Instructions to use thangkt/PCB-Prune-YOLO-P20-Direct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use thangkt/PCB-Prune-YOLO-P20-Direct with ultralytics:
from ultralytics import YOLOvv8 model = YOLOvv8.from_pretrained("thangkt/PCB-Prune-YOLO-P20-Direct") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- benchmark/benchmark.csv +2 -0
- benchmark/benchmark.json +24 -0
benchmark/benchmark.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
parameters,counted_parameters,macs,gmacs,flops_estimate,gflops_estimate,mean_latency_ms,median_latency_ms,p95_latency_ms,fps,model,model_size_mb,batch_size,imgsz,device,gpu_name,gpu_total_memory_mb,peak_gpu_memory_mb,python_version,torch_version,cuda_version,ultralytics_version
|
| 2 |
+
1913971,1913971,2572161600,2.5721616,5144323200,5.1443232,11.716616345202056,11.059291500714608,16.591671999776736,85.34887296275593,outputs/finetune_direct/p20_adamw_exact/weights/best.pt,3.8965396881103516,1,640,cuda:1,Tesla T4,14911.6875,34.1357421875,3.12.12,2.10.0+cu128,12.8,8.4.115
|
benchmark/benchmark.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"parameters": 1913971,
|
| 3 |
+
"counted_parameters": 1913971,
|
| 4 |
+
"macs": 2572161600,
|
| 5 |
+
"gmacs": 2.5721616,
|
| 6 |
+
"flops_estimate": 5144323200,
|
| 7 |
+
"gflops_estimate": 5.1443232,
|
| 8 |
+
"mean_latency_ms": 11.716616345202056,
|
| 9 |
+
"median_latency_ms": 11.059291500714608,
|
| 10 |
+
"p95_latency_ms": 16.591671999776736,
|
| 11 |
+
"fps": 85.34887296275593,
|
| 12 |
+
"model": "outputs/finetune_direct/p20_adamw_exact/weights/best.pt",
|
| 13 |
+
"model_size_mb": 3.8965396881103516,
|
| 14 |
+
"batch_size": 1,
|
| 15 |
+
"imgsz": 640,
|
| 16 |
+
"device": "cuda:1",
|
| 17 |
+
"gpu_name": "Tesla T4",
|
| 18 |
+
"gpu_total_memory_mb": 14911.6875,
|
| 19 |
+
"peak_gpu_memory_mb": 34.1357421875,
|
| 20 |
+
"python_version": "3.12.12",
|
| 21 |
+
"torch_version": "2.10.0+cu128",
|
| 22 |
+
"cuda_version": "12.8",
|
| 23 |
+
"ultralytics_version": "8.4.115"
|
| 24 |
+
}
|