Train with own dataset

[RaminAbbaszadi]

Dear Titu,
Thank you for sharing your source code. I try to train your code with my own dataset which include images with size 128*64. But I get a same error in most of train model in test.py.
error:
ValueError:
Using TensorFlow backend.
Training model : ImageSuperResolutionModel
2018-02-15 09:17:35.000003: 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.
2018-02-15 09:17:35.000047: 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.
2018-02-15 09:17:35.000061: 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.
2018-02-15 09:17:35.214561: I tensorflow/core/common_runtime/gpu/gpu_device.cc:887] Found device 0 with properties:
name: GeForce GTX TITAN X
major: 5 minor: 2 memoryClockRate (GHz) 1.076
pciBusID 0000:19:00.0
Total memory: 11.92GiB
Free memory: 3.33GiB
2018-02-15 09:17:35.214608: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0
2018-02-15 09:17:35.214622: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0: Y
2018-02-15 09:17:35.214644: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX TITAN X, pci bus id: 0000:19:00.0)
Epoch 1/250
Found 51744 images.
Traceback (most recent call last):
File "tests.py", line 47, in
sr.fit(nb_epochs=250)
File "/mnt/home/ramin/srcnn-org-codes/org/Image-Super-Resolution/models.py", line 516, in fit
return super(ImageSuperResolutionModel, self).fit(batch_size, nb_epochs, save_history, history_fn)
File "/mnt/home/ramin/srcnn-org-codes/org/Image-Super-Resolution/models.py", line 122, in fit
validation_steps=val_count // batch_size + 1)
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/keras/legacy/interfaces.py", line 87, in wrapper
return func(*args, **kwargs)
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/keras/engine/training.py", line 2115, in fit_generator
generator_output = next(output_generator)
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/keras/utils/data_utils.py", line 735, in get
six.reraise(value.class, value, value.traceback)
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/six.py", line 693, in reraise
raise value
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/keras/utils/data_utils.py", line 635, in data_generator_task
generator_output = next(self._generator)
File "/mnt/home/ramin/srcnn-org-codes/org/Image-Super-Resolution/img_utils.py", line 303, in image_generator
batch_x[i] = img
ValueError: could not broadcast input array from shape (16,16,3) into shape (64,64,3)
Exception ignored in: <bound method Session.del of <tensorflow.python.client.session.Session object at 0x7fe3e2aa9d68>>
Traceback (most recent call last):
File "/mnt/home/ramin/Image-Super-Resolution/superRe/lib/python3.4/site-packages/tensorflow/python/client/session.py", line 587, in del
TypeError: 'NoneType' object is not callable

I am very appreciate from you, if you help me about it.
Thank you,
Ramin