Raffi Khatchadourian

Fix bibtex citation in README.md

1

I am getting an error from `biblatex` that the entry has too many commas.

Fix https://github.com/tensorflow/models/issues/10474. CSVs should be text files. ## Type of change - [X] Bug fix (non-breaking change which fixes an issue) ## Tests I followed the instructions at https://github.com/tensorflow/models/blob/b4c7ea90e8e9209c568d1b59f71432cfd69bb688/research/delf/delf/python/training/README.md#prepare-the-data-for-training. ##...

Otherwise, the script fails if it doesn't exist. ## Type of change - [X] Bug fix (non-breaking change which fixes an issue) ## Tests I followed the instructions at https://github.com/tensorflow/models/blob/b4c7ea90e8e9209c568d1b59f71432cfd69bb688/research/delf/delf/python/training/README.md#prepare-the-data-for-training....

InvalidArgumentError: Boxes contains at least one element that is not finite

1

During the "overfitting a sample" section, I get the following error after the batch processing: ``` ... ('batch', 96, '-', 0.31591606) ('batch', 97, '-', 0.20713705) ('batch', 98, '-', 0.19917412) ('batch',...

Don't load the weights

1

We are training from scratch in the code later on in this file. I left it as a comment in case someone wants to load a pretrained model. See https://github.com/Viredery/tf-eager-fasterrcnn/issues/27#issuecomment-2263461724.

Fixes https://github.com/Viredery/tf-eager-fasterrcnn/issues/20?

Can't load weights when training the model

3

I'm getting the following error when trying to train the model: ``` Traceback (most recent call last): File "/home/user/git/Python-Subjects/tf-eager-fasterrcnn/train_model.py", line 73, in model.load_weights('weights/faster_rcnn.h5', by_name=True) File "/home/user/.local/lib/python3.10/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler...

# Prerequisites Please answer the following question for yourself before submitting an issue. - [X] I checked to make sure that this feature has not been requested already. ## 1....

Not tracking tensors returned by `tf.reshape()` for data sources other than MNIST

5

Consider the following code: ```python # tf2_test_reshape.py # From https://www.tensorflow.org/versions/r2.9/api_docs/python/tf/reshape import tensorflow as tf def f(a): pass t1 = tf.ones([2, 3]) t2 = tf.reshape(t1, [6]) f(t2) ``` `t2` should be...

Drop support for Python 2/Jython 2

1

Supporting both Python 3 / Jython 3 and Python 2 / Jython 2 simultaneously is making test maintenance very difficult. I don't think we need support for Python 2 /...