Not backward compatible - re-installation is required

* Fixes for PyTorch==1.0.0
* Refactoring folder structure
* Update installation section in docs

This patch corrects overlapping between
magnitude_fn and block_shape arguments during
block pruning.

Add a default value for the new parameter 'normalize_dataparallel_keys'

Sometime Symlinks can't be created, so we fail queitly.

--amc-reward-frequency
Computing the reward requires running the evaluated network on the Test
dataset (or parts of it) and may involve short-term fine-tuning before
the evaluation (depending on the configuration).
Use this new argument to configure the number of steps/iterations between
reward computation.

A small change to support ranking weight filters by the mean mean-value
of the feature-map channels.
Mean mean-value refers to computing the average value (across many
input images) of the mean-value of each channel.

Modified log_execution_env_state() to store
configuration file in the output directory,
under 'configs' sub-directory it creates.

At this time, the only configuration file is
passed via args.compress

To use automated compression you need to install several optional packages
which are not required for other use-cases.
This fix hides the import requirements for users who do not want to install
the extra packages.

The new directory 'examples/baseline_networks' contains YAML schedules
that we used to train the baseline networks for our experiments.
Theses scripts are currently scattered across the repository, so as a
first step I'm collecting them using softlinks.  Later we will physically
move these files to 'examples/baseline_networks', and remove the soft-links.

Merging the 'amc' branch with 'master'.
This updates the automated compression code in 'master', and adds a greedy filter-pruning algorithm.

This commit fixes (and adds a test) for the case that we with to load
a thinned GPU checkpoint onto the CPU.

The root-cause of issue #148 is that DataParallel modules cannot execute on the CPU,
on machines that have both CPUs and GPUs.
Therefore, we don’t use DataParallel for models loaded for the CPUs, but we do wrap
the models with DataParallel when loaded on the GPUs (to make them run faster).
The names of module keys saved in a checkpoint file depend if the modules are wrapped
by a DataParallel module or not.  So loading a checkpoint that ran on the GPU onto a
CPU-model (and vice-versa) will fail on the keys.
This is all PyTorch and despite the community asking for a fix -
e.g. https://github.com/pytorch/pytorch/issues/7457 - it is still pending.

This commit contains code to catch key errors when loading a GPU-generated model
(i.e. with DataParallel) onto a CPU, and convert the names of the keys.

This PR also merges refactoring to load_chackpoint.py done by @barrh, who also added
a test to further test loading checkpoints.

Added recent Distiller citations

Summary of changes:
(1) Post-train quantization based on pre-collected statistics
(2) Quantized concat, element-wise addition / multiplication and embeddings
(3) Move post-train quantization command line args out of sample code
(4) Configure post-train quantization from YAML for more fine-grained control

(See PR #136 for more detailed changes descriptions)

* For CIFAR-10 / ImageNet only
* Refactor data_loaders.py, reduce code duplication
* Implemented custom sampler
* Integrated in image classification sample
* Since we now shuffle the test set, had to update expected results
  in 2 full_flow_tests that do evaluation

A parameter was missing from one of the function calls.

Expand the command line arguments to recreate the original
command line invocation.

The use of DataParallel is causing various small problems when used
in conjunction with SummaryGraph.
The best solution is to force SummaryGraph to use a non-data-parallel
version of the model and to always normalize node names when accessing
SummaryGraph operations.

Specifically, gracefully handle a missing 'epoch' key in a loaded
checkpoint file.

* Current implementation doesn't play nice with DataParallel, so allow
  only with single GPU for now
* Bug-fix: Update ranges only when training (not in eval)
* Refactor activation replacement function - explicit module instead of
  sequential

* Always include 0 in the range
* Handle case where tensor is zeros only (fixes issue #115)
* Add unit tests

* Support for multi-phase activations logging

Enable logging activation both durning training and validation at
the same session.

* Refactoring: Move parser to its own file

* Parser is moved from compress_classifier into its own file.
* Torch version check is moved to precede main() call.
* Move main definition to the top of the file.
* Modify parser choices to case-insensitive

Fix a mismatch between the location of the model and the
computation.

When masks are loaded from a checkpoint file, they should use the
same device as the model.