Data preparation problem

jessemelpolio / Faster_RCNN_for_DOTA

Code used for training Faster R-CNN on DOTA

https://arxiv.org/abs/1711.10398

Apache License 2.0

336 stars 102 forks source link

Data preparation problem #19

Closed diego1109 closed 4 years ago

diego1109 commented 6 years ago

I don't know how to produce the train.txt. and what in images and labelTx. Can you provide more detail. thanks your help

huangqiuyu commented 5 years ago

'train.txt' include all your image's name for training, but without suffix. You can use this code to split your images and labels, it will generate 'images' and 'labelTx', and then use 'ls > train.txt' in your images path, and then delete the suffix of image's name in 'train.txt'.

FoilHao commented 5 years ago

Do the two folders(images and labelTxt) include all images and annotations for training? Does the train.py recognize train and test datasets only by train.txt and test.txt?