yolov7
yolov7 copied to clipboard
WongKinYiu
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
您好，因为我目前只有检测灰度图的需求，训练时所用数据集也全是灰度图，使用yolov7-tiny版本。请问有什么办法可以针对这种情况减少通道数，使得减少模型的参数量以达到提高训练和推理速度效果呢？如果有的话，可以讲解一下具体如何修改代码或配置文件吗？感谢！ Hello, because I only need to detect grayscale images at present, the datasets used in training are all grayscale images, using the yolov7-tiny version. Is there any way to...
Hello I have converted successfully Yolov7-Tiny to ONNX via https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7onnx.ipynb#scrollTo=VaPGM88g-_CE tutorial But when I try to convert ONNX to TensorRT on Jetson Nano I get this error: "Error Code 2:...
I generated an yolov7.onnx by command: `python export.py --weights weights/yolov7.pt --grid --simplify --dynamic` when I run the yolov7.onnx by: ``` # ONNX inference outputs = session.run(outname, {inname[0]:img})[0] ``` an error...
I use opencv dnn to get scores, classID, and confidence. But the scores result is still "[ ]". I can use opencv dnn in yolov4-tiny.weight. However, yolov7-tiny.onnx cannot use. How...
 Hi how could I solve this problem ? UnicodeDecodeError: 'cp950' codec can't decode byte 0x80 in position 64: illegal multibyte sequence I didn't see any issue about...
Hello all, I've done three trainings now and each one is bad because an overfitting is visible at obj_loss. The first one I did from scratch (orange), the second one...
How to set `--img-size` parameter for training set with diffrent input images size? I have a training set with images `640x352` and `1024x768` and `960x708` in the same directory. How...
Metadata
Owner
Metadata
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors