def bn_relu_dropout_conv(input_layer, filter_shape, strides, bn_param, keep_prob, device):
layer = [batch_norm(input_layer, bn_param, device=device)]
layer.append(tf.nn.relu(layer[-1]))
if FLAGS.keep_prob!=None:
layer.append(tf.nn.dropout(layer[-1], keep_prob[0]))
layer.append(convolution_layer(layer[-1], shape=filter_shape, strides=strides, bias=False, layer_name='conv', device=device))
return layer[-1]
def first_residual_block(input_layer, output_channel, bn_param, keep_prob, down_sample=False, device=None):
input_channel = input_layer.get_shape().as_list()[-1]
assert input_channel!=output_channel
if down_sample: strides=[1,2,2,1]
else: strides=[1,1,1,1]
with tf.variable_scope('layer1_in_block'):
conv1, relu = bn_relu_conv(input_layer, [3, 3, input_channel, output_channel], strides=strides, bn_param=bn_param, device=device)
with tf.variable_scope('layer2_in_block'):
conv2 = bn_relu_dropout_conv(conv1, [3, 3, output_channel, output_channel], strides=[1,1,1,1], bn_param=bn_param, keep_prob=keep_prob, device=device)
projection = convolution_layer(relu, shape=[1,1,input_channel,output_channel], strides=strides, bias=False, layer_name='projection', device=device)
return conv2 + projection
def inference(input_tensor_batch, bn_param, keep_prob, n, k, num_classes, device):
layers = []
with tf.variable_scope('group1'):
conv0 = convolution_layer(input_tensor_batch, shape=[3, 3, 3, 16], strides=[1, 1, 1, 1], bias=False, layer_name='conv0', device=device)
layers.append(conv0)
for i in range(n):
with tf.variable_scope('group2_block%d' %i):
if i == 0 and k!=1:
conv1 = first_residual_block(layers[-1], 16*k, bn_param, keep_prob, down_sample=False, device=device)
else:
conv1 = residual_block(layers[-1], 16*k, bn_param, keep_prob, device=device)
layers.append(conv1)
for i in range(n):
with tf.variable_scope('group3_block%d' %i):
if i==0:
conv2 = first_residual_block(layers[-1], 32*k, bn_param, keep_prob, down_sample=True, device=device)
else:
conv2 = residual_block(layers[-1], 32*k, bn_param, keep_prob, device=device)
layers.append(conv2)
for i in range(n):
with tf.variable_scope('group4_block%d' %i):
if i==0:
conv3 = first_residual_block(layers[-1], 64*k, bn_param, keep_prob, down_sample=True, device=device)
else:
conv3 = residual_block(layers[-1], 64*k, bn_param, keep_prob, device=device)
layers.append(conv3)
assert conv3.get_shape().as_list()[1:] == [8, 8, 64*k]
with tf.variable_scope('fc'):
bn_layer = batch_norm(layers[-1], bn_param, device=device)
relu_layer = tf.nn.relu(bn_layer)
global_pool = tf.reduce_mean(relu_layer, [1, 2])
assert global_pool.get_shape().as_list()[-1:] == [64*k]
shape=[global_pool.get_shape().as_list()[-1], num_classes]
output = full_connection_layer(global_pool, shape=shape, bias=True, layer_name='output', device=device)
layers.append(output)
return layers[-1]
def get_model(self):
params = {
'batch_size': 20,
'learning_rate': 0.01,
'epochs': 20,
'num_classes': 10,
'dropout_rate': 0.1
}
Model = model.model()
Model.add(layers.convolution_layer(field=8, padding=0, stride=1, depth=1, filters=5))
Model.add(layers.relu_layer())
Model.add(layers.flatten_layer())
Model.add(layers.dropout_layer(r = params['dropout_rate']))
Model.add(layers.linear_layer(13*13*5, 10))
Model.set_loss(layers.softmax_cross_entropy())
Model.set_hyper_params(params)
return Model
def conv_bn_relu(inputTensor, shape, bn_param, device): conv = convolution_layer(inputTensor, shape, strides=[1,1,1,1], bias=False, layer_name='conv', device=device) bn = batch_norm(conv, bn_param=bn_param, scale=False, device = device) return tf.nn.relu(bn)
