jonbruner / generative-adversarial-networks Goto Github PK

Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs

License: MIT License

Jupyter Notebook 67.77% Python 32.23%

tensorflow tensorflow-tutorials tensorflow-models generative-adversarial-network gan

generative-adversarial-networks's Introduction

Introduction to generative adversarial networks

This repository contains code to accompany the O'Reilly tutorial on generative adversarial networks written by Jon Bruner and Adit Deshpande. See the original tutorial to run this code in a pre-built environment on O'Reilly's servers with cell-by-cell guidance, or run these files on your own machine.

There are three versions of our simple GAN model in this repository:

gan-notebook.ipynb is identical to the interactive tutorial, available here so that you can run it on your own machine.
gan-script.py is a straightforward Python script containing code drawn directly from the tutorial, to be run from the command line. Note that it doesn't print anything when it's executed, but it does send regular updates to TensorBoard so that you can track its progress.
gan-script-fast.py is a modest refactoring of gan-script.py that runs slightly faster because more of its computations are contained in the TensorFlow graph.

Requirements and installation

In order to run gan-script.py or gan-script-fast.py, you'll need TensorFlow version 1.0 or later and NumPy. In order to run gan-notebook.ipynb, you'll additionally need Jupyter and matplotlib.

If you've already got TensorFlow on your machine, then you've got NumPy and should be able to run the raw Python scripts.

Installing Anaconda Python and TensorFlow

The easiest way to install TensorFlow as well as NumPy, Jupyter, and matplotlib is to start with the Anaconda Python distribution.

Follow the installation instructions for Anaconda Python. We recommend using Python 3.6.
Follow the platform-specific TensorFlow installation instructions. Be sure to follow the "Installing with Anaconda" process, and create a Conda environment named tensorflow.
If you aren't still inside your Conda TensorFlow environment, enter it by opening your terminal and typing
```
source activate tensorflow
```
Download and unzip this entire repository from GitHub, either interactively, or by entering
```
git clone https://github.com/jonbruner/generative-adversarial-networks.git
```
Use cd to navigate into the top directory of the repo on your machine
Launch Jupyter by entering
```
jupyter notebook
```
and, using your browser, navigate to the URL shown in the terminal output (usually http://localhost:8888/)

generative-adversarial-networks's People

Contributors

Stargazers

Watchers

Forkers

heathervica steccami yuechengli jdc08161063 allensmile chongbingbao wanjinchang little1tow jianweilin joizhang2012 doingodswork37 lgen bigmaye godmoves leihao612 pandamax giserh benjamesbabala prasannanatarajan nikolayvoronchikhin kormilitzin andremtsilva chaoyue0307 cavestruz winner1986 paddymahoney sanguin vskabelkin bityangke lyiuy eivado cantren jahin07 tonydeep shafiahmed thecpshah homada zahorecztibor deeplearningsky johnson0722 eltonlaw zgcgreat libennext wronk kebitmatf alvinli-jp nanfengpo samgregoost alokkshukla cybercoderbot vince-lynch intellifora codeje springle fanshaopu willnewton519 mridulksingh aichitudou sfailsthy anhqphm ent0m0l0gist kevcruzx vivekwisdom novembersun sdwldchl tanganyao mdrahos gchoi arassem dporcher megapotatosan vgoklani jmrinaldi shirand t51645 satnamdatageek jtkostman anhngml shubhampachori12110095 miturchi usefulfwei jbdatascience azmfaridee nincro vivarsin599 cosastro josai frogoscar lss616263 haihongtran superkey79 nephilaw samelltiger aneesht90 littlepai timefunny gjjg1331jggj enggen akasranjan005 raulvigo

generative-adversarial-networks's Issues

What should I do if I want to use this to train my own database

I have a database which consist of low-dose pictures, how should I train them with this algorithm?

Error for running with TensorFlow: ValueError: Variable d_w1/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

Hello, please maybe could you help me? I had a running for running, I tried to figurate how to solve but I could not, I tried also with Python 2, 3.5, 3.6, And Tensorflow 1 and 1.1

The complete Error was:
heather@heather-ThinkPad-P50:~/Downloads/generative-adversarial-networks-master (2)$ python3 gan-script.py
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Traceback (most recent call last):
File "gan-script.py", line 131, in
d_trainer_fake = tf.train.AdamOptimizer(0.0003).minimize(d_loss_fake, var_list=d_vars)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 325, in minimize
name=name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 446, in apply_gradients
self._create_slots([_get_variable_for(v) for v in var_list])
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/adam.py", line 122, in _create_slots
self._zeros_slot(v, "m", self._name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 766, in _zeros_slot
named_slots[_var_key(var)] = slot_creator.create_zeros_slot(var, op_name)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 174, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 146, in create_slot_with_initializer
dtype)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 66, in _create_slot_var
validate_shape=validate_shape)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1049, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 948, in get_variable
use_resource=use_resource, custom_getter=custom_getter)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 356, in get_variable
validate_shape=validate_shape, use_resource=use_resource)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
use_resource=use_resource)
File "/home/heather/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 671, in _get_single_variable
"VarScope?" % name)
ValueError:
Variable d_w1/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

Not able to load pre-trained model

Error Tensor name "g_b1/beta" not found in checkpoint files pretrained-model/pretrained_gan.ckpt when loading pre-trained model, can anyone help?

Python 3.5 TensorFlow 1.2 variable scope related error

ValueError: Variable d_w1/Adam_1/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

at line 128: d_trainer_fake = tf.train.AdamOptimizer(0.0003).minimize(d_loss_fake, var_list=d_vars)

Variable d_w1/Adam_3/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?

error
ValueError: Variable d_w1/Adam_3/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?
trial 1

d_trainer_fake = tf.train.AdamOptimizer(0.0003).minimize(d_loss_fake, var_list=d_vars)
d_trainer_real = tf.train.AdamOptimizer(0.0003).minimize(d_loss_real, var_list=d_vars)

# Train the generator
g_trainer = tf.train.AdamOptimizer(0.0001).minimize(g_loss, var_list=g_vars)

trial 2

with tf.variable_scope(tf.get_variable_scope()):
    d_trainer_real = tf.train.AdamOptimizer(0.0003).minimize(d_loss_real, var_list=d_vars)

    d_trainer_fake = tf.train.AdamOptimizer(0.0003).minimize(d_loss_fake, var_list=d_vars)
    g_trainer = tf.train.AdamOptimizer(0.0001).minimize(g_loss, var_list=g_vars)

Python 3.5.2
tf.version = '1.11.0'

ValueError: Variable d_w1/Adam_5/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?

Help~!!!!

Training Betas and Gammas of the batch normalization

Am I wrong, or in your current implementation you are not updating the betas and the gammas of the batch normalization layers (during of course the training) ?

Bests,
Andrea

why this code only in discriminator, but not in generator?:

why this code only in discriminator, but not in generator?:
with tf.variable_scope(tf.get_variable_scope(), reuse=reuse_variables) as scope: