YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone copied to clipboard

剪枝后精度太差

1

wangshiyu001

Bumps [numpy](https://github.com/numpy/numpy) from 1.17 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

TaoZhang1993

我在使用最新版v9.6版本的u版yolov3框架，使用v3tiny在我自己的数据集中得到的精度[email protected]=56%。然后因为量化的需要，我在使用作者您的代码，但是在这个代码中使用我自己的数据集我得到的[email protected]的精度为48.8%，为什么同一个框架下的精度会相差这么多？然后我调节了img-size=640以及一些超参数和激活函数但精度没有明显的增加，这个问题一直没有解决，所以请教各位，谢谢谢谢

liu202204

RuntimeError: shape[16,3,6,13,13] is invalid for input of size 689520

7

 RuntimeError: shape[16,3,6,13,13] is invalid for input of size 689520 我用自己的数据集（只有1个类别）训练出现上述错误，分析是某处代码强制把类别写成80（coco数据集的类别），已检查数据、模型配置文件均无误，也排除了下载的预训练模型，跪求解答！！！

Timothy-105

将 model.py 的 ONNX_EXPORT设置为True，模型输入尺寸(416,416) 设置detect()函数 内 imgsz = (416, 256) if ONNX_EXPORT else opt.img_size 运行detect.py 出现如下错误： `image 1/1 data\samples\84.jpg: Traceback (most recent call last): File "e:/lixx/vscode_python_project/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone/detect.py", line 220, in detect()...

likelyxx

Conversion of Weight and cfg files after quantization

2

Hello, I have tried your quantization approach and the final output of your quantization training is a .pt file. Can you help me to convert back to .weight from the...

ahasan016

@SpursLipu @domdal @yingbiaoluo @TianhaoFu @ScarceStar-XieCY I did the training with --quantized 2 flag. the detect.py is running fine with --quantized 2 flag. But when I convert it to tflite then...

Abhishek672

yolov4-tiny retrain

9

我在retrain 剪支過的模型時，出現了以下問題 Traceback (most recent call last): File "train.py", line 985, in train(hyp) # train normally File "train.py", line 164, in train load_darknet_weights(model, weights, pt=opt.pt, BN_Fold=opt.BN_Fold) File "/home/joy/yolo_darknet/YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone/models.py", line 632,...

chingi071

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

3

When I run the PTW.py or test.py, I encounter the following error. 

ivs-pychen