Hi,

When I clone your repo, download the datasets and run the code, this is the error that I get. The issue comes from the assignment of variable h4 in the discriminator when calling the linear() function.

Any ideas of what the problem might be?

Thanks!

Configuration：tensorflow 0.12.1, python3.4.3 ,ubuntu14.04 I have successfully run python download.py mnist and got the mnist data.but when I ran python download.py celebAt ,there was an error : File "/usr/lib/python3.4/urllib/request.py", line 1182, in do_open h.request(req.get_method(), req.selector, req.data, headers) File "/usr/lib/python3.4/http/client.py", line 1125, in request self._send_request(method, url, body, headers) File "/usr/lib/python3.4/http/client.py", line 1163, in _send_request self.endheaders(body) File "/usr/lib/python3.4/http/client.py", line 1121, in endheaders self._send_output(message_body) File "/usr/lib/python3.4/http/client.py", line 951, in _send_output self.send(msg File "/usr/lib/python3.4/http/client.py", line 886, in send self.connect() File "/usr/lib/python3.4/http/client.py", line 1260, in connect super().connect() File "/usr/lib/python3.4/http/client.py", line 863, in connect self.timeout, self.source_address) File "/usr/lib/python3.4/socket.py", line 512, in create_connection raise err File "/usr/lib/python3.4/socket.py", line 503, in create_connection sock.connect(sa) TimeoutError: [Errno 110] Connection timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "download.py", line 140, in download_celeb_a('./data') File "download.py", line 65, in download_celeb_a filepath = download(url, dirpath) File "download.py", line 28, in download u = urllib.request.urlopen(url) File "/usr/lib/python3.4/urllib/request.py", line 161, in urlopen return opener.open(url, data, timeout) File "/usr/lib/python3.4/urllib/request.py", line 463, in open response = self._open(req, data) File "/usr/lib/python3.4/urllib/request.py", line 481, in _open '_open', req) File "/usr/lib/python3.4/urllib/request.py", line 441, in _call_chain result = func(*args) File "/usr/lib/python3.4/urllib/request.py", line 1225, in https_open context=self._context, check_hostname=self._check_hostname) File "/usr/lib/python3.4/urllib/request.py", line 1184, in do_open raise URLError(err) urllib.error.URLError: <urlopen error [Errno 110] Connection timed out>

anyone has the same error?could someone teach me how to fix it,please?thx a lot!

Hello,

I'm having some difficulties getting the example code to execute. I believe the issue stems from a tensorflow versioning delta. I first tried to train a model on the celebA data after setting up a cpu tensorflow docker container from: https://hub.docker.com/r/tensorflow/tensorflow/

When I run

python main.py --dataset celebA --input_height=108 --is_train --is_crop True

I get the following traceback:

Traceback (most recent call last):
  File "main.py", line 96, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 43, in run
    sys.exit(main(sys.argv[:1] + flags_passthrough))
  File "main.py", line 76, in main
    sample_dir=FLAGS.sample_dir)
  File "/root/git_repos/DCGAN-tensorflow/model.py", line 71, in __init__
    self.build_model()
  File "/root/git_repos/DCGAN-tensorflow/model.py", line 115, in build_model
    logits=self.D_logits, labels=tf.ones_like(self.D)))
TypeError: sigmoid_cross_entropy_with_logits() got an unexpected keyword argument 'labels'

After looking, I found sigmoid_cross_entropy_with_logits here: https://github.com/tensorflow/tensorflow/blob/cb17d1b0e2b581b5da1d9597b7929ba764749d38/tensorflow/python/ops/nn_impl.py#L99 which shows that it does take a labels arg. However, the version under v0.12.1 does not take this arg which I believe is the error I'm receiving above.

Furthermore, if I try to install the specific version of tensorflow branch that you linked to:

pip install git+https://github.com/tensorflow/[email protected]

I get the following traceback:

Collecting git+https://github.com/tensorflow/[email protected]
  Cloning https://github.com/tensorflow/tensorflow.git (to r0.12) to /tmp/pip-oKC0L1-build
    Complete output from command python setup.py egg_info:
    Traceback (most recent call last):
      File "<string>", line 1, in <module>
    IOError: [Errno 2] No such file or directory: '/tmp/pip-oKC0L1-build/setup.py'

    ----------------------------------------
Command "python setup.py egg_info" failed with error code 1 in /tmp/pip-oKC0L1-build/

Any suggestions on how to get this up and running?

