Bug: Using images out of ImageSets\Main\trainval.txt for training

Open jamiechoi1995 opened this issue 6 years ago • 1 comments

In convert_tfrecords.py, it converts all images in VOCdevkit\VOC2012\JPEGImages into tfrecords for training, https://github.com/HiKapok/SSD.TensorFlow/blob/b47ff6164c8925a8bbccc593719d5bbbab996058/dataset/convert_tfrecords.py#L366-L370

However, not all the images in VOC2012 are for detection, there are only 11540 images specified in ImageSets\Main\trainval.txt for detection. But in JPEGImages there are 17125 images, these extra images are for action classification, so they only annotate human, ignoring other classes. Eg,

Using these images will be harmful for training.

Apr 15 '19 05:04 jamiechoi1995

after removing the images and using 11540 images to train the model, I got 0.7785 mAP with the default settings using model-ckpt-116604

Apr 17 '19 06:04 jamiechoi1995