Merge branch 'master' of github.com:ixaxaar/pytorch-dnc into sparse

README.md

@@ -2,6 +2,8 @@
 
 [![Build Status](https://travis-ci.org/ixaxaar/pytorch-dnc.svg?branch=master)](https://travis-ci.org/ixaxaar/pytorch-dnc) [![PyPI version](https://badge.fury.io/py/dnc.svg)](https://badge.fury.io/py/dnc)
 
+[![Build Status](https://travis-ci.org/ixaxaar/pytorch-dnc.svg?branch=master)](https://travis-ci.org/ixaxaar/pytorch-dnc) [![PyPI version](https://badge.fury.io/py/dnc.svg)](https://badge.fury.io/py/dnc)
+
 This is an implementation of [Differentiable Neural Computers](http://people.idsia.ch/~rupesh/rnnsymposium2016/slides/graves.pdf), described in the paper [Hybrid computing using a neural network with dynamic external memory, Graves et al.](https://www.nature.com/articles/nature20101)
 and the Sparse version of the DNC (the SDNC) described in [Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes](http://papers.nips.cc/paper/6298-scaling-memory-augmented-neural-networks-with-sparse-reads-and-writes.pdf).
 
@@ -36,6 +38,8 @@ Tested on `ubuntu 16.04`, `Arch / Manjaro` and `Fedora 27`.
 
 Following are the constructor parameters:
 
+Following are the constructor parameters:
+
 | Argument | Default | Description |
 | --- | --- | --- |
 | input_size | `None` | Size of the input vectors |

tasks/copy_task.py

@@ -207,8 +207,13 @@ if __name__ == '__main__':
 
     last_save_losses.append(loss_value)
 
-    if summarize:
+    if summarize and rnn.debug:
       loss = np.mean(last_save_losses)
+      # print(input_data)
+      # print("1111111111111111111111111111111111111111111111")
+      # print(target_output)
+      # print('2222222222222222222222222222222222222222222222')
+      # print(F.relu6(output))
       llprint("\n\tAvg. Logistic Loss: %.4f\n" % (loss))
       if np.isnan(loss):
         raise Exception('nan Loss')