Thanks, Scott

{'batch_size': 64,
 'beta1': 0.5,
 'checkpoint_dir': 'checkpoint',
 'crop': False,
 'dataset': 'faces',
 'epoch': 25,
 'input_fname_pattern': '*.jpg',
 'input_height': 96,
 'input_width': 96,
 'learning_rate': 0.0002,
 'output_height': 64,
 'output_width': 64,
 'sample_dir': 'samples',
 'train': True,
 'train_size': inf,
 'visualize': False}
2017-05-02 18:44:49.160149: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-02 18:44:49.160180: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-02 18:44:49.160190: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-05-02 18:44:49.160197: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-05-02 18:44:49.160204: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Traceback (most recent call last):
  File "main.py", line 97, in <module>
    tf.app.run()
  File "/usr/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "main.py", line 75, in main
    sample_dir=FLAGS.sample_dir)
  File "/opt/DCGAN-tensorflow/model.py", line 82, in __init__
    self.build_model()
  File "/opt/DCGAN-tensorflow/model.py", line 118, in build_model
    self.D_, self.D_logits_ = self.discriminator(self.G, reuse=True)
  File "/opt/DCGAN-tensorflow/model.py", line 332, in discriminator
    h4 = linear(tf.reshape(h3, [self.batch_size, -1]), 1, 'd_h3_lin')
  File "/opt/DCGAN-tensorflow/ops.py", line 98, in linear
    tf.random_normal_initializer(stddev=stddev))
  File "/usr/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 "/usr/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 "/usr/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 "/usr/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
    use_resource=use_resource)
  File "/usr/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 658, in _get_single_variable
    found_var.get_shape()))
ValueError: Trying to share variable discriminator/d_h3_lin/Matrix, but specified shape (8192, 1) and found shape (18432, 1).

My commond is

python main.py --dataset faces --input_height=96 --output_height=64 --train

my data file size is 96*96,i'm try many time but always this error. can you help me?

run code :

python main.py --dataset mnist --input_height=28 --output_height=28 --c_dim=1 --is_train 

TypeError: Expected int32, got list containing Tensors of type '_Message' instead.

I have been troubleshooting this for a few days now and I think it's about time to ask. I have tried importing a couple of datasets that I reshaped with PIL to 96x96(RGB).

When I use one of the datasets and specify the input_height and output_height flags i get this error:

....DCGAN-tensorflow-master/utils.py", line 104, in transform im = Image.fromarray(image[j:j+crop_h, i:i+crop_w]) NameError: name 'j' is not defined

When I specify the --crop flag I get this:

....DCGAN-tensorflow-master/utils.py", line 94, in center_crop im = Image.fromarray(x[j:j+crop_h, i:i+crop_w]) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/PIL/Image.py", line 2517, in fromarray raise TypeError("Cannot handle this data type") TypeError: Cannot handle this data type

With all this being said, I think it is an issue with my images and the crop function. I have used the mnist dataset and it works fine.

For reference on what my images are, I have attached two. If you have any advice on what I can change to fix this issue I would really appreciate it.

I started training with: python main.py --input_height 256 --input_width 256 --output_height 64 --output_width 64 --dataset test1 --crop --train --epoch 300 --input_fname_pattern "*.jpg" I tried to generate test images with: python main.py --dataset test1 --input_height 256 --input_width 256 --output_height 64 --output_width 64 --crop However, no test or feedback was generated.

Hi! I managed to train the networks with a custom dataset which contains over 50k samples, and the results are fantastic.

Then I tried to train another much smaller dataset with 468 images. I thought maybe it'd help to use a smaller batch_size rather than 64 so that I would get more iterations. I changed mod(counter, 100) == 1 to mod(counter, 5) == 1 because I wanted to see more intermediate results. But I got one pic error!... during training. Here's the script I use:

python main.py --dataset faces --input_height 96 --output_height 48 --c_dim 3 --batch_size 20 --train_size 468 --is_train True --is_crop True --visualize True --epoch 10

With commenting out the try and except block around line 302-311 to show the exact error messages, I trained again and got the following error:

ValueError: Cannot feed value of shape (64, 48, 48, 3) for Tensor u'real_images: 0', which has shape '(20, 48, 48, 3)'

It seems that even with keyword batch_size 20 fed, somewhere in the networks somehow still assumes that batch_size is 64, which causes a value error.

