thtrieu/darkflow

training my own data set with ']' output predict

Open

#300 aberto em 23 de jun. de 2017

Ver no GitHub
 (7 comments) (0 reactions) (0 assignees)Python (2.102 forks)batch import
bughelp wanted

Métricas do repositório

Stars
 (6.120 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

hi I tried to train my own data set using cfg/tiny-yolo-voc.cfg tiny-yolo-voc.weight. I have changed the class to 2, lable.txt, and the last conv filter to 35(5*(2+5)) the training script is as follow: ./flow --model cfg/tiny-yolo-voc-1.cfg --load bin/tiny-yolo-voc.weights --train --annotation train/Annotations --dataset train/JPEGImages --gpu 1.0 --batch 30 --epoch 100 after trained the loss is under 2.0 the testing script is: /flow --imgdir test_dir/ --model cfg/tiny-yolo-voc.cfg --load -1 --json the result is ']' why is it ? the sample under test data is just a training data.

Guia do colaborador