activations = activation_model.predict(img_arr) giving error

[KVK012]

Hello,

I am new to TF and I am using TF version 1.13.1

I am using jupyter notebook and I got stuck at following line.
activations = activation_model.predict(img_arr)

When I execute it then it is giving an error as shown below.
`InvalidArgumentError Traceback (most recent call last)
in
----> 1 activations = activation_model.predict(img_arr)

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\keras\engine\training.py in predict(self, x, batch_size, verbose, steps)
1167 batch_size=batch_size,
1168 verbose=verbose,
-> 1169 steps=steps)
1170
1171 def train_on_batch(self, x, y,

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\keras\engine\training_arrays.py in predict_loop(model, f, ins, batch_size, verbose, steps)
292 ins_batch[i] = ins_batch[i].toarray()
293
--> 294 batch_outs = f(ins_batch)
295 batch_outs = to_list(batch_outs)
296 if batch_index == 0:

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\keras\backend\tensorflow_backend.py in call(self, inputs)
2713 return self._legacy_call(inputs)
2714
-> 2715 return self._call(inputs)
2716 else:
2717 if py_any(is_tensor(x) for x in inputs):

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\keras\backend\tensorflow_backend.py in _call(self, inputs)
2669 feed_symbols,
2670 symbol_vals,
-> 2671 session)
2672 if self.run_metadata:
2673 fetched = self._callable_fn(*array_vals, run_metadata=self.run_metadata)

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\keras\backend\tensorflow_backend.py in _make_callable(self, feed_arrays, feed_symbols, symbol_vals, session)
2621 callable_opts.run_options.CopyFrom(self.run_options)
2622 # Create callable.
-> 2623 callable_fn = session._make_callable_from_options(callable_opts)
2624 # Cache parameters corresponding to the generated callable, so that
2625 # we can detect future mismatches and refresh the callable.

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\tensorflow\python\client\session.py in _make_callable_from_options(self, callable_options)
1469 """
1470 self._extend_graph()
-> 1471 return BaseSession._Callable(self, callable_options)
1472
1473

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\tensorflow\python\client\session.py in init(self, session, callable_options)
1423 with errors.raise_exception_on_not_ok_status() as status:
1424 self._handle = tf_session.TF_SessionMakeCallable(
-> 1425 session._session, options_ptr, status)
1426 finally:
1427 tf_session.TF_DeleteBuffer(options_ptr)

c:\users\rameshmdamor777.conda\envs\pythongpu\lib\site-packages\tensorflow\python\framework\errors_impl.py in exit(self, type_arg, value_arg, traceback_arg)
526 None, None,
527 compat.as_text(c_api.TF_Message(self.status.status)),
--> 528 c_api.TF_GetCode(self.status.status))
529 # Delete the underlying status object from memory otherwise it stays alive
530 # as there is a reference to status from this from the traceback due to

InvalidArgumentError: input_3:0 is both fed and fetched.
`

Can you please help me on this.

Thanks

[anktplwl91]

Hi @KVK012
I guess you are talking about line 79 here. I have made a mistake the line should be

activations = activation_model.predict(img_tensor)

I'll correct it in code. If this doesn't solve your issue, can you please tell me more details about whats the input shape of your img_tensor and if you are trying to do anything other than what I've done?

[KVK012]

Thanks for the quick response.

No, I am using "model_training.ipynb" from GitHub as it is, I kept image size 299x299 (color image).

ipynb file code portion:
P[14]:
img = image.load_img(test_image, target_size=(299, 299))
img_arr = image.img_to_array(img)
img_arr = np.expand_dims(img_arr, axis=0)
img_arr /= 255.

P[15] (I am stuck here):
activations = activation_model.predict(img_arr)

p[16]:
activations[1].shape

First, I want to see how visualization works so I have reduced epoch to 10 (steps_per_epoch=10). Just wanted to speed up the execution.