I haven't further investigated how to resolve this issue, and hope that someone more familiar with the codes could point out for me where to look. Thanks!

Getting the following error during run:

Traceback (most recent call last):
  File "main.py", line 96, in <module>
    tf.app.run()
  File "....../tensorflow/python/platform/app.py", line 44, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "main.py", line 93, in main
    visualize(sess, dcgan, FLAGS, OPTION)
  File "...../DCGAN-tensorflow/utils.py", line 174, in visualize
    save_images(samples, [8, 8], './samples/test_arange_%s.png' % (idx))
  File "....../DCGAN-tensorflow/utils.py", line 26, in save_images
    return imsave(inverse_transform(images), size, image_path)
  File "....../DCGAN-tensorflow/utils.py", line 47, in imsave
    return scipy.misc.imsave(path, merge(images, size))
  File "....../DCGAN-tensorflow/utils.py", line 43, in merge
    img[j*h:j*h+h, i*w:i*w+w, :] = image
ValueError: could not broadcast input array from shape (64,64,3) into shape (0,64,3)

I've been trying to download celebA dataset for a couple of weeks now "python download.py celebA", but it always generates the same error: urllib2.HTTPError: HTTP Error 429: Too Many Requests

I finished implementation of training on mnist dataset and it can run now. However, the g_loss is not converging. I need help from other users to improve the program.

[ WARN:[email protected]] global D:\a\opencv-python\opencv-python\opencv\modules\imgcodecs\src\loadsave.cpp (239) cv::findDecoder imread_('./datasets/mobile_data_img'): can't open/read file: check file path/integrity Traceback (most recent call last): File "main.py", line 146, in tf.app.run() File "C:\Users\For36\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.7_qbz5n2kfra8p0\LocalCache\local-packages\Python37\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "main.py", line 114, in main max_to_keep=FLAGS.max_to_keep) File "C:\Users\For36\Desktop\New folder\DCGAN-tensorflow-master\model.py", line 93, in init imreadImg = imread(self.data[0]) File "C:\Users\For36\Desktop\New folder\DCGAN-tensorflow-master\utils.py", line 56, in imread img_rgb = img_bgr[..., ::-1] TypeError: 'NoneType' object is not subscriptable

how do i fix this

I'm trying to build a Attention mechanism for Medical report Generation using Chest X-rays.

train, test = train_test_split(data, test_size = 0.2, random_state = 1, shuffle = True) print(train.shape) - (3056, 4) print(test.shape) - (764, 4)

Function for Extracting the Images:

def image_feature_extraction(image1,image2):

  image_1 = Image.open(image1).convert('RGB')
  image_1 = np.asarray(image_1)

  image_2 = Image.open(image2).convert('RGB')
  image_2 = np.asarray(image_2)

    #normalize the values of the image
  image_1 = image_1/255
  image_2 = image_2/255

    #resize all image into (224,224)
  image_1 = cv2.resize(image_1,(224,224))
  image_2 = cv2.resize(image_2,(224,224))

  image_1 = np.expand_dims(image_1, axis=0)
  image_2 = np.expand_dims(image_2, axis=0)

    #now we have read two image per patient. this is goven to the chexnet model for feature extraction

  image_1_out = final_chexnet_model(image_1)
  image_2_out = final_chexnet_model(image_2)

  #conactenate along the width
  conc = np.concatenate((image_1_out,image_2_out),axis = -1)

  #reshape into(no.of images passed, length*breadth, depth)
  image_feature=tf.reshape(conc,(conc.shape[0], -1, conc.shape[-1]))
  #image_feature = feature_extraction_model([image_1,image_2])

  return image_feature

print(image_2_out)

KerasTensor(type_spec=TensorSpec(shape=(None, 1024), dtype=tf.float32, name=None), name='Chexnet_model/avg_pool/Mean:0', description="created by layer 'Chexnet_model'")

train_features = np.zeros((3056,98,1024))

for row in tqdm(range(train.shape[0])): image_1=train.iloc[row]["image1"] image_2=train.iloc[row]["image2"] train_features[row] = (image_feature_extraction(image_1,image_2))

0%| | 0/3056 [00:00<?, ?it/s]

ValueError Traceback (most recent call last) in 2 image_1=train.iloc[row]["image1"] 3 image_2=train.iloc[row]["image2"] ----> 4 train_features[row] = (image_feature_extraction(image_1,image_2))

ValueError: could not broadcast input array from shape (1,2048) into shape (98,1024)

I have already checked the previous issues, #338 , #380 , #383 , #369 and I still can't create checkpoint under my checkpoint_dir. The checkpoint and the samples folders remain empty.

