------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
| densenet121 | 75.67 | 92.77 | 8.06 | 32 | 8 | 47,34 | O2 | [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) |

</div>

Illustration:
- Model: model name in lower case with _ seperator.
- Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
- Top-1 and Top-5: Accuracy reported on the validatoin set of ImageNet-1K. Keep 2 digits after the decimal point.
- Params (M): # of model parameters in millions (10^6). Keep **2 digits** after the decimal point
- Batch Size: Training batch size
- Cards: # of cards
- Ms/step: Time used on training per step in ms
- Jit_level: Jit level of mindspore context, which contains 3 levels: O0(kbk mode)/O1(dvm mode)/O2(ge mode)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove kbk/dvm/ge

- Recipe: Training recipe/configuration linked to a yaml config file.
- Download: url of the pretrained model weights

Expand All @@ -62,10 +65,10 @@ Illustration:
For consistency, it is recommended to provide distributed training commands based on `msrun --bind_core=True --worker_num {num_devices} python train.py`, instead of using shell script such as `distrubuted_train.sh`.

```shell
# standalone training on a gpu or ascend device
# standalone training on single NPU device
python train.py --config configs/densenet/densenet_121_gpu.yaml --data_dir /path/to/dataset --distribute False

# distributed training on gpu or ascend divices
# distributed training on NPU divices
msrun --bind_core=True --worker_num 8 python train.py --config configs/densenet/densenet_121_ascend.yaml --data_dir /path/to/imagenet

```
Expand Down
24 changes: 9 additions & 15 deletions configs/bit/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,25 +17,24 @@ too low. 5) With BiT fine-tuning, good performance can be achieved even if there

Our reproduced model performance on ImageNet-1K is reported as follows.

performance tested on ascend 910*(8p) with graph mode
- ascend 910* with graph mode

*coming soon*

performance tested on ascend 910(8p) with graph mode
- ascend 910 with graph mode


<div align="center">

| Model | Top-1 (%) | Top-5 (%) | Params(M) | Batch Size | Recipe | Download |
| ------------ | --------- | --------- | --------- | ---------- | ---------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
| bit_resnet50 | 76.81 | 93.17 | 25.55 | 32 | [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 | top-1 (%) | top-5 (%) | params(M) | batch size | cards | ms/step | jit_level | recipe | download |
| ------------ | --------- | --------- | --------- | ---------- | ----- |---------| --------- | ---------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
| bit_resnet50 | 76.81 | 93.17 | 25.55 | 32 | 8 | 74.52 | O2 | [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) |


</div>

#### Notes

- Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.

## Quick Start
Expand All @@ -44,7 +43,7 @@ performance tested on ascend 910(8p) with graph mode

#### Installation

Please refer to the [installation instruction](https://github.com/mindspore-lab/mindcv#installation) in MindCV.
Please refer to the [installation instruction](https://mindspore-lab.github.io/mindcv/installation/) in MindCV.

#### Dataset Preparation

Expand All @@ -57,11 +56,10 @@ Please download the [ImageNet-1K](https://www.image-net.org/challenges/LSVRC/201
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run

```shell
# distributed training on multiple GPU/Ascend devices
# distributed training on multiple NPU devices
msrun --bind_core=True --worker_num 8 python train.py --config configs/bit/bit_resnet50_ascend.yaml --data_dir /path/to/imagenet
```

Similarly, you can train the model on multiple GPU devices with the above `msrun` command.

For detailed illustration of all hyper-parameters, please refer to [config.py](https://github.com/mindspore-lab/mindcv/blob/main/config.py).

Expand All @@ -72,7 +70,7 @@ For detailed illustration of all hyper-parameters, please refer to [config.py](h
If you want to train or finetune the model on a smaller dataset without distributed training, please run:

```shell
# standalone training on a CPU/GPU/Ascend device
# standalone training on single NPU device
python train.py --config configs/bit/bit_resnet50_ascend.yaml --data_dir /path/to/dataset --distribute False
```

Expand All @@ -84,10 +82,6 @@ To validate the accuracy of the trained model, you can use `validate.py` and par
python validate.py -c configs/bit/bit_resnet50_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
```

### Deployment

Please refer to the [deployment tutorial](https://mindspore-lab.github.io/mindcv/tutorials/deployment/) in MindCV.

## References

<!--- Guideline: Citation format should follow GB/T 7714. -->
Expand Down
24 changes: 9 additions & 15 deletions configs/cmt/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,24 +14,23 @@ on ImageNet-1K dataset.

Our reproduced model performance on ImageNet-1K is reported as follows.

performance tested on ascend 910*(8p) with graph mode
- ascend 910* with graph mode

*coming soon*

performance tested on ascend 910(8p) with graph mode
- ascend 910 with graph mode

<div align="center">

| Model | Top-1 (%) | Top-5 (%) | Params(M) | Batch Size | Recipe | Download |
| --------- | --------- | --------- | --------- | ---------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| cmt_small | 83.24 | 96.41 | 26.09 | 128 | [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) |

| model | top-1 (%) | top-5 (%) | params(M) | batch size | cards | ms/step | jit_level | recipe | download |
| --------- | --------- | --------- | --------- | ---------- | ----- |---------| --------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
| cmt_small | 83.24 | 96.41 | 26.09 | 128 | 8 | 500.64 | O2 | [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) |


</div>

#### Notes

- Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.

## Quick Start
Expand All @@ -40,7 +39,7 @@ performance tested on ascend 910(8p) with graph mode

#### Installation

Please refer to the [installation instruction](https://github.com/mindspore-lab/mindcv#installation) in MindCV.
Please refer to the [installation instruction](https://mindspore-lab.github.io/mindcv/installation/) in MindCV.

#### Dataset Preparation

Expand All @@ -53,11 +52,10 @@ Please download the [ImageNet-1K](https://www.image-net.org/challenges/LSVRC/201
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run

