You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 18, 2022. It is now read-only.
下载VOC2007和PASCAL_VOC_SSD300_weight_checkpoint-epoch-16-loss-3.3392.hdf5文件,运行SSD.py,可以识别自行车、人物,图片上都能正确标注区域,但是所有带猫的图片没有标注。
我自己fork了你的项目,https://github.com/sunjl/keras_ssd,修改了SSD.py文件:
自己训练模型,无法识别pics任一图片,怎么回事?
运行环境:Ubuntu 16.04,CUDA 8.0,Python 3.5,Keras 2.0.9,Tensorflow 1.3.0
GTX960显卡,4G显存不够用,所以把SSD.py文件中的batch改为1
The text was updated successfully, but these errors were encountered: