Instructions to use thangkt/PCB-Prune-YOLO-TensorRT-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use thangkt/PCB-Prune-YOLO-TensorRT-FP16 with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| parameters,counted_parameters,macs,gmacs,flops_estimate,gflops_estimate,source_model,measurement_scope,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 | |
| 3012018,3012018,4073266400,4.0732664,8146532800,8.1465328,outputs/train/baseline/weights/best.pt,pure_engine_forward_excludes_preprocess_and_nms,1.837303730117128,1.5013949996500742,2.739976000157185,544.2758231031568,outputs/tensorrt_fp16/baseline/model.engine,7.476772308349609,1,640,cuda:1,Tesla T4,14911.6875,19.05322265625,3.12.12,2.10.0+cu128,12.8,8.4.115 | |