low mAP, high classification loss in eval - object detection resnet 50
qazalkz opened this issue · 6 comments
Hi guys. I have about 4000 images and Im using resnrt50 640*640 with 70000 steps. but after all Im getting low mAP. could you please give me some advice.
p.n: also I divide original learning rate to my batch size
pipeline_config.model.ssd.num_classes = 1
pipeline_config.train_config.batch_size = 64//8
pipeline_config.train_config.fine_tune_checkpoint = "checkpointmodels/retina101/ssd_/checkpoint/ckpt-0"
pipeline_config.train_config.fine_tune_checkpoint_type = "detection"
pipeline_config.train_input_reader.label_map_path= LABELMAP
pipeline_config.train_config.optimizer.momentum_optimizer.learning_rate.cosine_decay_learning_rate.warmup_learning_rate=0.013333000242710114/8
pipeline_config.train_config.optimizer.momentum_optimizer.learning_rate.cosine_decay_learning_rate.learning_rate_base=0.03999999910593033/8
on 20000 stept eval
on 70000 steps
also you can see that classification loss is high on eval output
The model might be overfitting. Try increasing the learning rate and adding image augmentation.
thanks. I'll do it and share the results.
Hi @qazalkz,
Sorry for the late response and Please work out on @Sam-Seaberry suggestions,it might solve the issue .This question is better asked on StackOverflow and TensorFlow Forum since it is not a bug or feature request. There is also a larger community that reads questions there.
Thanks for understanding.
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.