MachineLearning/hands-on
1
0
Fork 0
Code Issues Pull Requests Releases Activity

Add notebooks for chapters 5 to 14

Browse Source
This commit is contained in:
Aurelien Geron
2016-09-27 23:31:21 +02:00
parent ade25b2aff
commit da638e55e4
30 changed files with 13471 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
.gitignore vendored
View File

@@ -1,5 +1,10 @@
.ipynb_checkpoints
.DS_Store
my_*
images/**/*.png
*.bak
*.ckpt
*.pyc
.DS_Store
.ipynb_checkpoints
checkpoint
logs/*
tf_logs/*
images/**/*.png
my_*

2
fundamentals.ipynb → 01_the_machine_learning_landscape.ipynb
View File

@@ -4,7 +4,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"**Chapter 1 – Fundamentals of Machine Learning**\n",
"**Chapter 1 – The Machine Learning landscape**\n",
"\n",
"_This is the code used to generate some of the figures in chapter 1._"
]

2
end_to_end_project.ipynb → 02_end_to_end_machine_learning_project.ipynb
View File

@@ -4,7 +4,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"**Chapter 2 – End to end Machine Learning project**\n",
"**Chapter 2 – End-to-end Machine Learning project**\n",
"\n",
"*Welcome to Machine Learning Housing Corp.! Your task is to predict median house values in Californian districts, given a number of features from these districts.*\n",
"\n",

0
training_linear_models.ipynb → 04_training_linear_models.ipynb
View File

1749
05_support_vector_machines.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

686
06_decision_trees.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1101
07_ensemble_learning_and_random_forests.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1906
08_dimensionality_reduction.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

2234
09_up_and_running_with_tensorflow.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

908
10_introduction_to_artificial_neural_networks.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

