From e4602cf73f49a2d86054706b1f8c2256787d4d63 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Tue, 6 Apr 2021 17:48:49 +0200 Subject: [PATCH 1/3] Update README with collapsable notes. --- README.md | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 6e3f38761543..7d5f5be7b8b2 100755 --- a/README.md +++ b/README.md @@ -6,7 +6,13 @@ This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices evolved over thousands of hours of training and evolution on anonymized client datasets. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk. -** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8. + +
+ Figure Notes (click to expand) + + * GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. + * EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8. +
- **January 5, 2021**: [v4.0 release](https://github.com/ultralytics/yolov5/releases/tag/v4.0): nn.SiLU() activations, [Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_readme) logging, [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/) integration. - **August 13, 2020**: [v3.0 release](https://github.com/ultralytics/yolov5/releases/tag/v3.0): nn.Hardswish() activations, data autodownload, native AMP. @@ -31,11 +37,15 @@ This repository represents Ultralytics open-source research into future object d | [YOLOv5l6](https://github.com/ultralytics/yolov5/releases) |1280 |53.0 |53.0 |70.8 |12.3ms |81 ||77.2M |117.7 ---> -** APtest denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results denote val2017 accuracy. -** All AP numbers are for single-model single-scale without ensemble or TTA. **Reproduce mAP** by `python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` -** SpeedGPU averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and includes image preprocessing, FP16 inference, postprocessing and NMS. NMS is 1-2ms/img. **Reproduce speed** by `python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45` -** All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). -** Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) runs at 3 image sizes. **Reproduce TTA** by `python test.py --data coco.yaml --img 832 --iou 0.65 --augment` +
+ Table Notes (click to expand) + + * APtest denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results denote val2017 accuracy. + * All AP numbers are for single-model single-scale unless denoted by TTA. **Reproduce mAP** by `python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` + * SpeedGPU averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and includes FP16 inference, postprocessing and NMS. **Reproduce speed** by `python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45` + * All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). + * Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale augmentation. **Reproduce TTA** by `python test.py --data coco.yaml --img 832 --iou 0.65 --augment` +
## Requirements From def773321d3a88186b6eae1beb7e93541a3d46e5 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Tue, 6 Apr 2021 17:50:24 +0200 Subject: [PATCH 2/3] cleanup --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7d5f5be7b8b2..1bf3e4d57b81 100755 --- a/README.md +++ b/README.md @@ -41,7 +41,7 @@ This repository represents Ultralytics open-source research into future object d Table Notes (click to expand) * APtest denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results denote val2017 accuracy. - * All AP numbers are for single-model single-scale unless denoted by TTA. **Reproduce mAP** by `python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` + * AP values are for single-model single-scale unless otherwise noted. **Reproduce mAP** by `python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65` * SpeedGPU averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) V100 instance, and includes FP16 inference, postprocessing and NMS. **Reproduce speed** by `python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45` * All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). * Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) includes reflection and scale augmentation. **Reproduce TTA** by `python test.py --data coco.yaml --img 832 --iou 0.65 --augment` From d4a8a4b81a11bfdc2d326a4dae6e8fc8db4655f9 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Tue, 6 Apr 2021 17:53:10 +0200 Subject: [PATCH 3/3] center table --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 1bf3e4d57b81..f51ccd97712f 100755 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices evolved over thousands of hours of training and evolution on anonymized client datasets. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk. - +

Figure Notes (click to expand)