search

raghakot / keras-vis

Neural network visualization toolkit for keras
https://raghakot.github.io/keras-vis
MIT License
2.97k stars 664 forks source link

InvalidArgumentError: input_1_2:0 is both fed and fetched. #127

Closed hasibzunair closed 6 years ago

hasibzunair commented 6 years ago

https://github.com/raghakot/keras-vis/blob/master/examples/vggnet/activation_maximization.ipynb

The above code is showing this error when i try to run it

keisen commented 6 years ago

Please let's me know the versions of Keras, Tensorflow and Keras-vis.

hasibzunair commented 6 years ago

Keras 2.2.0 Tensorflow 1.8 Keras-vis 0.4.1

hasibzunair commented 6 years ago

Resloved!

Thanks to Keisen.

Run: pip install git+https://github.com/raghakot/keras-vis.git@137f268b77f40a12d373db17da74dcc9fe759680

decewei commented 5 years ago

The above code has not fixed my issues.

Error info: File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/vis/visualization/saliency.py", line 125, in visualize_saliency return visualize_saliency_with_losses(model.input, losses, seed_input, grad_modifier) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/vis/visualization/saliency.py", line 73, in visualize_saliency_with_losses grads = opt.minimize(seed_input=seed_input, max_iter=1, grad_modifier=grad_modifier, verbose=False)[1] File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/vis/optimizer.py", line 143, in minimize computed_values = self.compute_fn([seed_input, 0]) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2661, in call return self._call(inputs) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2630, in _call session) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2582, in _make_callable callable_fn = session._make_callable_from_options(callable_opts) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1480, in _make_callable_from_options return BaseSession._Callable(self, callable_options) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1441, in init session._session, options_ptr, status) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 519, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: img_tensor_2:0 is both fed and fetched. Exception ignored in: <bound method BaseSession._Callable.del of <tensorflow.python.client.session.BaseSession._Callable object at 0x7fa93b44d588>> Traceback (most recent call last): File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1464, in del self._session._session, self._handle, status) File "/home/celine/.environments/tensorflow_new/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 519, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: No such callable handle: 1225037744

hasibzunair commented 5 years ago

@celinew1221 please check the version of your packages

aakaashjois commented 5 years ago

I am ending up with the same error.

Keras: 2.2.0 Tensorflow: 1.8.0 Keras-vis: 0.4.1

When I install the library as mentioned in this comment, I get the error:

  File "visualization.py", line 15, in <module>
    grads = visualize_saliency(model, layer_idx, filter_indices=5, seed_input=img)
  File "/usr/local/lib/python3.5/dist-packages/vis/visualization/saliency.py", line 125, in visualize_saliency
    return visualize_saliency_with_losses(model.input, losses, seed_input, grad_modifier)
  File "/usr/local/lib/python3.5/dist-packages/vis/visualization/saliency.py", line 73, in visualize_saliency_with_losses
    grads = opt.minimize(seed_input=seed_input, max_iter=1, grad_modifier=grad_modifier, verbose=False)[1]
  File "/usr/local/lib/python3.5/dist-packages/vis/optimizer.py", line 143, in minimize
    computed_values = self.compute_fn([seed_input, 0])
  File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2661, in __call__
    return self._call(inputs)
  File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2630, in _call
    session)
  File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2582, in _make_callable
    callable_fn = session._make_callable_from_options(callable_opts)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1480, in _make_callable_from_options
    return BaseSession._Callable(self, callable_options)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1441, in __init__
    session._session, options_ptr, status)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 519, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: input_1:0 is both fed and fetched.
Exception ignored in: <bound method BaseSession._Callable.__del__ of <tensorflow.python.client.session.BaseSession._Callable object at 0x7fe5a4a31e48>>
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1464, in __del__
    self._session._session, self._handle, status)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 519, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: No such callable handle: 140624093988304
Exception ignored in: <bound method BaseSession.__del__ of <tensorflow.python.client.session.Session object at 0x7fe59f8c4d30>>
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 707, in __del__
TypeError: 'NoneType' object is not callable
keisen commented 5 years ago

Hi, @aakaashjois . This issue was fixed by PR #120 .

Please look a part of your stack trace, computed_values = self.compute_fn([seed_input, 0]) is in optimizer.py, line 143.

  File "/usr/local/lib/python3.5/dist-packages/vis/optimizer.py", line 143, in minimize
    computed_values = self.compute_fn([seed_input, 0])

But, In the currently master branch, It is in optimizer.py, line 152.

https://github.com/raghakot/keras-vis/blob/e019cc43ce6c00b2151941b18dbad63164ad632a/vis/optimizer.py#L151-L152

So It have possible that keras-vis version is old in your environment. Please retry pip install git+https://github.com/raghakot/keras-vis.git .

Thanks.

ale152 commented 4 years ago

If you're having this issue because your input layer is fed directly into the output layer, simply add an intermediate Lambda layer to solve the problem.

This generates the error:

input_stuff = Input(...)
model = Model(input_stuff, output_stuff)

This works perfectly:

input_stuff = Input(...)
dummy_layer = Lambda(lambda x: x)(input_stuff)
model = Model(dummy_layer, output_stuff)
love6tao commented 4 years ago

pip install git+https://github.com/raghakot/keras-vis.git can solve the problem