schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use tensorflow_graph_in_jupyter.py in notebooks, fixes #223

main
Aurélien Geron 2018-05-18 21:22:56 +02:00
parent ef2a7b5bd0
commit 703815bca9
5 changed files with 30 additions and 197 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
09_up_and_running_with_tensorflow.ipynb
View File

@ -114,9 +114,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 5,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"sess.close()" "sess.close()"
@ -168,9 +166,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 10,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"init = tf.global_variables_initializer()" "init = tf.global_variables_initializer()"
@ -191,9 +187,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 12,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"sess.close()" "sess.close()"
@ -383,9 +377,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 23, "execution_count": 23,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from sklearn.preprocessing import StandardScaler\n", "from sklearn.preprocessing import StandardScaler\n",
@ -491,9 +483,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 28, "execution_count": 28,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"gradients = tf.gradients(mse, [theta])[0]" "gradients = tf.gradients(mse, [theta])[0]"
@ -533,9 +523,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 30, "execution_count": 30,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"def my_func(a, b):\n", "def my_func(a, b):\n",
@ -620,9 +608,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 35, "execution_count": 35,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)\n", "optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)\n",
@ -680,9 +666,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 38, "execution_count": 38,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate,\n", "optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate,\n",
@ -692,9 +676,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 39, "execution_count": 39,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"training_op = optimizer.minimize(mse)\n", "training_op = optimizer.minimize(mse)\n",
@ -780,9 +762,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 44, "execution_count": 44,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"reset_graph()\n", "reset_graph()\n",
@ -794,9 +774,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 45, "execution_count": 45,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name=\"theta\")\n", "theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0, seed=42), name=\"theta\")\n",
@ -812,9 +790,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 46, "execution_count": 46,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"n_epochs = 10" "n_epochs = 10"
@ -823,9 +799,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 47, "execution_count": 47,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"batch_size = 100\n", "batch_size = 100\n",
@ -947,9 +921,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 54, "execution_count": 54,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"saver = tf.train.Saver({\"weights\": theta})" "saver = tf.train.Saver({\"weights\": theta})"
@ -1003,50 +975,20 @@
"## inside Jupyter" "## inside Jupyter"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To visualize the graph within Jupyter, we will use a TensorBoard server available online at https://tensorboard.appspot.com/ (so this will not work if you do not have Internet access). As far as I can tell, this code was originally written by Alex Mordvintsev in his [DeepDream tutorial](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/deepdream/deepdream.ipynb). Alternatively, you could use a tool like [tfgraphviz](https://github.com/akimach/tfgraphviz)."
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 57, "execution_count": 57,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from IPython.display import clear_output, Image, display, HTML\n", "from tensorflow_graph_in_jupyter import show_graph"
"\n",
"def strip_consts(graph_def, max_const_size=32):\n",
" \"\"\"Strip large constant values from graph_def.\"\"\"\n",
" strip_def = tf.GraphDef()\n",
" for n0 in graph_def.node:\n",
" n = strip_def.node.add() \n",
" n.MergeFrom(n0)\n",
" if n.op == 'Const':\n",
" tensor = n.attr['value'].tensor\n",
" size = len(tensor.tensor_content)\n",
" if size > max_const_size:\n",
" tensor.tensor_content = b\"<stripped %d bytes>\"%size\n",
" return strip_def\n",
"\n",
"def show_graph(graph_def, max_const_size=32):\n",
" \"\"\"Visualize TensorFlow graph.\"\"\"\n",
" if hasattr(graph_def, 'as_graph_def'):\n",
" graph_def = graph_def.as_graph_def()\n",
" strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
" code = \"\"\"\n",
" <script>\n",
" function load() {{\n",
" document.getElementById(\"{id}\").pbtxt = {data};\n",
" }}\n",
" </script>\n",
" <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
" <div style=\"height:600px\">\n",
" <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
" </div>\n",
" \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
"\n",
" iframe = \"\"\"\n",
" <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
" \"\"\".format(code.replace('\"', '&quot;'))\n",
" display(HTML(iframe))"
] ]
}, },
{ {

