Open flaviut opened 5 years ago
Agreed, this should be documented. For the time being, object detection models are pre-trained ones from Tensorflow Model Zoo. Other ones like the style model were trained by me but I need to make sure the datasets are fully reproducible.
It'd be nice if there was some documentation explaining how the model files, like
faster_rcnn_inception_resnet_v2_atrous_lowproposals_oid_2018_01_28_frozen_inference_graph.pb.xz
, are created.