1311
11_deep_learning.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

556
12_distributed_tensorflow.ipynb Normal file
View File

@@ -0,0 +1,556 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Chapter 12 – Distributed TensorFlow**"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"_This notebook contains all the sample code and solutions to the exercices in chapter 12._"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Setup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, let's make sure this notebook works well in both python 2 and 3, import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# To support both python 2 and python 3\n",
"from __future__ import division, print_function, unicode_literals\n",
"\n",
"# Common imports\n",
"import numpy as np\n",
"import numpy.random as rnd\n",
"import os\n",
"\n",
"# to make this notebook's output stable across runs\n",
"rnd.seed(42)\n",
"\n",
"# To plot pretty figures\n",
"%matplotlib inline\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
"plt.rcParams['axes.labelsize'] = 14\n",
"plt.rcParams['xtick.labelsize'] = 12\n",
"plt.rcParams['ytick.labelsize'] = 12\n",
"\n",
"# Where to save the figures\n",
"PROJECT_ROOT_DIR = \".\"\n",
"CHAPTER_ID = \"distributed\"\n",
"\n",
"def save_fig(fig_id, tight_layout=True):\n",
" path = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID, fig_id + \".png\")\n",
" print(\"Saving figure\", fig_id)\n",
" if tight_layout:\n",
" plt.tight_layout()\n",
" plt.savefig(path, format='png', dpi=300)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Local server"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import tensorflow as tf"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"c = tf.constant(\"Hello distributed TensorFlow!\")\n",
"server = tf.train.Server.create_local_server()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"b'Hello distributed TensorFlow!'\n"
]
}
],
"source": [
"with tf.Session(server.target) as sess:\n",
" print(sess.run(c))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Cluster"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"cluster_spec = tf.train.ClusterSpec({\n",
" \"ps\": [\n",
" \"127.0.0.1:2221\", # /job:ps/task:0\n",
" \"127.0.0.1:2222\", # /job:ps/task:1\n",
" ],\n",
" \"worker\": [\n",
" \"127.0.0.1:2223\", # /job:worker/task:0\n",
" \"127.0.0.1:2224\", # /job:worker/task:1\n",
" \"127.0.0.1:2225\", # /job:worker/task:2\n",
" ]})"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"task_ps0 = tf.train.Server(cluster_spec, job_name=\"ps\", task_index=0)\n",
"task_ps1 = tf.train.Server(cluster_spec, job_name=\"ps\", task_index=1)\n",
"task_worker0 = tf.train.Server(cluster_spec, job_name=\"worker\", task_index=0)\n",
"task_worker1 = tf.train.Server(cluster_spec, job_name=\"worker\", task_index=1)\n",
"task_worker2 = tf.train.Server(cluster_spec, job_name=\"worker\", task_index=2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pinning operations across devices and servers"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"tf.reset_default_graph()\n",
"\n",
"with tf.device(\"/job:ps\"):\n",
" a = tf.Variable(1.0, name=\"a\")\n",
"\n",
"with tf.device(\"/job:worker\"):\n",
" b = a + 2\n",
"\n",
"with tf.device(\"/job:worker/task:1\"):\n",
" c = a + b"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"4.0\n"
]
}
],
"source": [
"with tf.Session(\"grpc://127.0.0.1:2221\") as sess:\n",
" sess.run(a.initializer)\n",
" print(c.eval())"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"tf.reset_default_graph()\n",
"\n",
"with tf.device(tf.train.replica_device_setter(\n",
" ps_tasks=2,\n",
" ps_device=\"/job:ps\",\n",
" worker_device=\"/job:worker\")):\n",
" v1 = tf.Variable(1.0, name=\"v1\") # pinned to /job:ps/task:0 (defaults to /cpu:0)\n",
" v2 = tf.Variable(2.0, name=\"v2\") # pinned to /job:ps/task:1 (defaults to /cpu:0)\n",
