I've annotated new image with new class according to the approach is recommended by http://www.immersivelimit.com/tutorials/create-coco-annotations-from-scratch then I combined new class annotations with coco json annotate files and create TFrecord by running create_coco_tf_record.py from this repository : https://github.com/tensorflow/models/tree/master/research/object_detection/dataset_tools then I retrained faster_rcnn_resnet101 which its pretrained model is available in Tensorflow Model Zoo. I did retrain process according to this tutorial: https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 the problem is that the loss curve didn't converge and also had oscillation!! how can I do to get better result from retraining models?
Asked
Active
Viewed 620 times
0
-
Your learning rate might be to large, try a smaller learning rate. – Danny Fang Apr 20 '19 at 09:46
-
Thanks for your response, but I tried this solution and the results didn’t change! What can I do more? – Mozhgan vazifehdoost Apr 23 '19 at 16:36