A more consistent and multi-functional global level of verbosity control,
suggest an enhancement that will see print(...) in project be converted to using the python logging. module

import logging
#Then instead of print() use either
logging.info(......)
#or
logging.debug(.....)
#or
logging.warning(....)
#or
#logging.error()

In that way verbosity can be globally

Damn. Is there any one who can clearly explain below two lines???
link

matches = truths[best_truth_idx]          # Shape: [num_priors,4]
conf = labels[best_truth_idx] + 1         # Shape: [num_priors]

When attempting to download cityscapes_2048x1024 I got: ./download-models.sh: line 721: download_fcn_resnet18_cityscapes_2048x512: command not found
It looks like there was a typo, and line 721 needs to be changed from:
download_fcn_resnet18_cityscapes_2048x512 to download_fcn_resnet18_cityscapes_2048x1024

Thanks for the amazing repo!

There is a section that I think could improve the docs in https://github.com/reshamas/fastai_deeplearn_part1/blob/master/tools/paperspace.md

Some users may need to run the line sudo ufw allow 8888 to allow traffic over the port 8888, as sometimes it is not open by default.

This was necessary for me to be able to connect with jupyter notebook

Source: http://forums.fast.ai/t/paperspace-ju

I want to integrate the model programmatically, how to receive more detailed information from the output model. How are the tensors named and structured in the graph to receive information like this (if available):

input:

image data bytes

output:

bounding box location
score/probability
single character location

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.

In the paper the Table 1 Bottom layers should be addressed as Top Layers and vice versa. Because, the all layers except input layers are being updated and X0 is the input layer and is written under the column of bottom layers so maybe I think either the column names should be switched.
I make above understanding based on the assumption that the top layers update the bottom layers.
If I misunder

pip insatll tensorflow==2.0.0 or pip install tensorflow==2.0.0-beta1，tensorflow2.0.0or tensorflow2.0.0-beta1,but when I run train.py, the error of "ValueError: This converter can only convert a single ConcreteFunction. Converting multiple functions is under development" appears,why?How to do?