Getting Value error while executing this code.

[Rajendrasinh-AI]

Hello i'm getting following error while executing this code.

all the input array dimensions except for the concatenation axis must match exactly
Apply node that caused the error: Join(TensorConstant{0}, /variable, /variable, /placeholder)
Toposort index: 8

Inputs types: [TensorType(int8, scalar), TensorType(float32, 4D), TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(), (1, 400, 400, 3), (1, 400, 400, 3), (1, 3, 400, 400)]
Inputs strides: [(), (1920000, 4800, 12, 4), (1920000, 4800, 12, 4), (1920000, 640000, 1600, 4)]
Inputs values: [array(0, dtype=int8), 'not shown', 'not shown', 'not shown']
Outputs clients: [[InplaceDimShuffle{0,3,1,2}(Join.0)]]

[faizankshaikh]

The project was build on previous versions of keras and theano, so there may be some unknown issues. I would check it extensively later someday.

Anyways, on which block of code are you getting the error?

[Rajendrasinh-AI]

Hello Following is whole stack trace for error.

error is from following line
x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x.flatten(), fprime=evaluator.grads, maxfun=20)

('Start of iteration', 0)

ValueError Traceback (most recent call last)
in ()
4 start_time = time.time()
5 x, min_val, info = fmin_l_bfgs_b(evaluator.loss, x.flatten(),
----> 6 fprime=evaluator.grads, maxfun=20)
7 print("Current loss value: ", min_val)
8

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/scipy/optimize/lbfgsb.pyc in fmin_l_bfgs_b(func, x0, fprime, args, approx_grad, bounds, m, factr, pgtol, epsilon, iprint, maxfun, maxiter, disp, callback, maxls)
191
192 res = _minimize_lbfgsb(fun, x0, args=args, jac=jac, bounds=bounds,
--> 193 **opts)
194 d = {'grad': res['jac'],
195 'task': res['message'],

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/scipy/optimize/lbfgsb.pyc in _minimize_lbfgsb(fun, x0, args, jac, bounds, disp, maxcor, ftol, gtol, eps, maxfun, maxiter, iprint, callback, maxls, **unknown_options)
326 # until the completion of the current minimization iteration.
327 # Overwrite f and g:
--> 328 f, g = func_and_grad(x)
329 elif task_str.startswith(b'NEW_X'):
330 # new iteration

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/scipy/optimize/lbfgsb.pyc in func_and_grad(x)
276 else:
277 def func_and_grad(x):
--> 278 f = fun(x, *args)
279 g = jac(x, *args)
280 return f, g

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/scipy/optimize/optimize.pyc in function_wrapper(*wrapper_args)
290 def function_wrapper(wrapper_args):
291 ncalls[0] += 1
--> 292 return function((wrapper_args + args))
293
294 return ncalls, function_wrapper

in loss(self, x)
7 def loss(self, x):
8 assert self.loss_value is None
----> 9 loss_value, grad_values = eval_loss_and_grads(x)
10 self.loss_value = loss_value
11 self.grad_values = grad_values

in eval_loss_and_grads(x)
2 def eval_loss_and_grads(x):
3 x = x.reshape((1, 3, img_nrows, img_ncols))
----> 4 outs = f_outputs([x])
5 loss_value = outs[0]
6 if len(outs[1:]) == 1:

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/keras/backend/theano_backend.pyc in call(self, inputs)
1120 def call(self, inputs):
1121 assert isinstance(inputs, (list, tuple))
-> 1122 return self.function(*inputs)
1123
1124

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/theano/compile/function_module.pyc in call(self, *args, **kwargs)
896 node=self.fn.nodes[self.fn.position_of_error],
897 thunk=thunk,
--> 898 storage_map=getattr(self.fn, 'storage_map', None))
899 else:
900 # old-style linkers raise their own exceptions

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/theano/gof/link.pyc in raise_with_op(node, thunk, exc_info, storage_map)
323 # extra long error message in that case.
324 pass
--> 325 reraise(exc_type, exc_value, exc_trace)
326
327

/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/theano/compile/function_module.pyc in call(self, *args, **kwargs)
882 try:
883 outputs =
--> 884 self.fn() if output_subset is None else
885 self.fn(output_subset=output_subset)
886 except Exception:

ValueError: all the input array dimensions except for the concatenation axis must match exactly
Apply node that caused the error: Join(TensorConstant{0}, /variable, /variable, /placeholder)
Toposort index: 8
Inputs types: [TensorType(int8, scalar), TensorType(float32, 4D), TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(), (1, 400, 400, 3), (1, 400, 400, 3), (1, 3, 400, 400)]
Inputs strides: [(), (1920000, 4800, 12, 4), (1920000, 4800, 12, 4), (1920000, 640000, 1600, 4)]
Inputs values: [array(0, dtype=int8), 'not shown', 'not shown', 'not shown']
Outputs clients: [[InplaceDimShuffle{0,3,1,2}(Join.0)]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/ipykernel/kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/ipykernel/zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
if self.run_code(code, result):
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/IPython/core/interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 6, in
input_tensor = K.concatenate((base_image, ref_image, final_image), axis=0)
File "/Users/AI/anaconda/envs/pyAI/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 735, in concatenate
return T.concatenate([to_dense(x) for x in tensors], axis=axis)

HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.

[faizankshaikh]

Well we would have to dig in deeper to get the solution. Could you debug the code and check where the error is? You might find these helpful

• http://deeplearning.net/software/theano/tutorial/debug_faq.html
• https://wookayin.github.io/tensorflow-talk-debugging/#1

[Rajendrasinh-AI]

Hello tried some solutions, updated code to match the dimensions but no luck.!

can you please tell me which version is working fine so that i can at least test this code with that version.

[faizankshaikh]

Try this, use tensorflow instead of theano.

Also, can you comment on what is the shape of your input and type (eg. jpeg , png etc)?

[preetparikh8]

Hello @Rajendrasinh-AI Did you find any solution to the issue? I'm having the same issue.