I am trying to migrate my project from TF1 to TF2. However, after certain round of training, I noticed that the training conducted in TF2 was not capable of capturing certain object characteristic (which was doing well in TF1).
I am using Mask RCNN Inception Resnet V2 pre-trained model for both scenarios, the model for TF2 was obtained from https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md and https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md for TF1. Mask R-CNN Inception ResNet V2 1024x1024 mask_rcnn_inception_resnet_v2_atrous_coco
The image set used for training and evaluation were same for both scenario and parameter in the pipeline.config is minimal (only in the feature extractor section, exception occurred if I changed it to what it is in TF1). Differences between feature extractor
How should I do to make the Mask R-CNN Inception Resnet V2 to perform as good as in TF1? Or is it possible to convert the model from TF1 model zoo so that it is compatible with TF2?
I run the inference on same dataset in both TF1 and TF2, and TF1 got significant lesser overkill in overall while TF2 was too easily affected by background noise.