Recipes

Training Recipes

We defined recipes to ensure that anyone can reproduce our results in the most simple way.

Setup

To run recipes you first need to clone the super-gradients repository:

git clone https://github.com/Deci-AI/super-gradients

You then need to move to the root of the clone project (where you find "requirements.txt" and "setup.py") and install super-gradients:

pip install -e .

Finally, append super-gradients to the python path: (Replace "YOUR-LOCAL-PATH" with the path to the downloaded repo)

export PYTHONPATH=$PYTHONPATH:<YOUR-LOCAL-PATH>/super-gradients/

How to run a recipe

The recipes are defined in .yaml format and we use the hydra library to allow you to easily customize the parameters. The basic basic syntax is as follow:

python -m super_gradients.train_from_recipe --config-name=<CONFIG-NAME> dataset_params.data_dir=<PATH-TO-DATASET>

Note: this script needs to be launched from the root folder of super_gradients Note: if you stored your dataset in the path specified by the recipe you can drop "dataset_params.data_dir=".

Explore our recipes

You can find all of our recipes here. You will find information about the performance of a recipe as well as the command to execute it in the header of its config file.

Example: Training of YoloX Small on Coco 2017, using 8 GPU

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_s dataset_params.data_dir=/home/coco2017

List of commands

All the commands to launch the recipes described here are listed below. Please make to "dataset_params.data_dir=" if you did not store the dataset in the path specified by the recipe (as showed in the example above).

- Classification

Cifar10

resnet

python -m super_gradients.train_from_recipe --config-name=cifar10_resnet +experiment_name=cifar10

ImageNet

efficientnet

python -m super_gradients.train_from_recipe --config-name=imagenet_efficientnet

mobilenetv2

python -m super_gradients.train_from_recipe --config-name=imagenet_mobilenetv2

mobilenetv3 small

python -m super_gradients.train_from_recipe --config-name=imagenet_mobilenetv3_small

mobilenetv3 large

python -m super_gradients.train_from_recipe --config-name=imagenet_mobilenetv3_large

regnetY200

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY200

regnetY400

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY400

regnetY600

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY600

regnetY800

python -m super_gradients.train_from_recipe --config-name=imagenet_regnetY architecture=regnetY800

repvgg

python -m super_gradients.train_from_recipe --config-name=imagenet_repvgg

resnet50

python -m super_gradients.train_from_recipe --config-name=imagenet_resnet50

resnet50_kd

python -m super_gradients.train_from_kd_recipe --config-name=imagenet_resnet50_kd

vit_base

python -m super_gradients.train_from_recipe --config-name=imagenet_vit_base

vit_large

python -m super_gradients.train_from_recipe --config-name=imagenet_vit_large

- Detection

Coco2017

ssd_lite_mobilenet_v2

python -m super_gradients.train_from_recipe --config-name=coco2017_ssd_lite_mobilenet_v2

yolox_n

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_n

yolox_t

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_t

yolox_s

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_s

yolox_m

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_m

yolox_l

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_l

yolox_x

python -m super_gradients.train_from_recipe --config-name=coco2017_yolox architecture=yolox_x

- Segmentation

Cityscapes

DDRNet23

python -m super_gradients.train_from_recipe --config-name=cityscapes_ddrnet

DDRNet23-Slim

python -m super_gradients.train_from_recipe --config-name=cityscapes_ddrnet architecture=ddrnet_23_slim

RegSeg48

python -m super_gradients.train_from_recipe --config-name=cityscapes_regseg48

STDC1-Seg50

python -m super_gradients.train_from_recipe --config-name=cityscapes_stdc_seg50

STDC2-Seg50

python -m super_gradients.train_from_recipe --config-name=cityscapes_stdc_seg50 architecture=stdc2_seg

STDC1-Seg75

python -m super_gradients.train_from_recipe --config-name=cityscapes_stdc_seg75

STDC2-Seg75

python -m super_gradients.train_from_recipe --config-name=cityscapes_stdc_seg75 external_checkpoint_path=<stdc2-backbone-pretrained-path> architecture=stdc2_seg