multispectral-object-detection
multispectral-object-detection copied to clipboard
DocF
Multispectral Object Detection with Yolov5 and Transformer
'SPPF'
 #Can't get attribute 'SPPF' on How to solve this problem?
Thank you for your great work! I'd like to ask about your training settings of FLIR. I stuck to all default settings except for Batchsize. I set Batchsize to 8...
您好！感谢您的贡献。 我在跑flird数据集时出现了指标一直很差的情况。如图  我所加载的模型是yolov5l.pt yaml文件为yolov5l_fusion_transformer_flir_aligned.yaml. 其余的设置都没有变。 请问是哪里设置错了吗？ 期望收到您的回复
我将数据集做了处理，xml格式转化为了txt，但是txt也是三个类别没错，训练结果也是三个类别，只有推理有问题，请问是推理代码哪里需要改嘛？ parser.add_argument('--weights', nargs='+', type=str, default='./runs/train/iou/weights/best.pt', help='model.pt path(s)') parser.add_argument('--source1', type=str, default='./FLIR_ADAS-v5/train/rgb/FLIR_09973_RGB.jpg', help='source') # file/folder, 0 for webcam parser.add_argument('--source2', type=str, default='./FLIR_ADAS-v5/train/thermal_8_bit/FLIR_09973_PreviewData.jpeg', help='source') # file/folder, 0 for webcam parser.add_argument('--img-size', type=int, default=640, help='inference size...
Thanks for your contribution！ Could you please tell me the input shape for training LLVIP YOLOV5L, which achieves 97.5 [email protected] and 5.40 MR？
Thanks for your great work~ I find the result in LLVIP origin paper is higher than the result in your paper. I want to know why this difference happened. I...
