YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone copied to clipboard

 i have trainning it by using tiny-yolov3. why the precision down sofast ? and i python test.py /or detect.py ,报错为load_state_dict,  是不是Torch版本造成的？ 我的版本是1.4.0. 按照网上说的办法尝试修改了，还是不行。 期待您的回复，谢谢

zhengwl0714

Out of Memory during pruning

13

Hi. I'm trying to do pruning on a yolov4 model. I've done all the steps. However, I keep going out of memory. I'm using a T4 card with 15 GB...

ColinPeeris

由于v3 和 V4 的 cfg 文件中， yolo 层出现的顺序正好相反。

chumingqian

Hi thanks for this project I use command below for training with quantization but get problem. python train.py -pt --data cfg/obj.data --batch-size 4 --weights weights/yolov3-tiny.weights --cfg cfg/yolov3-tiny.cfg -sr --s .001...

saeedkhanehgir

使用知识蒸馏策略四进行训练出现feature mismatch

5

怎么才能使feature_s和feature_t长度相同

shaolingongfuhao

训练Dior遥感数据集，报错shape '[256, 128, 3, 3]' is invalid for input of size 37347

1

训练命令是： python train.py --data data/dior.data --batch-size 4 --weights weights/yolov3-dior-best.weights -pt --cfg cfg/yolov3/yolov3-onDIOR.cfg --epochs 10 --img-size 608 报错： Traceback (most recent call last): File "train.py", line 956, in train(hyp) # train...

wagnzi

It can be referred to lutzroeder/netron#544

mlbo

请问这是因为环境版本出现的问题吗

gooodfan

大神您好，请问下面几种方法对应的是哪些量化方法，有没有具体的论文，谢谢！ if quantized == 1: modules.add_module('Conv2d', BNFold_QuantizedConv2d_For_FPGA() elif quantized == 2: modules.add_module('Conv2d', TPSQ_BNFold_QuantizedConv2d_For_FPGA()) elif quantized == 3: modules.add_module('Conv2d', BNFold_COSPTQuantizedConv2d_For_FPGA(), 您的readme中quantized 2 对应Dorefa，但在代码中没有调用quantized_dorefa.py, 这个对应是对的吗？ quantized=3 时是哪种量化方法？ FPGA参数是如何使用，起到什么作用呢？ 非常感谢

noobgrow

TypeError: forward() missing 1 required positional argument: 'x'

lvy1999s