ultralytics/yolov3: v8 | 您所在的位置:网站首页 › yolov3-spp-ultralytics › ultralytics/yolov3: v8 |
This is the final release of the darknet-compatible version of the https://github.com/ultralytics/yolov3 repository. This release is backwards-compatible with darknet *.cfg files for model configuration. All pytorch (.pt) and darknet (.weights) models/backbones available are attached to this release in the Assets section below. Breaking ChangesThere are no breaking changes in this release. Bug Fixes Various Added Functionality Various Speedhttps://cloud.google.com/deep-learning-vm/ Machine type: preemptible n1-standard-8 (8 vCPUs, 30 GB memory) CPU platform: Intel Skylake GPUs: K80 ($0.14/hr), T4 ($0.11/hr), V100 ($0.74/hr) CUDA with Nvidia Apex FP16/32 HDD: 300 GB SSD Dataset: COCO train 2014 (117,263 images) Model: yolov3-spp.cfg Command: python3 train.py --data coco2017.data --img 416 --batch 32 GPU n --batch-size img/s epochtime epochcost K80 1 32 x 2 11 175 min $0.41 T4 12 32 x 264 x 1 4161 48 min32 min $0.09$0.11 V100 12 32 x 264 x 1 122178 16 min11 min $0.21$0.28 2080Ti 12 32 x 264 x 1 81140 24 min14 min -- mAP Size COCO [email protected] COCO [email protected] YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 320 14.028.730.537.7 29.151.852.356.8 YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 416 16.031.233.941.2 33.055.456.960.6 YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 512 16.632.735.642.6 34.957.759.562.4 YOLOv3-tinyYOLOv3YOLOv3-SPPYOLOv3-SPP-ultralytics 608 16.633.137.043.1 35.458.260.762.8 TODO NA |
CopyRight 2018-2019 实验室设备网 版权所有 |