From 39f34ac6196b1ae92bfa31c60c63b0ca947acc69 Mon Sep 17 00:00:00 2001 From: "mingjiang.li" Date: Mon, 3 Mar 2025 17:32:22 +0800 Subject: [PATCH] update model template to unify formats Signed-off-by: mingjiang.li --- docs/MODEL_TEMPLATE.md | 50 +++++++++++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 15 deletions(-) diff --git a/docs/MODEL_TEMPLATE.md b/docs/MODEL_TEMPLATE.md index 8a7bd98b9..d3c2c4103 100644 --- a/docs/MODEL_TEMPLATE.md +++ b/docs/MODEL_TEMPLATE.md @@ -1,22 +1,40 @@ -# MODEL_NAME +# MODEL_NAME (Related Toolbox for LLM) -## Model description -The paper proposes a method to convert a deep learning object detector into an equivalent spiking neural network. The aim is to provide a conversion framework that is not constrained to shallow network structures and classification problems as in state-of-the-art conversion libraries. The results show that models of higher complexity, such as the RetinaNet object detector, can be converted with limited loss in performance. +## Model Description -## Step 1: Installation +A brief introduction about this model. +A brief introduction about this model. +A brief introduction about this model. + +## Supported Environments + +| Iluvatar GPU | IXUCA Version | +|--------------|---------------| +| BI-V100 | 3.0.0 | +| BI-V150 | 4.2.0 | + +## Model Preparation + +### Prepare Resources + +### Prepare Datasets ```bash -pip install -r requirements.txt -python3 setup.py install +python3 dataset/coco/download_coco.py ``` -## Step 2: Preparing datasets +#### Prepare Pre-trained Weights (for LLM) + +Go to huggingface. + +### Install Dependencies ```bash -python3 dataset/coco/download_coco.py +pip install -r requirements.txt +python3 setup.py install ``` -## Step 3: Training +## Model Training ```bash # 8 GPUs @@ -28,12 +46,14 @@ export CUDA_VISIBLE_DEVICES=0 python3 tools/train.py -c configs/retinanet/retinanet_r50_fpn_1x_coco.yml --eval ``` -## Results +## Model Results -| GPUs | FPS | ACC | -|-------------|-----------|--------------| -| BI-V100 x 8 | 251 | 71.2 | +| Model | Iluvatar GPU | FPS | ACC | +|------------|--------------|-----|------| +| MODEL_NAME | BI-V100 x1 | 32 | 71.2 | +| MODEL_NAME | BI-V100 x8 | 251 | 71.2 | -## Reference +## References -- [Reference_link](https://github.com/reference_repo/reference_repo) \ No newline at end of file +- [Reference_link](https://github.com/reference_repo/reference_repo) +- [Paper](Paper_link) -- Gitee