Instructions to use thangkt/PCB-Prune-YOLO-P10-DepGraph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use thangkt/PCB-Prune-YOLO-P10-DepGraph with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("thangkt/PCB-Prune-YOLO-P10-DepGraph", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Download benchmark.csv from thangkt/PCB-Prune-YOLO-P10-DepGraph: direct link, hf CLI and curl.
- Browser
- Download file 557 Bytes
-
https://huggingface.co/thangkt/PCB-Prune-YOLO-P10-DepGraph/resolve/main/benchmark.csv
- Command line
-
hf download hf://thangkt/PCB-Prune-YOLO-P10-DepGraph/benchmark.csv
-
curl -L -o benchmark.csv https://huggingface.co/thangkt/PCB-Prune-YOLO-P10-DepGraph/resolve/main/benchmark.csv
557 Bytes
| 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 | |
| 2415613,2415613,3232802400,3.2328024,6465604800,6.4656048,9.718659240006673,9.886948000712437,10.987326000758912,102.89485157412653,outputs/finetune_sparse_reg5e4/p10/weights/best.pt,4.850336074829102,1,640,cuda:0,Tesla T4,14911.6875,40.015625,3.12.12,2.10.0+cu128,12.8,8.4.115 | |