YOLOv3_PyTorch

YOLOv3_PyTorch copied to clipboard

about trained weights

4

I used your code to train my own data. The loss drops normally. But when I used the trained weights to detect, no detection can be made. I also tried...

Brizel

Details about training code

13

Hi @BobLiu20, thanks for your excellent code! Can you please provide more details about training? Can it be done without the pretrained weights? How long would it take (how many...

themathgeek13

I trained the model in the voc dataset,and the loss is in 0.4-0.7.But when I test the trained model use image,the output is nothing,there only have the origin image,but not...

BCWang93

About the training process and question

2

Hi @BobLiu20 , thanks for your code of YOLO. I'm training under the COCO but there is no detection with the trained model(2 epochs 19000steps, loss=0.41). (1) Is this loss...

ThorinGondor

Prediction

3

Thanks for your excellent and easily understanding script. My simple question is how to predict, because there are no prediction module, modifying train.py or eval.py, I have no idea, hope...

crankson123

Hi, thank you for your great contribution. I want to train my own dataset which is a single-class dataset. Would you please give me some suggestions on that? Thanks~

ping-sun

mAP problem

4

I test the mAP result: 1: official_yolov3_weights_pytorch: (AP,IoU=0.5): 0.540 2: yolov3_weights_pytorch: (AP,IoU=0.5): 0.469, which is lower than what you says in 'weights/readme':0.5966

Yanxingang

the batch didn't slip when use muti-gpu

1

when i use two gpu and set the batch_size=16, i found that the batch is 16 on per gpu, not 8, why?

1453042287

I train the yolo in my dataset. Why I get these results as follows https://drive.google.com/file/d/1u_HnRLkJw14esg5WbmSrF23Nauo3icPo/view?usp=sharing https://drive.google.com/file/d/1PLIFPe2tbo0rihaNomkXgDfrlkpazZFR/view?usp=sharing

woshildh

is the loss_conf right in loss function?

2

Thanks for your work. i have a question. `loss_conf = .. + 0.5 * self.bce_loss(conf*noobj_mask,0)` why there is a zero? shouldn't it be`loss_conf = .. + 0.5 * self.bce_loss(conf*noobj_mask,tconf*noobj_mask)`? @BobLiu20...

Hsintao