in the rcnn model

`embedded_words_squeezed2.reverse()
embedding_afterward=self.right_side_last_word #tf.zeros((self.batch_size,self.embed_size)) # TODO self.right_side_last_word SHOULD WE ASSIGN A VARIABLE HERE
context_right_afterward = tf.zeros((self.batch_size, self.embed_size)) #self.right_side_context_last # TODO SHOULD WE ASSIGN A VARIABLE HERE
context_right_list

Current implementation does sequential sigmoid_out and mul_. We can get better performance by fusing this operations together.

Original line 87:
with open('README.md') as readme:

Corrected version of line 87:
with open('README.md','r',encoding='utf-8') as readme:

Explanation:
Windows uses GBK to decode rather than utf-8 at default setting

This should really help to keep a track of papers read so far. I would love to fork the repo and keep on checking the boxes in my local fork.

For example: Have a look at this section. People fork this repo and check the boxes as they finish reading each section.

Considering the MNIST dataset, wich has 5923 instances of the 0 class in the training set, I'm alittle confused about the following code for detemining the relative errors of the SGD classification model:

row_sums = conf_mx.sum(axis=1, keepdims=True)
norm_conf_mx = conf_mx / row_sums

(https://github.com/ageron/handson-ml/blob/master/03_classification.ipynb // In: 67)

Since using `axi

What's the ETA for updating the massively outdated documentation?

Please update all documents that are related building CNTK from source with latest CUDA dependencies that are indicated in CNTK.Common.props and CNTK.Cpp.props.
I tried to build from source, but it's a futile effort.

I am having difficulty in running this package as a Webservice. Would appreciate if we could provide any kind of documentation on implementing an API to get the keypoints from an image. Our aim is to able to deploy this API as an Azure Function and also know if it is feasible.

As I'm using anaconda2(python2 default), so when using :"conda env create -f build/environment.yml" need to specify the python version python=3, like :"conda env create python=3 -f build/environment.yml"

With the latest version of scipy.misc, scipy.misc.toimage is no longer available. To load and save an image as png we now have to use PIL, breaking tensorboard image summary.

Here is how I fixed the bug:
1./ At the end of main.py, log a uint8 image
logger.image_summary(tag, (images * 255).astype(np.uint8), step+1)
2./ In Logger class, package image as bytes with the PIL library (mode="L

transcribe.py has odd directory-scanning behavior which isn't documented

If you point --src to a directory, you get the error:

E Path in --src not existing

Looking at the code logic, the script expects a JSON file with a .catalog file extension. This is (1) not documented, and (2) not a really useful logic. It would be much better to point the script to a dir, and scan f