Neural Magic LogoNeural Magic Logo
Get Started
Transfer a Sparsified Model
CV Object Detection

Transfer a Sparsified Model for Object Detection

This page walks through an example of fine-tuning a pre-sparsified model from the SparseZoo onto a new dataset for object detection.

We will use SparseZoo to pull down a pre-sparsified YOLOv5l and will use SparseML to fine-tune onto the VOC dataset while preserving sparsity.

Install Requirements

This example requires SparseML Torchvision Install.

Transfer Learning

The SparseZoo contains several sparsified object detection models and transfer learning recipes, including YOLOv5l, which is used in this example. The SparseZoo stub is below:


The sparseml.yolov5.train CLI command kicks off a run to fine-tune the sparsified YOLOv5 model onto the VOC dataset for object detection. After the command completes, the trained model will reamin sparse, achieve a mAP@0.5 of around 0.80 on VOC, and will be stored in the local models/sparsified directory.

$sparseml.yolov5.train \
--weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95?recipe_type=transfer_learn \
--recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95?recipe_type=transfer_learn \
--cfg models_v5.0/yolov5l.yaml \
--hyp data/hyps/hyp.finetune.yaml \
--data VOC.yaml \
--project yolov5l \
--name sparsified

The most important arguments are --data, --weights, and --recipe:

  • --data specifies the dataset onto which the model will be fine-tuned
  • --weights specifies the base model used to start the transfer learning process (can be a SparseZoo stub or local custom model path)
  • --recipe specifies the hyperparameters of the fine-tuning process (can be a SparseZoo stub or a local custom recipe)

To utilize your own dataset, set up the appropriate image dataset structure and pass the path as the --data argument. An example for VOC is on GitHub.

The --cfg and --hyp are configuration files. You can checkout the examples on GitHub.

There are many additional command line arguments that can be passed to tweak your fine-tuning process. Run the following to see the full list of options:

$ sparseml.yolov5.train -h

Exporting for Inference

With the sparsified model successfully trained, it is time to export it for inference. The sparseml.yolov5.export_onnx command is used to export the training graph to a performant inference one. After the command completes, a model.onnx file is created in yolov5/sparsified folder. It is now ready for deployment with DeepSparse utilizing pipelines.

$sparseml.yolov5.export_onnx \
--weights yolov5l/sparsified/weights/ \
Transfer a Sparsified Model for Text Classification
Sparsify a Model