search

BobLiu20 / YOLOv3_PyTorch

Full implementation of YOLOv3 in PyTorch
624 stars 191 forks source link

About the training process and question #16

Open ThorinGondor opened 6 years ago

ThorinGondor commented 6 years ago

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 too high or something goes wrong? At the begining the loss is 5.1 and then quickly goes down to 0.5. Then in following 1 or 2 epochs the downward trend of loss is almost disappeared, always about 0.7-0.4. Is this normal? (2) The detection is none or has many faults. I'm not sure if it's because the training is not enough & sufficient. Maybe COCO is hard to train and needs many train epochs? Could you tell me? Danke for your reply!

ThorinGondor commented 6 years ago

Issues addressed. I forgot using the pretrained net. Subconsciously I supposed that your YOLO training process don't need to use the pretrained net.

BCWang93 commented 5 years ago

Issues addressed. I forgot using the pretrained net. Subconsciously I supposed that your YOLO training process don't need to use the pretrained net.

Hi,how do you solve this problem?I have some problem like this now.The loss is in 0.4-0.7,and,when I test the image, the output is none?Can you tell me how do you solve it?Thank you very much!