Skip to content

Commit

Permalink
docs: fix readme bugs
Browse files Browse the repository at this point in the history
  • Loading branch information
ChongWei905 committed Nov 14, 2024
1 parent 7bc4a44 commit 4f9f22a
Show file tree
Hide file tree
Showing 54 changed files with 1,304 additions and 1,588 deletions.
4 changes: 2 additions & 2 deletions benchmark_results.md
Original file line number Diff line number Diff line change
Expand Up @@ -114,5 +114,5 @@

</details>

#### Notes
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.
### Notes
- top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.
6 changes: 3 additions & 3 deletions configs/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -31,17 +31,17 @@ Please follow the outline structure and **table format** shown in [densenet/READ

#### Table Format

<div align="center">


| 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 | 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) |

</div>


Illustration:
- Model: model name in lower case with _ seperator.
- Top-1 and Top-5: Accuracy reported on the validatoin set of ImageNet-1K. Keep 2 digits after the decimal point.
- 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
Expand Down
52 changes: 24 additions & 28 deletions configs/bit/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,6 @@

> [Big Transfer (BiT): General Visual Representation Learning](https://arxiv.org/abs/1912.11370)
## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Introduction

Expand All @@ -17,30 +13,10 @@ is required. 3) Long pre-training time: Pretraining on a larger dataset requires
BiT use GroupNorm combined with Weight Standardisation instead of BatchNorm. Since BatchNorm performs worse when the number of images on each accelerator is
too low. 5) With BiT fine-tuning, good performance can be achieved even if there are only a few examples of each type on natural images.[[1, 2](#References)]


## Performance

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

- Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode

*coming soon*

- Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode


<div align="center">


| 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) |


</div>

#### Notes
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.
## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Quick Start

Expand Down Expand Up @@ -87,6 +63,26 @@ 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
```

## Performance

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

Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode.

*coming soon*

Experiments are tested on ascend 910 with mindspore 2.3.1 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) |



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

## References

<!--- Guideline: Citation format should follow GB/T 7714. -->
Expand Down
47 changes: 21 additions & 26 deletions configs/cmt/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,6 @@

> [CMT: Convolutional Neural Networks Meet Vision Transformers](https://arxiv.org/abs/2107.06263)
## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Introduction

Expand All @@ -14,29 +10,11 @@ dependencies and extract local information. In addition, to reduce computation c
and depthwise convolution and pointwise convolution like MobileNet. By combing these parts, CMT could get a SOTA performance
on ImageNet-1K dataset.

## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Performance

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

- Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode

*coming soon*

- Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode

<div align="center">


| 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) |


</div>

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

## Quick Start

Expand Down Expand Up @@ -83,6 +61,23 @@ 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
```

## Performance

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

Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode.

*coming soon*

Experiments are tested on ascend 910 with mindspore 2.3.1 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.

## References

<!--- Guideline: Citation format should follow GB/T 7714. -->
Expand Down
20 changes: 10 additions & 10 deletions configs/coat/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,37 +2,37 @@

> [Co-Scale Conv-Attentional Image Transformers](https://arxiv.org/abs/2104.06399v2)
## Introduction

Co-Scale Conv-Attentional Image Transformer (CoaT) is a Transformer-based image classifier equipped with co-scale and conv-attentional mechanisms. First, the co-scale mechanism maintains the integrity of Transformers' encoder branches at individual scales, while allowing representations learned at different scales to effectively communicate with each other. Second, the conv-attentional mechanism is designed by realizing a relative position embedding formulation in the factorized attention module with an efficient convolution-like implementation. CoaT empowers image Transformers with enriched multi-scale and contextual modeling capabilities.

## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Introduction

Co-Scale Conv-Attentional Image Transformer (CoaT) is a Transformer-based image classifier equipped with co-scale and conv-attentional mechanisms. First, the co-scale mechanism maintains the integrity of Transformers' encoder branches at individual scales, while allowing representations learned at different scales to effectively communicate with each other. Second, the conv-attentional mechanism is designed by realizing a relative position embedding formulation in the factorized attention module with an efficient convolution-like implementation. CoaT empowers image Transformers with enriched multi-scale and contextual modeling capabilities.

## Performance

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

- Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode
Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode.

*coming soon*


- Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode
Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode.


<div align="center">


| 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) |

</div>

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

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


## Quick Start
Expand Down
56 changes: 24 additions & 32 deletions configs/convit/README.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,6 @@
# ConViT
> [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://arxiv.org/abs/2103.10697)
## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Introduction

Expand All @@ -24,36 +20,12 @@ while offering a much improved sample efficiency.[[1](#references)]
<em>Figure 1. Architecture of ConViT [<a href="#references">1</a>] </em>
</p>

## Requirements
| mindspore | ascend driver | firmware | cann toolkit/kernel |
| :-------: | :-----------: | :---------: | :-----------------: |
| 2.3.1 | 24.1.RC2 | 7.3.0.1.231 | 8.0.RC2.beta1 |

## Performance

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

- Experiments are tested on ascend 910* with mindspore 2.3.1 graph mode


<div align="center">


| 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 | 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) |

</div>

- Experiments are tested on ascend 910 with mindspore 2.3.1 graph mode

<div align="center">


| 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) |

</div>

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

## Quick Start

Expand Down Expand Up @@ -98,6 +70,26 @@ To validate the accuracy of the trained model, you can use `validate.py` and par
python validate.py -c configs/convit/convit_tiny_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
```

## Performance

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

Experiments are tested on ascend 910* with mindspore 2.3.1 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 | 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 2.3.1 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.

## References

<!--- Guideline: Citation format should follow GB/T 7714. -->
Expand Down
Loading

0 comments on commit 4f9f22a

Please sign in to comment.