Day51 - P234+NWD改进在VisDrone上的表现
yolov5s/m和yolov8s删除P5检测头+添加P2检测头,使用NWD损失函数,在VisDrone上训练200epochs Yolov5s-p234-nwd Parameters: 6.273M Class Precision Recall ...
彩虹岛
Day50 - Backbone中C3/C2f后添加一层ECA在FLIR上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层ECA,在FLIR上训练200epochs Yolov5n-eca Parameters: 2.655M Class Precision Recall ...
Day49 - Backbone中C3/C2f后添加一层CA在FLIR上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层CA,在FLIR上训练200epochs Yolov5n-ca Parameters: 2.667M Class Precision Recall mA...
Day48 - Backbone中C3/C2f后添加一层SEAttention在FLIR上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层SE,在FLIR上训练200epochs Yolov5n-se Parameters: 2.666M Class Precision Recall mA...
Day47 - Backbone中C3/C2f后添加一层ECA在VisDrone上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层CA,在VisDrone上训练200epochs Yolov5n-eca Parameters: 2.655M Class Precision Recall ...
Day46 - Backbone中C3/C2f后添加一层CA在VisDrone上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层CA,在VisDrone上训练200epochs Yolov5n-ca Parameters: 2.667M Class Precision Recall ...
Day45 - Backbone中C3/C2f后添加一层SEAttention在VisDrone上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层SE,在VisDrone上训练200epochs Yolov5n-se Parameters: 2.666M Class Precision Recall ...
Day44 - Backbone中C3/C2f后添加一层GAM在VisDrone上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层GAM,在VisDrone上训练200epochs Yolov5n-gam Parameters: 3.234M Class Precision Recall ...
Day43 - Backbone中C3/C2f后添加一层GAM在FLIR上的表现
yolov5n/s/m和yolov8n/s仅在backbone的C3/C2f模块后添加一层GAM,在FLIR上训练200epochs Yolov5n-gam Parameters: 3.234M Class Precision Recall ...
Day42 - Neck中C3/C2f后添加一层GAM在FLIR上的表现
yolov5n/s/m和yolov8n/s仅在neck的C3/C2f模块后添加一层GAM,在FLIR上训练200epochs Yolov5n-gam Parameters: 3.336M Class Precision Recall mAP5...