" v3 = tf.Variable(3.0, name=\"v3\") # pinned to /job:ps/task:0 (defaults to /cpu:0)\n",
" s = v1 + v2 # pinned to /job:worker (defaults to task:0/cpu:0)\n",
" with tf.device(\"/task:1\"):\n",
" p1 = 2 * s # pinned to /job:worker/task:1 (defaults to /cpu:0)\n",
" with tf.device(\"/cpu:0\"):\n",
" p2 = 3 * s # pinned to /job:worker/task:1/cpu:0\n",
"\n",
"config = tf.ConfigProto()\n",
"config.log_device_placement = True\n",
"\n",
"with tf.Session(\"grpc://127.0.0.1:2221\", config=config) as sess:\n",
" v1.initializer.run()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Readers"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"No more files to read\n",
"[array([[ 7., 8.],\n",
" [ 4., 5.]], dtype=float32), array([0, 1], dtype=int32)]\n",
"[array([[ 1., 1.]], dtype=float32), array([0], dtype=int32)]\n",
"No more training instances\n"
]
}
],
"source": [
"tf.reset_default_graph()\n",
"\n",
"test_csv = open(\"my_test.csv\", \"w\")\n",
"test_csv.write(\"x1, x2 , target\\n\")\n",
"test_csv.write(\"1., , 0\\n\")\n",
"test_csv.write(\"4., 5. , 1\\n\")\n",
"test_csv.write(\"7., 8. , 0\\n\")\n",
"test_csv.close()\n",
"\n",
"filename_queue = tf.FIFOQueue(capacity=10, dtypes=[tf.string], shapes=[()])\n",
"filename = tf.placeholder(tf.string)\n",
"enqueue_filename = filename_queue.enqueue([filename])\n",
"close_filename_queue = filename_queue.close()\n",
"\n",
"reader = tf.TextLineReader(skip_header_lines=1)\n",
"key, value = reader.read(filename_queue)\n",
"\n",
"x1, x2, target = tf.decode_csv(value, record_defaults=[[-1.], [-1.], [-1]])\n",
"features = tf.pack([x1, x2])\n",
"\n",
"instance_queue = tf.RandomShuffleQueue(\n",
" capacity=10, min_after_dequeue=2,\n",
" dtypes=[tf.float32, tf.int32], shapes=[[2],[]],\n",
" name=\"instance_q\", shared_name=\"shared_instance_q\")\n",
"enqueue_instance = instance_queue.enqueue([features, target])\n",
"close_instance_queue = instance_queue.close()\n",
"\n",
"minibatch_instances, minibatch_targets = instance_queue.dequeue_up_to(2)\n",
"\n",
"with tf.Session() as sess:\n",
" sess.run(enqueue_filename, feed_dict={filename: \"my_test.csv\"})\n",
" sess.run(close_filename_queue)\n",
" try:\n",
" while True:\n",
" sess.run(enqueue_instance)\n",
" except tf.errors.OutOfRangeError as ex:\n",
" print(\"No more files to read\")\n",
" sess.run(close_instance_queue)\n",
" try:\n",
" while True:\n",
" print(sess.run([minibatch_instances, minibatch_targets]))\n",
" except tf.errors.OutOfRangeError as ex:\n",
" print(\"No more training instances\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#coord = tf.train.Coordinator()\n",
"#threads = tf.train.start_queue_runners(coord=coord)\n",
"#filename_queue = tf.train.string_input_producer([\"test.csv\"])\n",
"#coord.request_stop()\n",
"#coord.join(threads)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Queue runners and coordinators"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[array([[ 7., 8.],\n",
" [ 4., 5.]], dtype=float32), array([0, 1], dtype=int32)]\n",
"[array([[ 1., 1.]], dtype=float32), array([0], dtype=int32)]\n",
"No more training instances\n"
]
}
],
"source": [
"tf.reset_default_graph()\n",
"\n",
"filename_queue = tf.FIFOQueue(capacity=10, dtypes=[tf.string], shapes=[()])\n",
"filename = tf.placeholder(tf.string)\n",
"enqueue_filename = filename_queue.enqueue([filename])\n",
"close_filename_queue = filename_queue.close()\n",
"\n",
"reader = tf.TextLineReader(skip_header_lines=1)\n",
"key, value = reader.read(filename_queue)\n",
"\n",
"x1, x2, target = tf.decode_csv(value, record_defaults=[[-1.], [-1.], [-1]])\n",
"features = tf.pack([x1, x2])\n",
"\n",
"instance_queue = tf.RandomShuffleQueue(\n",
" capacity=10, min_after_dequeue=2,\n",
" dtypes=[tf.float32, tf.int32], shapes=[[2],[]],\n",
" name=\"instance_q\", shared_name=\"shared_instance_q\")\n",
"enqueue_instance = instance_queue.enqueue([features, target])\n",
"close_instance_queue = instance_queue.close()\n",
