hpc203
看train.py文件的第98行代码： image = torch.FloatTensor(opt.batchSize, 3, opt.imgH, opt.imgH) 按照常理来说，应该是image = torch.FloatTensor(opt.batchSize, 3, opt.imgH, opt.imgW) 可是我改成这样之后重新训练，不收敛的。请问作者，这里的image为什么要定义成torch.FloatTensor(opt.batchSize, 3, opt.imgH, opt.imgH)而不是torch.FloatTensor(opt.batchSize, 3, opt.imgH, opt.imgW)呢？
https://github.com/hpc203/yolov34-cpp-opencv-dnn https://github.com/hpc203/yolov5-dnn-cpp-python https://github.com/hpc203/yolov5-dnn-cpp-python-v2 https://github.com/hpc203/nanodet-opncv-dnn-cpp-python https://github.com/hpc203/nanodet-plus-opencv https://github.com/hpc203/yolact-opencv-dnn-cpp-python https://github.com/hpc203/yolov5-face-landmarks-opencv https://github.com/hpc203/yolov5-face-landmarks-opencv-v2 https://github.com/hpc203/yolox-opencv-dnn https://github.com/hpc203/yolo-fastestv2-opencv https://github.com/hpc203/YOLOP-opencv-dnn https://github.com/hpc203/yolor-onnxruntime https://github.com/hpc203/yolov5-detect-car_plate_corner https://github.com/hpc203/yolov5-lite-onnxruntime https://github.com/hpc203/picodet-onnxruntime https://github.com/hpc203/multiyolov5-opencv-onnxrun https://github.com/hpc203/rotate-yolov5-opencv-onnxrun https://github.com/hpc203/yolov5-v6.1-opencv-onnxrun https://github.com/hpc203/yolov5_pose_opencv https://github.com/hpc203/rotateyolov5-opencv-onnxrun https://github.com/hpc203/polygonyolov5-opencv-onnxrun https://github.com/hpc203/pp-yoloe-onnxrun-cpp-py https://github.com/hpc203/yolov6-opencv-onnxruntime https://github.com/hpc203/FastestDet-opencv-dnn https://github.com/hpc203/yolov7-opencv-onnxrun-cpp-py https://github.com/hpc203/yolopv2-opencv-onnxrun-cpp-py https://github.com/hpc203/centernet-opencv-onnxrun-cpp-py https://github.com/hpc203/yolov7-detect-face-onnxrun-cpp-py https://github.com/hpc203/DAMO-YOLO-detect-onnxrun-cpp-py https://github.com/hpc203/PP-YOLOE-Plus-detect-onnxrun-cpp-py...
https://github.com/hpc203/yolov34-cpp-opencv-dnn https://github.com/hpc203/yolov5-dnn-cpp-python https://github.com/hpc203/yolov5-dnn-cpp-python-v2 https://github.com/hpc203/nanodet-opncv-dnn-cpp-python https://github.com/hpc203/nanodet-plus-opencv https://github.com/hpc203/yolact-opencv-dnn-cpp-python https://github.com/hpc203/yolov5-face-landmarks-opencv https://github.com/hpc203/yolov5-face-landmarks-opencv-v2 https://github.com/hpc203/yolox-opencv-dnn https://github.com/hpc203/yolo-fastestv2-opencv https://github.com/hpc203/YOLOP-opencv-dnn https://github.com/hpc203/yolor-onnxruntime https://github.com/hpc203/yolov5-detect-car_plate_corner https://github.com/hpc203/yolov5-lite-onnxruntime https://github.com/hpc203/picodet-onnxruntime https://github.com/hpc203/multiyolov5-opencv-onnxrun https://github.com/hpc203/rotate-yolov5-opencv-onnxrun https://github.com/hpc203/yolov5-v6.1-opencv-onnxrun https://github.com/hpc203/yolov5_pose_opencv https://github.com/hpc203/rotateyolov5-opencv-onnxrun https://github.com/hpc203/polygonyolov5-opencv-onnxrun https://github.com/hpc203/pp-yoloe-onnxrun-cpp-py https://github.com/hpc203/yolov6-opencv-onnxruntime https://github.com/hpc203/FastestDet-opencv-dnn https://github.com/hpc203/yolov7-opencv-onnxrun-cpp-py
使用OpenCV部署yolov5检测车牌和4个角点，包含C++和Python两个版本的程序 使用ONNXRuntime部署yolov5检测车牌和4个角点，包含C++和Python两个版本的程序 https://github.com/hpc203/yolov5-detect-car_plate_corner
使用OpenCV部署FastestDet，包含C++和Python两种版本的程序。模型文件不超过1M https://github.com/hpc203/FastestDet-opencv-dnn
输入图片转灰度
dataset.py第48行： data = data.convert('L') 为什么输入图片要转成灰度的，保留RBG彩色三通道的不好嘛，难道就为了节省内存嘛
A-Light-and-Fast-Face-Detector-for-Edge-Devices用opencv的dnn模块做人脸检测的Python程序，请参见 https://github.com/hpc203/10kinds-light-face-detector-align-recognition/blob/master/lffd_detect_module.py
现在想要做前景物体检测，检测图片里的物体，不需要类别信息的。请问这时候要输入怎样的提示词呢？我尝试过输入"object"或者"objects"，可是图片里有漏检的情况。
https://github.com/hpc203/yolo-fastestv2-opencv