Can this be problem Specific?

[pGit1]

Does this implementation only work with ImageNet like images or can it be tuned to your specific problem?

[jacobgil]

It can be tuned to your specific problem. As long as you can specify a target cost function, you can use this. I used this for visualizing the PilotNet network that outputs angles. This network is used for regression and not classification. https://jacobgil.github.io/deeplearning/vehicle-steering-angle-visualizations

[pardha-fission]

InvalidArgumentError Traceback (most recent call last) /home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args) 1326 try: -> 1327 return fn(*args) 1328 except errors.OpError as e:

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata) 1305 feed_dict, fetch_list, target_list, -> 1306 status, run_metadata) 1307

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/contextlib.py in exit(self, type, value, traceback) 88 try: ---> 89 next(self.gen) 90 except StopIteration:

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status() 465 compat.as_text(pywrap_tensorflow.TF_Message(status)), --> 466 pywrap_tensorflow.TF_GetCode(status)) 467 finally:

InvalidArgumentError: You must feed a value for placeholder tensor 'batch_normalization_1/keras_learning_phase' with dtype bool [[Node: batch_normalization_1/keras_learning_phase = Placeholderdtype=DT_BOOL, shape=, _device="/job:localhost/replica:0/task:0/cpu:0"]]

During handling of the above exception, another exception occurred:

InvalidArgumentError Traceback (most recent call last) in () 1 for i,layer_name in enumerate([l.name for l in my_model.layers]): ----> 2 cam, heatmap = grad_cam(my_model, preprocessed_img, predicted_class, layer_name) 3 cam = cv2.cvtColor(cam, cv2.COLOR_BGR2RGB) 4 plt.figure(i) 5 plt.title(str(layer_name))

in grad_cam(input_model, image, category_index, layer_name) 14 gradient_function = K.function([model.layers[0].input], [conv_output, grads]) 15 print('hellooooooooo',gradient_function) ---> 16 output, grads_val = gradient_function([image]) 17 output, grads_val = output[0, :], grads_val[0, :, :, :] 18

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in call(self, inputs) 2266 updated = session.run(self.outputs + [self.updates_op], 2267 feed_dict=feed_dict, -> 2268 **self.session_kwargs) 2269 return updated[:len(self.outputs)] 2270

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata) 893 try: 894 result = self._run(None, fetches, feed_dict, options_ptr, --> 895 run_metadata_ptr) 896 if run_metadata: 897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 1122 if final_fetches or final_targets or (handle and feed_dict_tensor): 1123 results = self._do_run(handle, final_targets, final_fetches, -> 1124 feed_dict_tensor, options, run_metadata) 1125 else: 1126 results = []

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata) 1319 if handle is None: 1320 return self._do_call(_run_fn, self._session, feeds, fetches, targets, -> 1321 options, run_metadata) 1322 else: 1323 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/home/pardha/anaconda3/envs/for_tensorflow/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args) 1338 except KeyError: 1339 pass -> 1340 raise type(e)(node_def, op, message) 1341 1342 def _extend_graph(self):

InvalidArgumentError: You must feed a value for placeholder tensor 'batch_normalization_1/keras_learning_phase' with dtype bool [[Node: batch_normalization_1/keras_learning_phase = Placeholderdtype=DT_BOOL, shape=, _device="/job:localhost/replica:0/task:0/cpu:0"]]