Does anyone know how to solve this? Any advice would be really appreciated. I'm sharing the command and logs :

command

python main.py --dataset testdir --input_height 96 --input_width 96 --output_height 96 --output_width 96 --batch_size=1 --train --epoch=300 --ckpt_freq=100 --generate_test_images=10

logs

---------
Variables: name (type shape) [size]
---------
generator/g_h0_lin/Matrix:0 (float32_ref 100x18432) [1843200, bytes: 7372800]
generator/g_h0_lin/bias:0 (float32_ref 18432) [18432, bytes: 73728]
generator/g_bn0/beta:0 (float32_ref 512) [512, bytes: 2048]
generator/g_bn0/gamma:0 (float32_ref 512) [512, bytes: 2048]
generator/g_h1/w:0 (float32_ref 5x5x256x512) [3276800, bytes: 13107200]
generator/g_h1/biases:0 (float32_ref 256) [256, bytes: 1024]
generator/g_bn1/beta:0 (float32_ref 256) [256, bytes: 1024]
generator/g_bn1/gamma:0 (float32_ref 256) [256, bytes: 1024]
generator/g_h2/w:0 (float32_ref 5x5x128x256) [819200, bytes: 3276800]
generator/g_h2/biases:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/beta:0 (float32_ref 128) [128, bytes: 512]
generator/g_bn2/gamma:0 (float32_ref 128) [128, bytes: 512]
generator/g_h3/w:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
generator/g_h3/biases:0 (float32_ref 64) [64, bytes: 256]
generator/g_bn3/beta:0 (float32_ref 64) [64, bytes: 256]
generator/g_bn3/gamma:0 (float32_ref 64) [64, bytes: 256]
generator/g_h4/w:0 (float32_ref 5x5x3x64) [4800, bytes: 19200]
generator/g_h4/biases:0 (float32_ref 3) [3, bytes: 12]
discriminator/d_h0_conv/w:0 (float32_ref 5x5x3x64) [4800, bytes: 19200]
discriminator/d_h0_conv/biases:0 (float32_ref 64) [64, bytes: 256]
discriminator/d_h1_conv/w:0 (float32_ref 5x5x64x128) [204800, bytes: 819200]
discriminator/d_h1_conv/biases:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_bn1/beta:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_bn1/gamma:0 (float32_ref 128) [128, bytes: 512]
discriminator/d_h2_conv/w:0 (float32_ref 5x5x128x256) [819200, bytes: 3276800]
discriminator/d_h2_conv/biases:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_bn2/beta:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_bn2/gamma:0 (float32_ref 256) [256, bytes: 1024]
discriminator/d_h3_conv/w:0 (float32_ref 5x5x256x512) [3276800, bytes: 13107200]
discriminator/d_h3_conv/biases:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_bn3/beta:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_bn3/gamma:0 (float32_ref 512) [512, bytes: 2048]
discriminator/d_h4_lin/Matrix:0 (float32_ref 18432x1) [18432, bytes: 73728]
discriminator/d_h4_lin/bias:0 (float32_ref 1) [1, bytes: 4]
Total size of variables: 10496388
Total bytes of variables: 41985552
checkpoint_dir : ./out/20210412.235725 - data - testdir - x96.z100.uniform_signed.y96.b1/checkpoint
sample_dir : ./out/20210412.235725 - data - testdir - x96.z100.uniform_signed.y96.b1/samples
image_path : ./data/testdir/plane.jpg
 [*] Reading checkpoints... ./out/20210412.235725 - data - testdir - x96.z100.uniform_signed.y96.b1/checkpoint
 [*] Failed to find a checkpoint
 [!] Load failed...