def makeNeuralNet(input_var=None):
net = {}
net['input'] = InputLayer(shape=(None, 3, 224, 224), input_var=input_var)
net['bnorm'] = BatchNormLayer(net['input'])
net['conv1'] = ConvLayer(net['bnorm'],
num_filters=96,
filter_size=5,
stride=2) #96*112*112
net['norm1'] = NormLayer(
net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False) #96*37...approx
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
pad=1)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool2'], num_units=1024)
net['drop6'] = DropoutLayer(net['fc6'], p=0.2)
net['_fc7'] = DenseLayer(net['drop6'], num_units=256)
net['_drop7'] = DropoutLayer(net['_fc7'], p=0.2)
net['_fc8out'] = DenseLayer(net['_drop7'],
num_units=1,
nonlinearity=lasagne.nonlinearities.sigmoid)
output_layer_driver = net['_fc8out']
return output_layer_driver, net
def lasagne_layers_method(self):
'''
INPUT: None
OUTPUT: Dict
Creates dictionary of vgg_cnn_s model Lasagne layer objects. Here the
original output layer (softmax, 1000 classes) has been removed and
the output layer returns a vector of shape (1,4096).
'''
# Create dictionary of VGG_CNN_S model layers
self.lasagne_layers = {}
self.lasagne_layers['input'] = InputLayer((None, 3, 224, 224))
self.lasagne_layers['conv1'] = ConvLayer(self.lasagne_layers['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
self.lasagne_layers['norm1'] = NormLayer(self.lasagne_layers['conv1'],
alpha=0.0001)
self.lasagne_layers['pool1'] = PoolLayer(self.lasagne_layers['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
self.lasagne_layers['conv2'] = ConvLayer(self.lasagne_layers['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
self.lasagne_layers['pool2'] = PoolLayer(self.lasagne_layers['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
self.lasagne_layers['conv3'] = ConvLayer(self.lasagne_layers['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
self.lasagne_layers['conv4'] = ConvLayer(self.lasagne_layers['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
self.lasagne_layers['conv5'] = ConvLayer(self.lasagne_layers['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
self.lasagne_layers['pool5'] = PoolLayer(self.lasagne_layers['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
self.lasagne_layers['fc6'] = DenseLayer(self.lasagne_layers['pool5'],
num_units=4096)
self.lasagne_layers['drop6'] = DropoutLayer(self.lasagne_layers['fc6'],
p=0.5)
self.lasagne_layers['fc7'] = DenseLayer(self.lasagne_layers['drop6'],
num_units=4096)
def build_model(input_var):
net = {}
net['input'] = InputLayer((None, 3, 224, 224), input_var=input_var)
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
# caffe has alpha = alpha * pool_size
net['norm1'] = NormLayer(net['conv1'], alpha=0.0001)
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'], num_units=1000, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], softmax)
return net
def makeNeuralNet():
net = {}
net['input'] = InputLayer(shape=(None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2)
net['norm1'] = NormLayer(
net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'], num_filters=256, filter_size=5)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
# net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
# net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
# net['fc8'] = DenseLayer(net['drop7'], num_units=1000, nonlinearity=lasagne.nonlinearities.softmax)
# output_layer_vgg = net['fc8']
ini = lasagne.init.HeUniform()
net['_fc7'] = DenseLayer(net['drop6'], num_units=4096, W=ini)
net['_drop7'] = DropoutLayer(net['_fc7'], p=0.5)
net['_fc8out'] = DenseLayer(net['_drop7'],
num_units=6,
nonlinearity=lasagne.nonlinearities.softmax,
W=ini)
output_layer_driver = net['_fc8out']
return net['drop6'], output_layer_driver
def build_neural_network(input_var, input_shape):
net = {}
net['input'] = InputLayer(input_shape, input_var)
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2)
net['norm1'] = NormLayer(net['conv1'], alpha=0.0001)
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'], num_filters=256, filter_size=5)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'], num_units=1, nonlinearity=None)
net['prob'] = NonlinearityLayer(net['fc8'], sigmoid)
return net
def __init__(self, load=True):
# Architecture
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
net['norm1'] = NormLayer(
net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'],
num_units=1000,
nonlinearity=lasagne.nonlinearities.softmax)
self.output_layer = net['fc8']
self.net = net
if load:
self.load_weights()
# Compile
self.predict_fn = None
self.predict_fns = {}
self.train_fn = {}
self.lr = theano.shared(np.array(1e-2, dtype=np.float32))
self.regularizer_amount = theano.shared(
np.array(4e-5, dtype=np.float32))
def create_pretrained_vgg_nn_data():
'''
Create a vgg neural net. Load pretrained weights.
Return the dictionary of nn layers, the lasagne output_layer, the mean_image
'''
# define the vgg_s network
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
net['norm1'] = NormLayer(
net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
# these are here JUST to upload the model; then not used
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'],
num_units=1000,
nonlinearity=lasagne.nonlinearities.softmax)
output_layer = net['fc8']
# upload and input the pretrained weights
model = pickle.load(open('./vgg_cnn_s.pkl'))
MEAN_IMAGE = model['mean image']
lasagne.layers.set_all_param_values(output_layer, model['values'])
output_layer = net['fc7']
net.pop('fc8')
return net, output_layer, MEAN_IMAGE
experimentpath = 'experiments/' + experimentname + '/'
if not os.path.exists(experimentpath):
os.makedirs(experimentpath)
epoch = 0
#Define the network structure
print 'define network'
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
net['norm1'] = NormLayer(net['conv1'],
alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
def __init__(self):
net = {}
net['input'] = InputLayer((None, 3, 224, 224))
net['conv1'] = ConvLayer(net['input'],
num_filters=96,
filter_size=7,
stride=2,
flip_filters=False)
net['norm1'] = NormLayer(
net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'],
pool_size=3,
stride=3,
ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'],
num_filters=256,
filter_size=5,
flip_filters=False)
net['pool2'] = PoolLayer(net['conv2'],
pool_size=2,
stride=2,
ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv4'] = ConvLayer(net['conv3'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['conv5'] = ConvLayer(net['conv4'],
num_filters=512,
filter_size=3,
pad=1,
flip_filters=False)
net['pool5'] = PoolLayer(net['conv5'],
pool_size=3,
stride=3,
ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=4096)
net['drop7'] = DropoutLayer(net['fc7'], p=0.5)
net['fc8'] = DenseLayer(net['drop7'],
num_units=1000,
nonlinearity=lasagne.nonlinearities.softmax)
print "loading vgg_cnn_s.pkl..."
#model = pickle.load(urllib.urlopen('https://dl.dropboxusercontent.com/u/10578702/img/vgg_cnn_s.pkl'))
model = pickle.load(
open(
'/home/tweddielin/cbir/flask-imsearch/app/static/vgg_cnn_s.pkl'
))
print "vgg_cnn_s.pkl loaded!"
self.output_layer = net['fc7']
self.CLASSES = model['synset words']
self.MEAN_IMAGE = model['mean image']
lasagne.layers.set_all_param_values(self.output_layer,
model['values'][0:14])