def bn_relu_conv(input_layer, filter_shape, strides, bn_param, device):
bn = batch_norm(input_layer, bn_param, device=device)
relu = tf.nn.relu(bn)
conv = convolution_layer(relu, shape=filter_shape, strides=strides, bias=False, layer_name='conv', device=device)
return conv, relu
def run():
model_name = 'alexnet'
directory_caffe = './caffemodel'
directory_theano = './theanomodel'
url_prototxt = 'https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_alexnet/deploy.prototxt'
url_caffemodel = 'http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel'
filename_prototxt = '%s/%s.prototxt' % (directory_caffe, model_name)
filename_caffemodel = '%s/%s.caffemodel' % (directory_caffe, model_name)
filename_theanomodel = '%s/%s.model' % (directory_theano, model_name)
# download caffemodel
print 'downloading caffemodel'
if not os.path.exists(directory_caffe):
os.mkdir(directory_caffe)
if not os.path.exists(filename_prototxt):
p = subprocess.Popen(('wget', url_prototxt, '-O', filename_prototxt))
p.wait()
if not os.path.exists(filename_caffemodel):
p = subprocess.Popen((
'wget',
url_caffemodel,
'-O',
filename_caffemodel,
))
p.wait()
# load caffe model
print 'loading caffe model'
model_caffe = caffe.Net(filename_prototxt, filename_caffemodel, True)
conv1_W = theano.shared(model_caffe.params['conv1'][0].data[:, :, ::-1, ::-1])
conv2_W = theano.shared(model_caffe.params['conv2'][0].data[:, :, ::-1, ::-1])
conv3_W = theano.shared(model_caffe.params['conv3'][0].data[:, :, ::-1, ::-1])
conv4_W = theano.shared(model_caffe.params['conv4'][0].data[:, :, ::-1, ::-1])
conv5_W = theano.shared(model_caffe.params['conv5'][0].data[:, :, ::-1, ::-1])
conv1_b = theano.shared(model_caffe.params['conv1'][1].data.squeeze())
conv2_b = theano.shared(model_caffe.params['conv2'][1].data.squeeze())
conv3_b = theano.shared(model_caffe.params['conv3'][1].data.squeeze())
conv4_b = theano.shared(model_caffe.params['conv4'][1].data.squeeze())
conv5_b = theano.shared(model_caffe.params['conv5'][1].data.squeeze())
fc6_W = theano.shared(model_caffe.params['fc6'][0].data.squeeze())
fc7_W = theano.shared(model_caffe.params['fc7'][0].data.squeeze())
fc8_W = theano.shared(model_caffe.params['fc8'][0].data.squeeze())
fc6_b = theano.shared(model_caffe.params['fc6'][1].data.squeeze())
fc7_b = theano.shared(model_caffe.params['fc7'][1].data.squeeze())
fc8_b = theano.shared(model_caffe.params['fc8'][1].data.squeeze())
# make theano model
print 'building theano model'
model_theano = collections.OrderedDict()
model_theano['data'] = T.tensor4()
model_theano['conv1'] = layers.convolution_layer(model_theano['data'], conv1_W, conv1_b, subsample=(4, 4))
model_theano['relu1'] = layers.relu_layer(model_theano['conv1'])
model_theano['norm1'] = layers.lrn_layer(model_theano['relu1'])
model_theano['pool1'] = layers.pooling_layer(model_theano['norm1'])
model_theano['conv2'] = layers.convolution_layer(model_theano['pool1'], conv2_W, conv2_b, border='same', group=2)
model_theano['relu2'] = layers.relu_layer(model_theano['conv2'])
model_theano['norm2'] = layers.lrn_layer(model_theano['relu2'])
model_theano['pool2'] = layers.pooling_layer(model_theano['norm2'])
model_theano['conv3'] = layers.convolution_layer(model_theano['pool2'], conv3_W, conv3_b, border='same')
model_theano['relu3'] = layers.relu_layer(model_theano['conv3'])
model_theano['conv4'] = layers.convolution_layer(model_theano['relu3'], conv4_W, conv4_b, border='same', group=2)
