[YOLOv8] Fixing the sparsezoo pathway

[dbogunowicz]

Fix for: https://app.asana.com/0/1203126676641557/1204359816230311/f

Testing

Testing with "base" sparseml model

sparseml.ultralytics.val --model zoo:cv/detection/yolov8-s/pytorch/ultralytics/coco/base-none --data coco.yaml

Outputs:

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.009
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.013
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.010
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.002
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.008
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.016
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.012
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.017
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.018
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.009
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.018
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.025

Testing with "vanilla" ultralytics model

sparseml.ultralytics.val --model yolov8n.pt --data coco128.yaml

Outputs:

Ultralytics YOLOv8.0.30 🚀 Python-3.8.10 torch-1.12.1+cu116 CUDA:0 (NVIDIA RTX A4000, 16117MiB)
val: Scanning /home/ubuntu/damian/deepsparse/datasets/coco128/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100%|██████████| 128/128 [00:00<?, ?it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 8/8 [00:01<00:00,  6.26it/s]
                   all        128        929       0.64      0.537      0.605      0.446
Speed: 0.1ms pre-process, 2.1ms inference, 0.0ms loss, 0.7ms post-process per image

Testing with dummy sparseml checkpoint model

sparseml.ultralytics.val --model runs/detect/train281/weights/last.pt --data coco128.yaml

Outputs:

Ultralytics YOLOv8.0.30 🚀 Python-3.8.10 torch-1.12.1+cu116 CUDA:0 (NVIDIA RTX A4000, 16117MiB)
val: Scanning /home/ubuntu/damian/deepsparse/datasets/coco128/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100%|██████████| 128/128 [00:00<?, ?it/s]
                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 8/8 [00:01<00:00,  6.93it/s]
                   all        128        929          0          0          0          0
Speed: 0.1ms pre-process, 4.1ms inference, 0.0ms loss, 0.0ms post-process per image

[anmarques]

After update sparseml.ultralytics.val works