Skip to content
This repository was archived by the owner on Jun 3, 2025. It is now read-only.

[Cherry-Pick] ([Yolov5][Tutorials] replace local recipe paths with zoo stubs #1021) #1023

Merged
merged 1 commit into from
Aug 24, 2022
Merged

[Cherry-Pick] ([Yolov5][Tutorials] replace local recipe paths with zoo stubs #1021) #1023

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions integrations/ultralytics-yolov5/tutorials/sparsifying_yolov5_using_recipes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,12 +131,12 @@ The table below compares these tradeoffs and shows how to run them on the COCO d

| Recipe Name | Description | Train Command | COCO mAP@0.5 | Size on Disk | DeepSparse Performance** |
|----------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------|--------------|--------------------------|
| YOLOv5s Baseline | The baseline, small YOLOv5 model used as the starting point for sparsification. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights "" --data coco.yaml --hyp data/hyps/hyp.scratch.yaml ``` | 0.556 | 24.8 MB | 135.8 img/sec |
| [YOLOv5s Pruned](https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/recipes/yolov5s.pruned.md) | Creates a highly sparse, FP32 YOLOv5s model that recovers close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe recipes/yolov5s.pruned.md ``` | 0.534 | 8.4 MB | 199.1 img/sec |
| [YOLOv5s Pruned Quantized](https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/recipes/yolov5s.pruned_quantized.md) | Creates a highly sparse, INT8 YOLOv5s model that recovers reasonably close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe recipes/yolov5s.pruned_quantized.md ``` | 0.525 | 3.3 MB | 396.7 img/sec |
| YOLOv5l Baseline | The baseline, large YOLOv5 model used as the starting point for sparsification. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights "" --data coco.yaml --hyp data/hyps/hyp.scratch.yaml ``` | 0.654 | 154 MB | 27.9 img/sec |
| [YOLOv5l Pruned](https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/recipes/yolov5l.pruned.md) | Creates a highly sparse, FP32 YOLOv5l model that recovers close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe recipes/yolov5l.pruned.md ``` | 0.643 | 32.8 MB | 63.7 img/sec |
| [YOLOv5l Pruned Quantized](https://github.com/neuralmagic/sparseml/blob/main/integrations/ultralytics-yolov5/recipes/yolov5l.pruned_quantized.md) | Creates a highly sparse, INT8 YOLOv5l model that recovers reasonably close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe recipes/yolov5l.pruned_quantized.md ``` | 0.623 | 12.7 MB | 139.8 img/sec |
| [YOLOv5s Baseline](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none) | The baseline, small YOLOv5 model used as the starting point for sparsification. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights "" --data coco.yaml --hyp data/hyps/hyp.scratch.yaml ``` | 0.556 | 24.8 MB | 135.8 img/sec |
| [YOLOv5s Pruned](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fpruned-aggressive_96) | Creates a highly sparse, FP32 YOLOv5s model that recovers close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned-aggressive_96 ``` | 0.534 | 8.4 MB | 199.1 img/sec |
| [YOLOv5s Pruned Quantized](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-s%2Fpytorch%2Fultralytics%2Fcoco%2Fpruned_quant-aggressive_94) | Creates a highly sparse, INT8 YOLOv5s model that recovers reasonably close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5s.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned_quant-aggressive_94 ``` | 0.525 | 3.3 MB | 396.7 img/sec |
| [YOLOv5l Baseline](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-l%2Fpytorch%2Fultralytics%2Fcoco%2Fbase-none) | The baseline, large YOLOv5 model used as the starting point for sparsification. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights "" --data coco.yaml --hyp data/hyps/hyp.scratch.yaml ``` | 0.654 | 154 MB | 27.9 img/sec |
| [YOLOv5l Pruned](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-l%2Fpytorch%2Fultralytics%2Fcoco%2Fpruned-aggressive_98) | Creates a highly sparse, FP32 YOLOv5l model that recovers close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned-aggressive_98 ``` | 0.643 | 32.8 MB | 63.7 img/sec |
| [YOLOv5l Pruned Quantized](https://sparsezoo.neuralmagic.com/models/cv%2Fdetection%2Fyolov5-l%2Fpytorch%2Fultralytics%2Fcoco%2Fpruned_quant-aggressive_95) | Creates a highly sparse, INT8 YOLOv5l model that recovers reasonably close to the baseline model. | ``` sparseml.yolov5.train --cfg models_v5.0/yolov5l.yaml --weights PATH_TO_COCO_PRETRAINED_WEIGHTS --data coco.yaml --hyp data/hyps/hyp.scratch.yaml --recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95 ``` | 0.623 | 12.7 MB | 139.8 img/sec |

\*\* DeepSparse Performance measured on an AWS c5.12xlarge instance with 24 cores, batch size 64, and 640x640 input with version 0.12.0 of the DeepSparse Engine i.e. `deepsparse.benchmark --batch_size 64 --scenario sync [model_path]`

Expand Down
8 changes: 4 additions & 4 deletions integrations/ultralytics-yolov5/tutorials/yolov5_sparse_transfer_learning.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,23 +104,23 @@ The recipes are specific to the sparsification type, so the training command wil

- YOLOv5s Pruned transfer learning:
```bash
sparseml.yolov5.train --data VOC.yaml --cfg /models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned-aggressive_96?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe /recipes/yolov5.transfer_learn_pruned.md
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned-aggressive_96?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned-aggressive_96?recipe_type=transfer
```
- YOLOv5s Pruned-Quantized transfer learning:
```bash
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned_quant-aggressive_94?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe recipes/yolov5.transfer_learn_pruned_quantized.md
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned_quant-aggressive_94?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned_quant-aggressive_94?recipe_type=transfer
```
- YOLOv5s Baseline transfer learning:
```bash
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none --hyp data/hyps/hyp.finetune.yaml --epochs 50
```
- YOLOv5l Pruned transfer learning:
```bash
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5l.yaml --weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned-aggressive_98?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe recipes/yolov5.transfer_learn_pruned.md
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5l.yaml --weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned-aggressive_98?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned-aggressive_98?recipe_type=transfer
```
- YOLOv5l Pruned-Quantized transfer learning:
```bash
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5l.yaml --weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe recipes/yolov5.transfer_learn_pruned_quantized.md
sparseml.yolov5.train --data VOC.yaml --cfg models_v5.0/yolov5l.yaml --weights zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95?recipe_type=transfer --hyp data/hyps/hyp.finetune.yaml --recipe zoo:cv/detection/yolov5-l/pytorch/ultralytics/coco/pruned_quant-aggressive_95?recipe_type=transfer
```
- YOLOv5l Baseline transfer learning:
```bash
Expand Down