can you help me to solve this error,thank you!!!!

[jiahaoMeng]

runfile('/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master/train.py', wdir='/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master')
Reloaded modules: models, util, util.data, util.util
Traceback (most recent call last):

File "", line 1, in
runfile('/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master/train.py', wdir='/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master')

File "/home/meng/anaconda3/lib/python3.6/site-packages/spyder/utils/site/sitecustomize.py", line 710, in runfile
execfile(filename, namespace)

File "/home/meng/anaconda3/lib/python3.6/site-packages/spyder/utils/site/sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master/train.py", line 422, in
is_binary=params.is_a_binary)

File "/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master/models.py", line 235, in g_vae
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])

File "/home/meng/anaconda3/lib/python3.6/site-packages/Keras-1.2.2-py3.6.egg/keras/engine/topology.py", line 572, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)

File "/home/meng/anaconda3/lib/python3.6/site-packages/Keras-1.2.2-py3.6.egg/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)

File "/home/meng/anaconda3/lib/python3.6/site-packages/Keras-1.2.2-py3.6.egg/keras/engine/topology.py", line 172, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors, mask=input_masks))

File "/home/meng/anaconda3/lib/python3.6/site-packages/Keras-1.2.2-py3.6.egg/keras/layers/core.py", line 641, in call
return self.function(x, **arguments)

File "/media/meng/C disk/mjh/gan/end to end /code/adversarial_retinal_synthesis-master/models.py", line 232, in sampling
mean=0., std=1.)

File "/home/meng/anaconda3/lib/python3.6/site-packages/Keras-1.2.2-py3.6.egg/keras/backend/tensorflow_backend.py", line 2935, in random_normal
dtype=dtype, seed=seed)

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 71, in random_normal
shape_tensor = _ShapeTensor(shape)

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 42, in _ShapeTensor
return ops.convert_to_tensor(shape, dtype=dtype, name="shape")

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 836, in convert_to_tensor
as_ref=False)

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 926, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 229, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 208, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))

File "/home/meng/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 472, in make_tensor_proto
"supported type." % (type(values), values))

TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (Dimension(None), 16). Consider casting elements to a supported type.

[costapt]

It's hard to say what is the problem.
Are you sure you are using the th dim ordering?

[jiahaoMeng]

I've added this sentence. from keras import backend as K K.set_image_dim_ordering('th') , when I run train.py.
ipdb> vae = m.g_vae(params.a_ch, params.a_ch, params.nfatoa, params.latent_dim,
is_binary=params.is_a_binary)
*** TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (Dimension(None), 16). Consider casting elements to a supported type.

[diazandr3s]

Hi,

After adding the sentence K.set_image_dim_ordering('th'), I solved that error by changing line 231 in the models.py file. This way,

batch_size = K.shape(z_mean)[0]
epsilon = K.random_normal(shape=(batch_size, latent_dim), mean=0., std=1.)

However, I am getting another error, not sure why.

**Exception in thread Thread-2:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/usr/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/engine/training.py", line 429, in data_generator_task
generator_output = next(self._generator)
File "train.py", line 75, in discriminator_generator
b_fake = g.predict(a_fake)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/engine/training.py", line 1269, in predict
self._make_predict_function()
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/engine/training.py", line 798, in _make_predict_function
**kwargs)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1961, in function
return Function(inputs, outputs, updates=updates)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1919, in init
with tf.control_dependencies(self.outputs):
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 5027, in control_dependencies
return get_default_graph().control_dependencies(control_inputs)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 4631, in control_dependencies
c = self.as_graph_element(c)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3590, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3669, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("Tanh_2:0", shape=(?, 3, 256, 256), dtype=float32) is not an element of this graph.

Exception KeyError: KeyError(<weakref at 0x7f3ff4fa7f70; to 'tqdm' at 0x7f3ff4d53710>,) in <bound method tqdm.del of 0%| | 0/100 [00:00<?, ?it/s]> ignored
Traceback (most recent call last):
File "train.py", line 456, in
HERE WE ALRIGHT
POSSIBLE ERROR. BEFORE
train(models, it_train, it_val, params)
File "train.py", line 338, in train
train_iteration(models, generators, losses, params)
File "train.py", line 269, in train_iteration
dhist = train_discriminator(d, d_gen, batch_size=params.batch_size)
File "train.py", line 101, in train_discriminator
return d.fit_generator(it, samples_per_epoch=batch_size*2, nb_epoch=1, verbose=False)
File "/home/cvblab03/Documents/GANexperiment/vess2ret/vess2retEnv/local/lib/python2.7/site-packages/keras/engine/training.py", line 1532, in fit_generator
str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None**

