Re-run, set the random seeds for reproducible results

Author: nitnelave

00 Basic solver usage.ipynb

@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {
     "collapsed": true
    },
@@ -54,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -77,7 +77,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
@@ -113,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false
    },
@@ -133,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {
     "collapsed": true
    },
@@ -153,7 +153,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {
     "collapsed": true
    },
@@ -164,49 +164,29 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[('iter', 10000),\n",
-       " ('net', <caffe._caffe.Net at 0x1f9d488>),\n",
-       " ('restore',\n",
-       "  <bound method SGDSolver.restore of <caffe._caffe.SGDSolver object at 0x1fb19f0>>),\n",
-       " ('set_iter',\n",
-       "  <bound method SGDSolver.set_iter of <caffe._caffe.SGDSolver object at 0x1fb19f0>>),\n",
-       " ('snapshot',\n",
-       "  <bound method SGDSolver.snapshot of <caffe._caffe.SGDSolver object at 0x1fb19f0>>),\n",
-       " ('solve',\n",
-       "  <bound method SGDSolver.solve of <caffe._caffe.SGDSolver object at 0x1fb19f0>>),\n",
-       " ('step',\n",
-       "  <bound method SGDSolver.step of <caffe._caffe.SGDSolver object at 0x1fb19f0>>),\n",
-       " ('test_nets', <caffe._caffe.NetVec at 0x49f4de0>)]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "[(e, getattr(solver, e)) for e in dir(solver) if not e.startswith(\"__\")]"
+    "And there you go! This is the Python equivalent of\n",
+    "`example/mnist/train_lenet.sh`, or\n",
+    "\n",
+    "`$ caffe train --solver=examples/mnist/lenet_solver.prototxt`"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "And there you go! This is the Python equivalent of\n",
-    "`example/mnist/train_lenet.sh`, or\n",
-    "\n",
-    "`$ caffe train --solver=examples/mnist/lenet_solver.prototxt`\n",
+    "You can always consult at which iteration a solver is, with `solver.iter`. You can take a snapshot of the solver with `solver.snapshot(file)`, and load it with `solver.restort(file)`. You can choose to move step-by-step with `solver.step(step_num)`.\n",
     "\n",
-    "But you can do much more than that with python. The next part covers network manipulation."
+    "The underlying nets can be accessed with `solver.net` for the training net, and `solver.test_nets` for the testing nets."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "But you can do much more than that with python, you don't have to use a pre-made solver limiting your possibilities. The next part covers network manipulation."
    ]
   }
  ],

01 Loading a network.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 1,
    "metadata": {
     "collapsed": true
    },
@@ -144,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {
     "collapsed": true
    },
@@ -188,7 +188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {
     "collapsed": true
    },
@@ -227,7 +227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {
     "collapsed": false
    },
@@ -259,7 +259,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {
     "collapsed": true
    },
@@ -277,7 +277,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 9,
    "metadata": {
     "collapsed": false
    },
@@ -350,7 +350,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "metadata": {
     "collapsed": true
    },
@@ -368,7 +368,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "metadata": {
     "collapsed": true
    },
@@ -388,7 +388,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "metadata": {
     "collapsed": true
    },