Skip to content

Commit

Permalink
Update Failed README Links (#1725)
Browse files Browse the repository at this point in the history
* Update old zoo stubs yolo v5

* Update README.md

* Update README.md
  • Loading branch information
Satrat committed Sep 18, 2023
1 parent bd38892 commit b29ca93
Show file tree
Hide file tree
Showing 2 changed files with 5 additions and 6 deletions.
7 changes: 3 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,7 @@ SparseML enables you to create a sparse model trained on your dataset in two way
- [Sparsify From Scratch With the CLI](integrations/ultralytics-yolov5/tutorials/sparsify-from-scratch.md)

### Ultralytics YOLOv8
- [Sparse Transfer Learning With the CLI](integrations/ultralytics-yolov5/tutorials/sparse-transfer-learning.md)
- [Sparsify From Scratch With the CLI](integrations/ultralytics-yolov5/tutorials/sparsify-from-scratch.md)
- [Sparse Transfer Learning With the CLI](integrations/ultralytics-yolov8/tutorials/sparse-transfer-learning.md)

### Additional Examples

Expand Down Expand Up @@ -172,8 +171,8 @@ sparseml.yolov5.train \
--hyp hyps/hyp.finetune.yaml --cfg yolov5s.yaml --patience 0
```

- [YOLOv5 CLI](ultralytics-yolov5/tutorials/sparse-transfer-learning.md)
- [YOLOv8 CLI](ultralytics-yolov8/tutorials/sparse-transfer-learning.md)
- [YOLOv5 CLI](integrations/ultralytics-yolov5/tutorials/sparse-transfer-learning.md)
- [YOLOv8 CLI](integrations/ultralytics-yolov8/tutorials/sparse-transfer-learning.md)
- [Hugging Face CLI](integrations/huggingface-transformers/tutorials/sparse-transfer-learning-bert.md)
- [Torchvision CLI](integrations/torchvision/tutorials/sparse-transfer-learning.md)

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -81,10 +81,10 @@ Let's try a step-by-step example of Sparse Transfer Learning YOLOv5s onto the VO

To run sparse transfer learning, we first need to create/select a sparsification recipe. For sparse transfer, we need a recipe that instructs SparseML to maintain sparsity during training and to quantize the model over the final epochs.

For the VOC dataset, there is a [transfer learning recipe available in SparseZoo](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fpruned75_quant-none), identified by the following stub:
For the VOC dataset, there is a [transfer learning recipe available in SparseZoo](https://sparsezoo.neuralmagic.com/models/yolov5-x6-coco-pruned90_quantized?hardware=deepsparse-c6i.12xlarge&comparison=yolov5-x6-coco-base&tab=4), identified by the following stub:

```
zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned75_quant-none?recipe_type=transfer_learn
zoo:cv/detection/yolov5-x6/pytorch/ultralytics/coco/pruned90_quant-none?recipe=transfer_learn
```

Here's what the transfer learning recipe looks like:
Expand Down

0 comments on commit b29ca93

Please sign in to comment.