| --- |
| license: apache-2.0 |
| datasets: |
| - imagenet-1k |
| metrics: |
| - accuracy |
| pipeline_tag: image-classification |
| tags: |
| - pytorch |
| - torch-dag |
| --- |
| # Model Card for resnet50d_pruned_25 |
|
|
| This is a prunned version of the [timm/resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k) model in a [toch-dag](https://github.com/TCLResearchEurope/torch-dag) format. |
|
|
| This model has rougly 25% of the original model FLOPs with minimal metrics drop. |
|
|
|
|
| | Model | KMAPPs* | M Parameters | Accuracy (224x224) | |
| | ----------- | ----------- | ----------- | ------------------ | |
| | **timm/resnet50d.a3_in1 (baseline)** | 174 | 25.6 | 80.9% | |
| | **resnet50d_pruned_25 (ours)** | 43.4 **(25%)** | 7.2 **(28%)** | 77.21% **(↓ 3.69%)** | |
| |
| |
| \***KMAPPs** thousands of FLOPs per input pixel |
| |
| `KMAPPs(model) = FLOPs(model) / (H * W * 1000)`, where `(H, W)` is the input resolution. |
| |
| The accuracy was calculated on the ImageNet-1k validation dataset. For details about image pre-processing, please refer to the original repository. |
| ## Model Details |
| |
| ### Model Description |
| |
| |
| - **Developed by:** [TCL Research Europe](https://github.com/TCLResearchEurope/) |
| - **Model type:** Classification / feature backbone |
| - **License:** Apache 2.0 |
| - **Finetuned from model:** [timm/resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k) |
| |
| ### Model Sources |
| - **Repository:** [timm/resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k) |
| |
| |
| |
| ## How to Get Started with the Model |
| |
| To load the model, You have to install [torch-dag](https://github.com/TCLResearchEurope/torch-dag#3-installation) library, which can be done using `pip` by |
| |
| ``` |
| pip install torch-dag |
| ``` |
| |
| then, clone this repository |
| |
| ``` |
| # Make sure you have git-lfs installed (https://git-lfs.com) |
| git lfs install |
| git clone https://huggingface.co/TCLResearchEurope/resnet50d_pruned_25 |
| ``` |
| |
| and now You are ready to load the model: |
| |
| ``` |
| import torch_dag |
| import torch |
| |
| model = torch_dag.io.load_dag_from_path('./resnet50d_pruned_25') |
| |
| model.eval() |
| out = model(torch.ones(1, 3, 224, 224)) |
| print(out.shape) |
| ``` |