I think is something related to the g_unet architecture. But I am not sure :(

[diazandr3s]

I proposed a solution for these issues. Please check the Pull request @costapt @jiahaoMeng

[jiahaoMeng]

@diazandr3s
Thank you very much for your help, but when I did exactly what you did, I encountered such a mistake and I hope to get your help, thanks again.
runfile('/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py', wdir='/media/meng/My Passport/adversarial_retinal_synthesis-master')
Reloaded modules: util.util, util, models, util.data
0%| | 0/100 [00:00<?, ?it/s]Exception in thread Thread-15:
Traceback (most recent call last):
File "/home/meng/.conda/envs/python27/lib/python2.7/threading.py", line 801, in __bootstrap_inner
self.run()
File "/home/meng/.conda/envs/python27/lib/python2.7/threading.py", line 754, in run
self.__target(*self.__args, **self.__kwargs)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.py", line 429, in data_generator_task
generator_output = next(self._generator)
File "/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py", line 113, in code_discriminator_generator
z_fake = encoder.predict(a)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.py", line 1269, in predict
self._make_predict_function()
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.py", line 798, in _make_predict_function
**kwargs)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 1961, in function
return Function(inputs, outputs, updates=updates)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 1919, in init
with tf.control_dependencies(self.outputs):
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 4604, in control_dependencies
return get_default_graph().control_dependencies(control_inputs)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 4310, in control_dependencies
c = self.as_graph_element(c)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3323, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3402, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("add_1153:0", shape=(?, 16), dtype=float32) is not an element of this graph.

Traceback (most recent call last):

File "", line 1, in
runfile('/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py', wdir='/media/meng/My Passport/adversarial_retinal_synthesis-master')

File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 705, in runfile
execfile(filename, namespace)

File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
builtins.execfile(filename, *where)

File "/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py", line 474, in
train(models, it_train, it_val, params)

File "/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py", line 351, in train
train_iteration(models, generators, losses, params)

File "/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py", line 283, in train_iteration
cdhist = train_discriminator(code_d, code_d_gen, samples_per_batch=params.batch_size)

File "/media/meng/My Passport/adversarial_retinal_synthesis-master/train.py", line 106, in train_discriminator
return d.fit_generator(it, samples_per_epoch=samples_per_batch*2, nb_epoch=1, verbose=False)

File "/home/meng/.conda/envs/python27/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.py", line 1532, in fit_generator
str(generator_output))

ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

[diazandr3s]

@jiahaoMeng
You are right, I got the same error before. I forgot to add the complete solution. Please check the newly added piece of code. Let me know if it works.

[jiahaoMeng]

@diazandr3s
Thank you again for your help！When I modified it according to the changes you made, I encountered the first question again. So I modified the following sentence, the code can run.
if K.backend == 'tensorflow':
batch_size = K.shape(z_mean)[0]
else:
batch_size = z_mean.shape[0]
replaced:
batch_size = K.shape(z_mean)[0]

[jiahaoMeng]

@diazandr3s
Have you ever run the test code? I encountered this problem when I run the test code.
Traceback (most recent call last):
File "test1.py", line 216, in
save_generated_images(sampler, params.N, params)
File "test1.py", line 113, in save_generated_images
expt_dir = join_and_create_dir(params.results_dir, params.expt_name)
File "test1.py", line 33, in join_and_create_dir
path = os.path.join(*paths)
File "/usr/lib/python2.7/posixpath.py", line 68, in join
if b.startswith('/'):
AttributeError: 'NoneType' object has no attribute 'startswith'

And the pictures I trained are not very good. I don't know what the problem is.

[diazandr3s]

Hi @jiahaoMeng

Regarding the image quality, @costapt could tell us more.
You can modify the code to see the vessel masks as binary images and not as grey-scale.

[costapt]

Thank you for your help @diazandr3s !

I am not sure what might be the issue with the test script. By reading the error message it seems like params.results_dir and/or params.expt_name might be incorrectly set. Can you confirm their values?

About the results quality, it usually takes a long time to fully train the model, it may be the case that it still did not converge. Can you send the train and val losses?

[jiahaoMeng]

@costapt Thank you for your help!

[costapt]

It looks like the model still needs more training, you can see that the Pix2Pix loss was starting to decrease.

I remember that I have seen images like those during training, so I believe that the images will get sharper with more time.

[FFjiahao]

@jiahaoMeng I recently reproduced the code of this paper and found that the problems I encountered were the same as yours。How does the code of your experiment work in the end? Did you modify the code？Thank you very much for your reply.