Merge pull request #3 from AladdinPerzon/master

Code for the pool_backward from ConvNet on Deeplearning.ai

Author: fanghao6666

README.md

@@ -3,8 +3,8 @@
     * [***Neural Networks and Deep Learning***](https://www.coursera.org/learn/neural-networks-deep-learning/home/welcome)  
     * [***Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization***](https://www.coursera.org/learn/deep-neural-network/home/welcome) 
     * [***Structuring Machine Learning Projects***](https://www.coursera.org/learn/machine-learning-projects/home/welcome)
-    * [***Convolutional Neural Networks***]()
-    * [***Sequence Models***]()
+    * [***Convolutional Neural Networks***](https://www.coursera.org/learn/convolutional-neural-networks)
+    * [***Sequence Models***](https://www.coursera.org/learn/nlp-sequence-models)
 
 * [***Neural Networks and Deep Learning***](https://www.coursera.org/learn/neural-networks-deep-learning/home/welcome)
     * In this course, you will learn the foundations of deep learning. When you finish this class, you will:

notebook/Convolution model Step by Stepv1.ipynb

@@ -1228,16 +1228,16 @@
     "                        # Create the mask from a_prev_slice (≈1 line)\n",
     "                        mask = create_mask_from_window(a_prev_slice)\n",
     "                        # Set dA_prev to be dA_prev + (the mask multiplied by the correct entry of dA) (≈1 line)\n",
-    "                        dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += (mask * a_prev_slice)\n",
+    "                        dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += (dA[i, h, w, c] * mask)\n",
     "                        \n",
     "                    elif mode == \"average\":\n",
     "                        \n",
     "                        # Get the value a from dA (≈1 line)\n",
-    "                        da = dA\n",
+    "                        da = dA[i, h, w, c] \n",
     "                        # Define the shape of the filter as fxf (≈1 line)\n",
     "                        shape = (f,f)\n",
     "                        # Distribute it to get the correct slice of dA_prev. i.e. Add the distributed value of da. (≈1 line)\n",
-    "                        dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += da\n",
+    "                        dA_prev[i, vert_start: vert_end, horiz_start: horiz_end, c] += distribute_value(da, shape)\n",
     "                        \n",
     "    ### END CODE ###\n",
     "    \n",
@@ -1246,7 +1246,7 @@
     "    \n",
     "    return dA_prev\n",
     "\n",
-    "##### This code has some bugs that I have not found!"
+    "##### This code had some bugs, but I believe they are fixed now if you were to run the code above!"
    ]
   },
   {