Model.add(Dense(10, activation='softmax')) # Instead of 4096 classes, I have got 10 classes. Model.add(Dense(4096, activation='relu')) # we don't look at the last (fully-connected) layers in the savefile
#MYSCRIPT NOTES 2.2 LIGHT DOWNLOAD CODE#
I use the code above to classify into 10 classes.Īfter convolution layers, I add the following: f = h5py.File(weights_path)
#MYSCRIPT NOTES 2.2 LIGHT DOWNLOAD HOW TO#
Traceback (most recent call last): File "vgg-16_keras.py", line 69, in model = VGG_16('vgg16_weights.h5') File "vgg-16_keras.py", line 48, in VGG_16 model.add(Dense(4096, activation='relu')) File "build/bdist.linux-x86_64/egg/keras/layers/containers.py", line 70, in add File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 153, in set_previous File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 1015, in build File "build/bdist.linux-x86_64/egg/keras/initializations.py", line 59, in glorot_uniform File "build/bdist.linux-x86_64/egg/keras/initializations.py", line 31, in uniform File "build/bdist.linux-x86_64/egg/keras/backend/theano_backend.py", line 34, in variable File "/imatge/imasuda/kerasenv/local/lib/python2.7/site-packages/numpy/core/numeric.py", line 474, in asarray return array(a, dtype, copy=False, order=order) MemoryErrorĮven if it says MemoryError, I've run it with 3GB of RAM dedicated to it (with GPU acceleration) and still throwing the same error.Īny suggestions on how to fix this problem? Thks! Hi! I'm trying to run your example with the weight you provide and I'm getting the following error: TypeError: unsupported operand type(s) for *: 'int' and 'NoneType' > 35 return umr_prod(a, axis, dtype, out, keepdims)ģ7 def _any(a, axis=None, dtype=None, out=None, keepdims=False): usr/local/lib/python2.7/site-packages/numpy/core/_methods.pyc in _prod(a, axis, dtype, out, keepdims)ģ4 def _prod(a, axis=None, dtype=None, out=None, keepdims=False): usr/local/lib/python2.7/site-packages/numpy/core/fromnumeric.pyc in prod(a, axis, dtype, out, keepdims)Ģ480 return _methods._prod(a, axis=axis, dtype=dtype,Ģ482 return prod(axis=axis, dtype=dtype, out=out) usr/local/lib/python2.7/site-packages/Keras-0.3.1-py2.7.egg/keras/backend/tensorflow_backend.pyc in batch_flatten(x) > 173 previous_output = _output(train=train)ġ74 if hasattr(self, 'layer_cache') and self.cache_enabled:ġ75 previous_layer_id = '%s_%s' % (id(self.previous), train) usr/local/lib/python2.7/site-packages/Keras-0.3.1-py2.7.egg/keras/layers/core.pyc in get_input(self, train)ġ71 if previous_layer_id in self.layer_cache:ġ72 return self.layer_cache usr/local/lib/python2.7/site-packages/Keras-0.3.1-py2.7.egg/keras/layers/core.pyc in get_output(self, train)ĩ63 output = self.activation(K.dot(X, self.W) + self.b) usr/local/lib/python2.7/site-packages/Keras-0.3.1-py2.7.egg/keras/layers/containers.pyc in get_output(self, train)
> 435 self.y_train = self.get_output(train=True)Ĥ36 self.y_test = self.get_output(train=False) usr/local/lib/python2.7/site-packages/Keras-0.3.1-py2.7.egg/keras/models.pyc in compile(self, optimizer, loss, class_mode)Ĥ33 self.X_test = self.get_input(train=False) > 12 pile(optimizer=sgd, loss='categorical_crossentropy') TypeError Traceback (most recent call last)ġ1 sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True) compile( optimizer = sgd, loss = 'categorical_crossentropy') Sgd = SGD( lr = 0.1, decay = 1e-6, momentum = 0.9, nesterov = True) add( Dense( 1000, activation = 'softmax')) add( Convolution2D( 512, 3, 3, activation = 'relu')) add( Convolution2D( 256, 3, 3, activation = 'relu')) add( Convolution2D( 128, 3, 3, activation = 'relu')) add( Convolution2D( 64, 3, 3, activation = 'relu')) convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D core import Flatten, Dense, Dropoutįrom keras.
0 kommentar(er)