```shell
# distributed training on multiple GPU/Ascend devices
# distributed training on multiple NPU devices
msrun --bind_core=True --worker_num 8 python train.py --config configs/cmt/cmt_small_ascend.yaml --data_dir /path/to/imagenet
```

Similarly, you can train the model on multiple GPU devices with the above `msrun` command.

For detailed illustration of all hyper-parameters, please refer to [config.py](https://github.com/mindspore-lab/mindcv/blob/main/config.py).

Expand All @@ -68,7 +66,7 @@ For detailed illustration of all hyper-parameters, please refer to [config.py](h
If you want to train or finetune the model on a smaller dataset without distributed training, please run:

```shell
# standalone training on a CPU/GPU/Ascend device
# standalone training on single NPU device
python train.py --config configs/cmt/cmt_small_ascend.yaml --data_dir /path/to/dataset --distribute False
```

Expand All @@ -80,10 +78,6 @@ To validate the accuracy of the trained model, you can use `validate.py` and par
python validate.py -c configs/cmt/cmt_small_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
```

### Deployment

Please refer to the [deployment tutorial](https://mindspore-lab.github.io/mindcv/tutorials/deployment/).

## References

<!--- Guideline: Citation format should follow GB/T 7714. -->
Expand Down
23 changes: 9 additions & 14 deletions configs/coat/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,23 +10,23 @@ Co-Scale Conv-Attentional Image Transformer (CoaT) is a Transformer-based image

Our reproduced model performance on ImageNet-1K is reported as follows.

performance tested on ascend 910*(8p) with graph mode
- ascend 910* with graph mode

*coming soon*


performance tested on ascend 910(8p) with graph mode
- ascend 910 with graph mode

<div align="center">

| Model | Top-1 (%) | Top-5 (%) | Params (M) | Batch Size | Recipe | Weight |
| --------- | --------- | --------- | ---------- | ---------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| coat_tiny | 79.67 | 94.88 | 5.50 | 32 | [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 | top-1 (%) | top-5 (%) | params (M) | batch size | cards | ms/step | jit_level | recipe | Weight |
| --------- | --------- | --------- | ---------- | ---------- | ----- |---------| --------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| coat_tiny | 79.67 | 94.88 | 5.50 | 32 | 8 | 254.95 | O2 | [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) |

</div>

#### Notes
- Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.


Expand All @@ -35,7 +35,7 @@ performance tested on ascend 910(8p) with graph mode
### Preparation

#### Installation
Please refer to the [installation instruction](https://github.com/mindspore-lab/mindcv#installation) in MindCV.
Please refer to the [installation instruction](https://mindspore-lab.github.io/mindcv/installation/) in MindCV.

#### Dataset Preparation
Please download the [ImageNet-1K](https://www.image-net.org/challenges/LSVRC/2012/index.php) dataset for model training and validation.
Expand All @@ -47,12 +47,11 @@ Please download the [ImageNet-1K](https://www.image-net.org/challenges/LSVRC/201
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run

```shell
# distributed training on multiple GPU/Ascend devices
# distributed training on multiple NPU devices
msrun --bind_core=True --worker_num 8 python train.py --config configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/imagenet
```


Similarly, you can train the model on multiple GPU devices with the above `msrun` command.

For detailed illustration of all hyper-parameters, please refer to [config.py](https://github.com/mindspore-lab/mindcv/blob/main/config.py).

Expand All @@ -63,7 +62,7 @@ For detailed illustration of all hyper-parameters, please refer to [config.py](h
If you want to train or finetune the model on a smaller dataset without distributed training, please run:

```shell
# standalone training on a CPU/GPU/Ascend device
# standalone training on single NPU device
python train.py --config configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/dataset --distribute False
```

Expand All @@ -75,10 +74,6 @@ To validate the accuracy of the trained model, you can use `validate.py` and par
python validate.py -c configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
```

### Deployment

To deploy online inference services with the trained model efficiently, please refer to the [deployment tutorial](https://mindspore-lab.github.io/mindcv/tutorials/deployment/).

## References

[1] Han D, Yun S, Heo B, et al. Rethinking channel dimensions for efficient model design[C]//Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 2021: 732-741.
Loading
Loading