"\n",
"minibatch_instances, minibatch_targets = instance_queue.dequeue_up_to(2)\n",
"\n",
"n_threads = 5\n",
"queue_runner = tf.train.QueueRunner(instance_queue, [enqueue_instance] * n_threads)\n",
"coord = tf.train.Coordinator()\n",
"\n",
"with tf.Session() as sess:\n",
" sess.run(enqueue_filename, feed_dict={filename: \"my_test.csv\"})\n",
" sess.run(close_filename_queue)\n",
" enqueue_threads = queue_runner.create_threads(sess, coord=coord, start=True)\n",
" try:\n",
" while True:\n",
" print(sess.run([minibatch_instances, minibatch_targets]))\n",
" except tf.errors.OutOfRangeError as ex:\n",
" print(\"No more training instances\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[array([[ 7., 8.],\n",
" [ 4., 5.]], dtype=float32), array([0, 1], dtype=int32)]\n",
"[array([[ 1., 1.]], dtype=float32), array([0], dtype=int32)]\n",
"No more training instances\n"
]
}
],
"source": [
"tf.reset_default_graph()\n",
"\n",
"def read_and_push_instance(filename_queue, instance_queue):\n",
" reader = tf.TextLineReader(skip_header_lines=1)\n",
" key, value = reader.read(filename_queue)\n",
" x1, x2, target = tf.decode_csv(value, record_defaults=[[-1.], [-1.], [-1]])\n",
" features = tf.pack([x1, x2])\n",
" enqueue_instance = instance_queue.enqueue([features, target])\n",
" return enqueue_instance\n",
"\n",
"filename_queue = tf.FIFOQueue(capacity=10, dtypes=[tf.string], shapes=[()])\n",
"filename = tf.placeholder(tf.string)\n",
"enqueue_filename = filename_queue.enqueue([filename])\n",
"close_filename_queue = filename_queue.close()\n",
"\n",
"instance_queue = tf.RandomShuffleQueue(\n",
" capacity=10, min_after_dequeue=2,\n",
" dtypes=[tf.float32, tf.int32], shapes=[[2],[]],\n",
" name=\"instance_q\", shared_name=\"shared_instance_q\")\n",
"\n",
"minibatch_instances, minibatch_targets = instance_queue.dequeue_up_to(2)\n",
"\n",
"read_and_enqueue_ops = [read_and_push_instance(filename_queue, instance_queue) for i in range(5)]\n",
"queue_runner = tf.train.QueueRunner(instance_queue, read_and_enqueue_ops)\n",
"\n",
"with tf.Session() as sess:\n",
" sess.run(enqueue_filename, feed_dict={filename: \"my_test.csv\"})\n",
" sess.run(close_filename_queue)\n",
" coord = tf.train.Coordinator()\n",
" enqueue_threads = queue_runner.create_threads(sess, coord=coord, start=True)\n",
" try:\n",
" while True:\n",
" print(sess.run([minibatch_instances, minibatch_targets]))\n",
" except tf.errors.OutOfRangeError as ex:\n",
" print(\"No more training instances\")\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Setting a timeout"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2.0\n",
"6.0\n",
"3.0\n",
"4.0\n",
"Timed out while dequeuing\n"
]
}
],
"source": [
"tf.reset_default_graph()\n",
"\n",
"q = tf.FIFOQueue(capacity=10, dtypes=[tf.float32], shapes=[()])\n",
"v = tf.placeholder(tf.float32)\n",
"enqueue = q.enqueue([v])\n",
"dequeue = q.dequeue()\n",
"output = dequeue + 1\n",
"\n",
"config = tf.ConfigProto()\n",
"config.operation_timeout_in_ms = 1000\n",
"\n",
"with tf.Session(config=config) as sess:\n",
" sess.run(enqueue, feed_dict={v: 1.0})\n",
" sess.run(enqueue, feed_dict={v: 2.0})\n",
" sess.run(enqueue, feed_dict={v: 3.0})\n",
" print(sess.run(output))\n",
" print(sess.run(output, feed_dict={dequeue: 5}))\n",
" print(sess.run(output))\n",
" print(sess.run(output))\n",
" try:\n",
" print(sess.run(output))\n",
" except tf.errors.DeadlineExceededError as ex:\n",
" print(\"Timed out while dequeuing\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"# Exercise solutions"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Coming soon**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.1"
},
"nav_menu": {},
"toc": {
"navigate_menu": true,
"number_sections": true,
"sideBar": true,
"threshold": 6,
"toc_cell": false,
"toc_section_display": "block",
"toc_window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 0
}