43
10_introduction_to_artificial_neural_networks.ipynb
View File

@ -524,44 +524,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Works on Chrome, not guaranteed on other browsers\n", "from tensorflow_graph_in_jupyter import show_graph"
"\n",
"from IPython.display import clear_output, Image, display, HTML\n",
"\n",
"def strip_consts(graph_def, max_const_size=32):\n",
" \"\"\"Strip large constant values from graph_def.\"\"\"\n",
" strip_def = tf.GraphDef()\n",
" for n0 in graph_def.node:\n",
" n = strip_def.node.add() \n",
" n.MergeFrom(n0)\n",
" if n.op == 'Const':\n",
" tensor = n.attr['value'].tensor\n",
" size = len(tensor.tensor_content)\n",
" if size > max_const_size:\n",
" tensor.tensor_content = b\"<stripped %d bytes>\"%size\n",
" return strip_def\n",
"\n",
"def show_graph(graph_def, max_const_size=32):\n",
" \"\"\"Visualize TensorFlow graph.\"\"\"\n",
" if hasattr(graph_def, 'as_graph_def'):\n",
" graph_def = graph_def.as_graph_def()\n",
" strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
" code = \"\"\"\n",
" <script>\n",
" function load() {{\n",
" document.getElementById(\"{id}\").pbtxt = {data};\n",
" }}\n",
" </script>\n",
" <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
" <div style=\"height:600px\">\n",
" <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
" </div>\n",
" \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
"\n",
" iframe = \"\"\"\n",
" <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
" \"\"\".format(code.replace('\"', '&quot;'))\n",
" display(HTML(iframe))"
] ]
}, },
{ {
@ -676,7 +639,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 38, "execution_count": 37,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -697,7 +660,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 39, "execution_count": 38,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [

39
11_deep_learning.ipynb
View File

@ -1066,44 +1066,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Works on Chrome, not guaranteed on other browsers\n", "from tensorflow_graph_in_jupyter import show_graph"
"\n",
"from IPython.display import clear_output, Image, display, HTML\n",
"\n",
"def strip_consts(graph_def, max_const_size=32):\n",
" \"\"\"Strip large constant values from graph_def.\"\"\"\n",
" strip_def = tf.GraphDef()\n",
" for n0 in graph_def.node:\n",
" n = strip_def.node.add() \n",
" n.MergeFrom(n0)\n",
" if n.op == 'Const':\n",
" tensor = n.attr['value'].tensor\n",
" size = len(tensor.tensor_content)\n",
" if size > max_const_size:\n",
" tensor.tensor_content = b\"<stripped %d bytes>\"%size\n",
" return strip_def\n",
"\n",
"def show_graph(graph_def, max_const_size=32):\n",
" \"\"\"Visualize TensorFlow graph.\"\"\"\n",
" if hasattr(graph_def, 'as_graph_def'):\n",
" graph_def = graph_def.as_graph_def()\n",
" strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
" code = \"\"\"\n",
" <script>\n",
" function load() {{\n",
" document.getElementById(\"{id}\").pbtxt = {data};\n",
" }}\n",
" </script>\n",
" <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
" <div style=\"height:600px\">\n",
" <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
" </div>\n",
" \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
"\n",
" iframe = \"\"\"\n",
" <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
" \"\"\".format(code.replace('\"', '&quot;'))\n",
" display(HTML(iframe))"
] ]
}, },
{ {

39
14_recurrent_neural_networks.ipynb
View File

@ -236,42 +236,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from IPython.display import clear_output, Image, display, HTML\n", "from tensorflow_graph_in_jupyter import show_graph"
"\n",
"def strip_consts(graph_def, max_const_size=32):\n",
" \"\"\"Strip large constant values from graph_def.\"\"\"\n",
" strip_def = tf.GraphDef()\n",
" for n0 in graph_def.node:\n",
" n = strip_def.node.add() \n",
" n.MergeFrom(n0)\n",
" if n.op == 'Const':\n",
" tensor = n.attr['value'].tensor\n",
" size = len(tensor.tensor_content)\n",
" if size > max_const_size:\n",
" tensor.tensor_content = \"b<stripped %d bytes>\"%size\n",
" return strip_def\n",
"\n",
"def show_graph(graph_def, max_const_size=32):\n",
" \"\"\"Visualize TensorFlow graph.\"\"\"\n",
" if hasattr(graph_def, 'as_graph_def'):\n",
" graph_def = graph_def.as_graph_def()\n",
" strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
" code = \"\"\"\n",
" <script>\n",
" function load() {{\n",
" document.getElementById(\"{id}\").pbtxt = {data};\n",
" }}\n",
" </script>\n",
" <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
" <div style=\"height:600px\">\n",
" <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
" </div>\n",
" \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
"\n",
" iframe = \"\"\"\n",
" <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
" \"\"\".format(code.replace('\"', '&quot;'))\n",
" display(HTML(iframe))"
] ]
}, },
{ {
@ -2527,7 +2492,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.6.2" "version": "3.5.2"
}, },
"nav_menu": {}, "nav_menu": {},
"toc": { "toc": {

2
tensorflow_graph_in_jupyter.py
View File

@ -23,7 +23,7 @@ def strip_consts(graph_def, max_const_size=32):
tensor = n.attr['value'].tensor tensor = n.attr['value'].tensor
size = len(tensor.tensor_content) size = len(tensor.tensor_content)
if size > max_const_size: if size > max_const_size:
tensor.tensor_content = "<stripped %d bytes>"%size tensor.tensor_content = b"<stripped %d bytes>"%size
return strip_def return strip_def
def show_graph(graph_def, max_const_size=32): def show_graph(graph_def, max_const_size=32):