adding readme and image

Author: soumith

Introduction to PyTorch for former Torchies.ipynb

@@ -377,7 +377,9 @@
     "\n",
     "In autograd, we introduce a `Variable` class, which is a very thin wrapper around a `Tensor`. \n",
     "You can access the raw tensor through the `.data` attribute, and after computing the backward pass, a gradient w.r.t. this variable is accumulated into `.grad` attribute.\n",
-    "[Image: https://fb.quip.com/-/blob/WUCAAAluOup/gzkg-mq1VLAc3DlafCX1mg]\n",
+    "\n",
+    "![Variable](images/Variable.png)\n",
+    "\n",
     "There's one more class which is very important for autograd implementation - a `Function`. `Variable` and `Function` are interconnected and build up an acyclic graph, that encodes a complete history of computation. Each variable has a `.creator` attribute that references a function that has created a function (except for Variables created by the user - these have `None` as  `.creator`).\n",
     "\n",
     "If you want to compute the derivatives, you can call `.backward()` on a `Variable`. \n",

README.md

@@ -0,0 +1,7 @@
+PyTorch Tutorials
+-----------------
+
+1. [Introduction to PyTorch for former Torchies](Introduction to PyTorch for former Torchies.ipynb)
+   - A perfect introduction to PyTorch's torch, autograd, nn and optim APIs for the former Torch user
+2. Custom C extensions
+   - Write your own C code that interfaces into PyTorch