848
13_convolutional_neural_networks.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

2010
14_recurrent_neural_networks.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

146
classification.ipynb
View File

File diff suppressed because one or more lines are too long

1
images/ann/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/autoencoders/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/cnn/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

BIN
images/cnn/test_image.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 178 KiB

1
images/decision_trees/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/deep/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/dim_reduction/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/distributed/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/ensembles/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/rl/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/rnn/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/svm/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

1
images/tensorflow/README Normal file
View File

@@ -0,0 +1 @@
Images generated by the notebooks

45
index.ipynb
View File

@@ -16,19 +16,29 @@
"\n",
"### To run the examples\n",
"* **Jupyter** – These notebooks are based on Jupyter. If you just plan to read without running any code, there's really nothing more to know, just keep reading! But if you want to experiment with the code examples you need to:\n",
" * open these notebooks in Jupyter. If you clicked on the \"launch binder\" button in github or followed the Installation instructions, then you are good to go. If not you will need to go back to the project [home page](https://github.com/ageron/ml-notebooks/) and click on \"launch binder\" or follow the installation instructions.\n",
" * open these notebooks in Jupyter. If you clicked on the \"launch binder\" button in github or followed the Installation instructions, then you are good to go. If not you will need to go back to the project [home page](https://github.com/ageron/handson-ml/) and click on \"launch binder\" or follow the installation instructions.\n",
" * learn how to use Jupyter. Start the User Interface Tour from the Help menu.\n",
"\n",
"### To activate extensions\n",
"* If this is an interactive session (see above), you may want to turn on a few Jupyter extensions by going to the [Extension Configuration](../nbextensions/) page. In particular the \"*table of contents (2)*\" extension is quite useful.\n",
"* If this is an interactive session (see above), you may want to turn on a few Jupyter extensions by going to the [Extension Configuration](../nbextensions/) page. In particular the \"*Table of Contents (2)*\" extension is quite useful.\n",
"\n",
"## Chapters\n",
"1. [Fundamentals](fundamentals.ipynb)\n",
"2. [End-to-end project](end_to_end_project.ipynb)\n",
"3. [Classification](classification.ipynb)\n",
"4. [Training Linear Models](training_linear_models.ipynb)\n",
"\n",
"More explanations and chapters coming soon.\n",
"## Notebooks\n",
"1. [The Machine Learning landscape](01_the_machine_learning_landscape.ipynb)\n",
"2. [End-to-end Machine Learning project](02_end_to_end_machine_learning_project.ipynb)\n",
"3. [Classification](03_classification.ipynb)\n",
"4. [Training Linear Models](04_training_linear_models.ipynb)\n",
"5. [Support Vector Machines](05_support_vector_machines.ipynb)\n",
"6. [Decision Trees](06_decision_trees.ipynb)\n",
"7. [Ensemble Learning and Random Forests](07_ensemble_learning_and_random_forests.ipynb)\n",
"8. [Dimensionality Reduction](08_dimensionality_reduction.ipynb)\n",
"9. [Up and running with TensorFlow](09_up_and_running_with_tensorflow.ipynb)\n",
"10. [Introduction to Artificial Neural Networks](10_introduction_to_artificial_neural_networks.ipynb)\n",
"11. [Deep Learning](11_deep_learning.ipynb)\n",
"12. [Distributed TensorFlow](12_distributed_tensorflow.ipynb)\n",
"13. [Convolutional Neural Networks](13_convolutional_neural_networks.ipynb)\n",
"14. [Recurrent Neural Networks](14_recurrent_neural_networks.ipynb)\n",
"15. Autoencoders (coming soon)\n",
"16. Reinforcement Learning (coming soon)\n",
"\n",
"## Scientific Python tutorials\n",
"* [NumPy](tools_numpy.ipynb)\n",
@@ -39,6 +49,15 @@
"* [Linear Algebra](math_linear_algebra.ipynb)\n",
"* Calculus (coming soon)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
@@ -59,10 +78,14 @@
"pygments_lexer": "ipython2",
"version": "2.7.11"
},
"nav_menu": {},
"toc": {
"navigate_menu": true,
"number_sections": true,
"sideBar": true,
"threshold": 6,
"toc_cell": false,
"toc_number_sections": true,
"toc_threshold": 6,
"toc_section_display": "block",
"toc_window_display": false
}
},

10
nets/inception_v3.py
View File

@@ -94,7 +94,9 @@ def inception_v3_base(inputs,
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with tf.variable_scope(scope, 'InceptionV3', [inputs]):
#Backported to 0.10.0
#with tf.variable_scope(scope, 'InceptionV3', [inputs]):
with tf.variable_scope(scope or 'InceptionV3'):
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='VALID'):
# 299 x 299 x 3
@@ -470,8 +472,10 @@ def inception_v3(inputs,
raise ValueError('depth_multiplier is not greater than zero.')
depth = lambda d: max(int(d * depth_multiplier), min_depth)
with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes],
reuse=reuse) as scope:
#Backported to 0.10.0
#with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes],
# reuse=reuse) as scope:
with tf.variable_scope(scope or 'InceptionV3', reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v3_base(