updated toy example to use minibatched function

Author: riceric22

examples/2D.ipynb

@@ -12,7 +12,9 @@
   {
    "cell_type": "code",
    "execution_count": 47,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import torch\n",
@@ -36,7 +38,9 @@
   {
    "cell_type": "code",
    "execution_count": 63,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# random points at least 2r apart\n",
@@ -66,7 +70,9 @@
   {
    "cell_type": "code",
    "execution_count": 64,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -122,7 +128,9 @@
   {
    "cell_type": "code",
    "execution_count": 65,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -162,6 +170,7 @@
    "cell_type": "code",
    "execution_count": 66,
    "metadata": {
+    "collapsed": false,
     "scrolled": true
    },
    "outputs": [
@@ -203,7 +212,7 @@
     "data = []\n",
     "opt = optim.Adam(robust_net.parameters(), lr=1e-3)\n",
     "for i in range(1000):\n",
-    "    robust_ce, robust_err = robust_loss_batch(robust_net, epsilon, Variable(X), Variable(y), False, False)\n",
+    "    robust_ce, robust_err = robust_loss(robust_net, epsilon, Variable(X), Variable(y))\n",
     "    out = robust_net(Variable(X))\n",
     "    l2 = nn.CrossEntropyLoss()(out, Variable(y))\n",
     "    err = (out.max(1)[1].data != y).float().mean()\n",
@@ -227,7 +236,9 @@
   {
    "cell_type": "code",
    "execution_count": 67,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -266,7 +277,9 @@
   {
    "cell_type": "code",
    "execution_count": 68,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "def plot_grid(net, ax): \n",
@@ -289,7 +302,9 @@
   {
    "cell_type": "code",
    "execution_count": 69,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -320,7 +335,9 @@
   {
    "cell_type": "code",
    "execution_count": 26,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -357,7 +374,9 @@
   {
    "cell_type": "code",
    "execution_count": 43,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
@@ -385,7 +404,9 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "ename": "AttributeError",
@@ -428,7 +449,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }