____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
convolution2d_1 (Convolution2D) (None, 137, 275, 32) 896 convolution2d_input_1[0][0]
____________________________________________________________________________________________________
maxpooling2d_1 (MaxPooling2D) (None, 68, 137, 32) 0 convolution2d_1[0][0]
____________________________________________________________________________________________________
convolution2d_2 (Convolution2D) (None, 68, 137, 64) 18496 maxpooling2d_1[0][0]
____________________________________________________________________________________________________
maxpooling2d_2 (MaxPooling2D) (None, 33, 68, 64) 0 convolution2d_2[0][0]
____________________________________________________________________________________________________
convolution2d_3 (Convolution2D) (None, 33, 68, 64) 36928 maxpooling2d_2[0][0]
____________________________________________________________________________________________________
maxpooling2d_3 (MaxPooling2D) (None, 16, 33, 64) 0 convolution2d_3[0][0]
____________________________________________________________________________________________________
convolution2d_4 (Convolution2D) (None, 16, 33, 128) 73856 maxpooling2d_3[0][0]
____________________________________________________________________________________________________
maxpooling2d_4 (MaxPooling2D) (None, 7, 16, 128) 0 convolution2d_4[0][0]
____________________________________________________________________________________________________
convolution2d_5 (Convolution2D) (None, 7, 16, 128) 147584 maxpooling2d_4[0][0]
____________________________________________________________________________________________________
maxpooling2d_5 (MaxPooling2D) (None, 3, 7, 128) 0 convolution2d_5[0][0]
____________________________________________________________________________________________________
flatten_1 (Flatten) (None, 2688) 0 maxpooling2d_5[0][0]
____________________________________________________________________________________________________
dense_1 (Dense) (None, 1024) 2753536 flatten_1[0][0]
____________________________________________________________________________________________________
activation_1 (Activation) (None, 1024) 0 dense_1[0][0]
____________________________________________________________________________________________________
dropout_1 (Dropout) (None, 1024) 0 activation_1[0][0]
____________________________________________________________________________________________________
dense_2 (Dense) (None, 1024) 1049600 dropout_1[0][0]
____________________________________________________________________________________________________
activation_2 (Activation) (None, 1024) 0 dense_2[0][0]
____________________________________________________________________________________________________
dropout_2 (Dropout) (None, 1024) 0 activation_2[0][0]
____________________________________________________________________________________________________
dense_3 (Dense) (None, 800) 820000 dropout_2[0][0]
====================================================================================================
Total params: 4,900,896
Trainable params: 4,900,896
Non-trainable params: 0
____________________________________________________________________________________________________
INFO:tensorflow:Summary name inference/convolution2d_1_W:0 is illegal; using inference/convolution2d_1_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_1_W:0 is illegal; using inference/convolution2d_1_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_1_b:0 is illegal; using inference/convolution2d_1_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_1_b:0 is illegal; using inference/convolution2d_1_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_2_W:0 is illegal; using inference/convolution2d_2_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_2_W:0 is illegal; using inference/convolution2d_2_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_2_b:0 is illegal; using inference/convolution2d_2_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_2_b:0 is illegal; using inference/convolution2d_2_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_3_W:0 is illegal; using inference/convolution2d_3_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_3_W:0 is illegal; using inference/convolution2d_3_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_3_b:0 is illegal; using inference/convolution2d_3_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_3_b:0 is illegal; using inference/convolution2d_3_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_4_W:0 is illegal; using inference/convolution2d_4_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_4_W:0 is illegal; using inference/convolution2d_4_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_4_b:0 is illegal; using inference/convolution2d_4_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_4_b:0 is illegal; using inference/convolution2d_4_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_5_W:0 is illegal; using inference/convolution2d_5_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_5_W:0 is illegal; using inference/convolution2d_5_W_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_5_b:0 is illegal; using inference/convolution2d_5_b_0 instead.
INFO:tensorflow:Summary name inference/convolution2d_5_b:0 is illegal; using inference/convolution2d_5_b_0 instead.
INFO:tensorflow:Summary name inference/dense_1_W:0 is illegal; using inference/dense_1_W_0 instead.
INFO:tensorflow:Summary name inference/dense_1_W:0 is illegal; using inference/dense_1_W_0 instead.
INFO:tensorflow:Summary name inference/dense_1_b:0 is illegal; using inference/dense_1_b_0 instead.
INFO:tensorflow:Summary name inference/dense_1_b:0 is illegal; using inference/dense_1_b_0 instead.
INFO:tensorflow:Summary name inference/dense_2_W:0 is illegal; using inference/dense_2_W_0 instead.
INFO:tensorflow:Summary name inference/dense_2_W:0 is illegal; using inference/dense_2_W_0 instead.
INFO:tensorflow:Summary name inference/dense_2_b:0 is illegal; using inference/dense_2_b_0 instead.
INFO:tensorflow:Summary name inference/dense_2_b:0 is illegal; using inference/dense_2_b_0 instead.
INFO:tensorflow:Summary name inference/dense_3_W:0 is illegal; using inference/dense_3_W_0 instead.
INFO:tensorflow:Summary name inference/dense_3_W:0 is illegal; using inference/dense_3_W_0 instead.
INFO:tensorflow:Summary name inference/dense_3_b:0 is illegal; using inference/dense_3_b_0 instead.
INFO:tensorflow:Summary name inference/dense_3_b:0 is illegal; using inference/dense_3_b_0 instead.
Epoch 1/5
100/200 [==============>...............] - ETA: 7s - loss: -14.5242 - acc: 0.0000e+00Epoch 00000: val_loss improved from inf to 5.98299, saving model to ./tensorlog/weights.hdf5
200/200 [==============================] - 16s - loss: -12.3660 - acc: 0.0000e+00 - val_loss: 5.9830 - val_acc: 0.0000e+00
Epoch 2/5
100/200 [==============>...............] - ETA: 5s - loss: 17.7468 - acc: 0.0000e+00Epoch 00001: val_loss did not improve
200/200 [==============================] - 14s - loss: 10.8940 - acc: 0.0000e+00 - val_loss: 8.6897 - val_acc: 0.0000e+00
Epoch 3/5
100/200 [==============>...............] - ETA: 6s - loss: -2.0779 - acc: 0.0000e+00
---------------------------------------------------------------------------
KeyboardInterrupt Traceback (most recent call last)
<ipython-input-21-13739671e65d> in <module>()
15 es_cb = EarlyStopping(monitor='val_loss', patience=1, verbose=1, mode='auto')
16 cp_cb = ModelCheckpoint(filepath = fpath, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
---> 17 history = model.fit_generator(train_generator,samples_per_epoch=nb_train_samples, nb_epoch=nb_epoch, validation_data=validation_generator, nb_val_samples=nb_validation_samples, callbacks=[cp_cb, es_cb, tb_cb])
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/models.pyc in fit_generator(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, nb_worker, pickle_safe, initial_epoch, **kwargs)
933 nb_worker=nb_worker,
934 pickle_safe=pickle_safe,
--> 935 initial_epoch=initial_epoch)
936
937 def evaluate_generator(self, generator, val_samples,
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.pyc in fit_generator(self, generator, samples_per_epoch, nb_epoch, verbose, callbacks, validation_data, nb_val_samples, class_weight, max_q_size, nb_worker, pickle_safe, initial_epoch)
1555 outs = self.train_on_batch(x, y,
1556 sample_weight=sample_weight,
-> 1557 class_weight=class_weight)
1558
1559 if not isinstance(outs, list):
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/engine/training.pyc in train_on_batch(self, x, y, sample_weight, class_weight)
1318 ins = x + y + sample_weights
1319 self._make_train_function()
-> 1320 outputs = self.train_function(ins)
1321 if len(outputs) == 1:
1322 return outputs[0]
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/Keras-1.2.2-py2.7.egg/keras/backend/tensorflow_backend.pyc in __call__(self, inputs)
1941 session = get_session()
1942 updated = session.run(self.outputs + [self.updates_op],
-> 1943 feed_dict=feed_dict)
1944 return updated[:len(self.outputs)]
1945
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
765 try:
766 result = self._run(None, fetches, feed_dict, options_ptr,
--> 767 run_metadata_ptr)
768 if run_metadata:
769 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
963 if final_fetches or final_targets:
964 results = self._do_run(handle, final_targets, final_fetches,
--> 965 feed_dict_string, options, run_metadata)
966 else:
967 results = []
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1013 if handle is None:
1014 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1015 target_list, options, run_metadata)
1016 else:
1017 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1020 def _do_call(self, fn, *args):
1021 try:
-> 1022 return fn(*args)
1023 except errors.OpError as e:
1024 message = compat.as_text(e.message)
/Users/YumaKajihara/.pyenv/versions/anaconda2-2.5.0/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1002 return tf_session.TF_Run(session, options,
1003 feed_dict, fetch_list, target_list,
-> 1004 status, run_metadata)
1005
1006 def _prun_fn(session, handle, feed_dict, fetch_list):
KeyboardInterrupt: