GitLab

For stitched models, the readin matrices and bias vectors are initialized to the
"alignment" matrix and bias specified in each dataset's .h5 file. If do_train_readin is
True, these will be trainable, and if not, they will be fixed.

`max_number_of_evaluation` -> `max_number_of_evaluations`.

__six__ is used on lines 174 and 175 but is never imported or defined.

In Python 2 the string and the r-string behave the same:
$ __python2__
```
>>> '$\Uparrow$ '
'$\\Uparrow$ '
>>> r'$\Uparrow$ '
'$\\Uparrow$ '
>>> '$\Uparrow$ ' == r'$\Uparrow$ '
True
```

In Python 3 the string raises a Syntax Error while the r-string works just like Python 2.
```
>>> '$\Uparrow$ '
  File "<stdin>", line 1
SyntaxError: (unicode error) 'unicodeescape' codec can't decode bytes in position 1-2: truncated \UXXXXXXXX escape
>>> r'$\Uparrow$ '
'$\\Uparrow$ '
```

See: https://github.com/tensorflow/models/pull/3220#discussion_r163131613

Added an 'env' parameter to env_step function since one an unreferenced one is used in the function.

Incorporated the suggested changes.

Use temp variable for predictions.

Before the fix the demo_inference.py used batch_norm and it did the
normalization of input image implicitly. If at inference time the
batch_norm was disabled the inference produced incorrect results.
This fix does the proper input image normalization and disables the batch_norm
at inference time.

Change in Object Dectection Model. Change parameter name given to RewriterConfig Proto. optimize_tensor_layout was changed to layout_optimizer in current tf version.

Fix AudioSet url

Fix typo: "the most is mostly converged" vs "the model is mostly converged"

Fixed one typo in my previous fix, added specific nltk data to install , mention unzip as a requirement