jizhishutong / yolou Goto Github PK

使用yolov7训练数据时，出现了下列错误：
RuntimeError: result type Float can't be cast to the desired output type __int64
目前在网上还没有找到yolov7相关解决方案，我的运行环境是pytorch==1.12,cuda==11.3,python==3.7

If yes, is it possible to provide a reparameterization script (like reparameterization.ipynb in official yolov7 repo)？

Hi jizhishutong, I check the export onnx model of yolov6 and find that some rep module is not reparameterized. Wanna know how to reparameterize when exporting, thanks!

当我尝试运行val_det.py时,提示forward()出现了未知的参数val,然后查看代码

但是去models/common.py中查看DetectMultiBackend()却发现forward()中并没有val这个参数

所以这应该是个小bug或者是没有及时更新的地方,无论是在common.py的forward()中添加一个val参数或者是去掉推理时的val=True都可以解决这个问题.

When training yolov7, there comes
name 'DownC' is not defined.
Seems some modules not defined

yolov7-x 53.7？高出的也太多了？
另外Yolov5精度和官方一模一样，贸然问下是不是就是搬来的权重呢？
而yolox却低了官方很多，是实现上有什么不一样吗？还是没训好呢？

命令：python train.py --mode yolov7 --use_aux True --data garbage.yaml --cfg yolov7.yaml --weights weights/yolov7/yolov7.pt --batch-size 8
出现错误
**Logging results to runs/train/exp14
Starting training for 100 epochs...

 Epoch   gpu_mem       box       obj       cls    labels  img_size

0%| | 0/5 [00:01<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 772, in
main(opt)
File "train.py", line 670, in main
train(opt.hyp, opt, device, callbacks)
File "train.py", line 448, in train
loss, loss_items = compute_loss(pred, targets.to(device), imgs) # init loss class
File "YOLOU/utils/loss.py", line 992, in call
bs_aux, as_aux_, gjs_aux, gis_aux, targets_aux, anchors_aux = self.build_targets2(p[:self.nl], targets, imgs)
File "YOLOU/utils/loss.py", line 1202, in build_targets2
indices, anch = self.find_5_positive(p, targets)
File "YOLOU/utils/loss.py", line 1388, in find_5_positive
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
RuntimeError: result type Float can't be cast to the desired output type long int
**

yolov7 推理的时候，同样的模型同样的图片，与官方的推理代码的结果相差很远。一个是0.5 官方有0.91

if mode == 'yolox':
if epoch == epochs - no_aug_epochs:
LOGGER.info("--->No mosaic aug now!")
dataset.mosaic = False # close mosaic
LOGGER.info("--->Add additional L1 loss now!")

我自己单步调试的时候发现， dataset.mosaic 在运行过程中还是True

Does detect.py only support the yolov5 model?

something wrong with yolov7

Can the pre-trained model released by the official repository be used normally in this repository?

缺少 yolov4 系列的模型，yolov4标准版、yolov4-tiny，以及Scaled-yolov4系列

Can I use your source for commercial purposes?

outputs must be a Tensor or an iterable of Tensors

File "/home/pc/dawn_work_space/yolou/YOLOU/models/yolox.py", line 210, in get_output_and_grid
reg_box[..., :2] = (reg_box[..., :2] + grid) * stride
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!

When will other pretrained models for yolox and other yaml profiles for yolov6 be released

How can I get a pretrained weight about YOLOX, will train the model from the beginning?Thank you!

这个工程感觉有几百M，下载有点慢，建议权重文件最好别上传在这个里面啊

Your experiment is based on COCO dataset? If it is true, some data is not consistent the official data.

Yolov6 is anchor-free，please correct the information.

Megvii-BaseDetection/YOLOX#712

https://github.com/Linaom1214/TensorRT-For-YOLO-Series/blob/main/Examples.ipynb

感谢博主的开源，我想使用yolov5-seg进行实例分割 请问数据格式是什么样的？

It is inconvenient to download them outside of China. Maybe it is a good idea to upload them in the release, where large files are supported.

size mismatch for model.33.cls_preds.2.bias: copying a param with shape torch.Size([80]) from check point, the shape in current model is torch.Size([14]).

You can find yolo with pose form this. https://github.com/BingfengYan/yolo_pose.
train+test+to tensorRT

Hi,

What is the password to access the Baidu Drive ?

这个项目好长时间没有更新了，是不再维护了吗？

export: weights=['./weights/yolov6s.pt'], imgsz=[640, 640], batch_size=1, device=cpu, half=False, inplace=False, train=False, optimize=False, dynamic=True, simplify=True, opset=12, include=['onnx']
YOLOv5 2022-8-25 Python-3.10.5 torch-1.12.0+cpu CPU

Traceback (most recent call last):
File "E:\Code\YOLOU-main\export.py", line 209, in
main(opt)
File "E:\Code\YOLOU-main\export.py", line 204, in main
run(**vars(opt))
File "E:\Code\pythonCode\changeable_region_detection-main\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "E:\Code\YOLOU-main\export.py", line 133, in run
model = attempt_load(weights, device=device, inplace=True, fuse=True) # load FP32 model
File "E:\Code\YOLOU-main\models\experimental.py", line 228, in attempt_load
ckpt = torch.load(attempt_download(w), map_location='cpu') # load
File "E:\Code\pythonCode\changeable_region_detection-main\venv\lib\site-packages\torch\serialization.py", line 712, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "E:\Code\pythonCode\changeable_region_detection-main\venv\lib\site-packages\torch\serialization.py", line 1049, in _load
result = unpickler.load()
File "E:\Code\pythonCode\changeable_region_detection-main\venv\lib\site-packages\torch\serialization.py", line 1042, in find_class
return super().find_class(mod_name, name)

ModuleNotFoundError: No module named 'yolov6'

进程已结束,退出代码1

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

Hi jizhishutong, do you have a script to do inference with onnx, just to check if the model works normally. Thanks.

if there is a download link?