model_theano['relu4'] = layers.relu_layer(model_theano['conv4'])
model_theano['conv5'] = layers.convolution_layer(model_theano['relu4'], conv5_W, conv5_b, border='same', group=2)
model_theano['relu5'] = layers.relu_layer(model_theano['conv5'])
model_theano['pool5'] = layers.pooling_layer(model_theano['relu5'])
model_theano['fc6'] = layers.inner_product_layer(model_theano['pool5'], fc6_W, fc6_b)
model_theano['relu6'] = layers.relu_layer(model_theano['fc6'])
model_theano['fc7'] = layers.inner_product_layer(model_theano['relu6'], fc7_W, fc7_b)
model_theano['relu7'] = layers.relu_layer(model_theano['fc7'])
model_theano['fc8'] = layers.inner_product_layer(model_theano['relu7'], fc8_W, fc8_b)
model_theano['prob'] = layers.softmax_layer(model_theano['fc8'])
# check
print 'checking model'
data = np.random.randn(*model_caffe.blobs['data'].data.shape)
data = data.astype(np.float32) * 10
model_caffe.blobs['data'].data[:] = data
model_caffe.forward()
theano_output = theano.function(
[model_theano['data']],
model_theano['prob'],
)(data)
error = (
theano_output.squeeze() -
model_caffe.blobs['prob'].data.squeeze()
).max()
assert error < 1e-6
# save
print 'saving'
if not os.path.exists(directory_theano):
os.mkdir(directory_theano)
sys.setrecursionlimit(100000)
pickle.dump(
model_theano,
open(filename_theanomodel, 'wb'),
protocol=pickle.HIGHEST_PROTOCOL,
)
print 'done'
def run():
model_name = 'alexnet'
directory_caffe = './caffemodel'
directory_theano = './theanomodel'
url_prototxt = 'https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_alexnet/deploy.prototxt'
url_caffemodel = 'http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel'
filename_prototxt = '%s/%s.prototxt' % (directory_caffe, model_name)
filename_caffemodel = '%s/%s.caffemodel' % (directory_caffe, model_name)
filename_theanomodel = '%s/%s.model' % (directory_theano, model_name)
# download caffemodel
print 'downloading caffemodel'
if not os.path.exists(directory_caffe):
os.mkdir(directory_caffe)
if not os.path.exists(filename_prototxt):
p = subprocess.Popen(('wget', url_prototxt, '-O', filename_prototxt))
p.wait()
if not os.path.exists(filename_caffemodel):
p = subprocess.Popen((
'wget',
url_caffemodel,
'-O',
filename_caffemodel,
))
p.wait()
# load caffe model
print 'loading caffe model'
model_caffe = caffe.Net(filename_prototxt, filename_caffemodel, True)
conv1_W = theano.shared(
model_caffe.params['conv1'][0].data[:, :, ::-1, ::-1])
conv2_W = theano.shared(
model_caffe.params['conv2'][0].data[:, :, ::-1, ::-1])
conv3_W = theano.shared(
model_caffe.params['conv3'][0].data[:, :, ::-1, ::-1])
conv4_W = theano.shared(
model_caffe.params['conv4'][0].data[:, :, ::-1, ::-1])
conv5_W = theano.shared(
model_caffe.params['conv5'][0].data[:, :, ::-1, ::-1])
conv1_b = theano.shared(model_caffe.params['conv1'][1].data.squeeze())
conv2_b = theano.shared(model_caffe.params['conv2'][1].data.squeeze())
conv3_b = theano.shared(model_caffe.params['conv3'][1].data.squeeze())
conv4_b = theano.shared(model_caffe.params['conv4'][1].data.squeeze())
conv5_b = theano.shared(model_caffe.params['conv5'][1].data.squeeze())
fc6_W = theano.shared(model_caffe.params['fc6'][0].data.squeeze())
fc7_W = theano.shared(model_caffe.params['fc7'][0].data.squeeze())
fc8_W = theano.shared(model_caffe.params['fc8'][0].data.squeeze())
fc6_b = theano.shared(model_caffe.params['fc6'][1].data.squeeze())
fc7_b = theano.shared(model_caffe.params['fc7'][1].data.squeeze())
fc8_b = theano.shared(model_caffe.params['fc8'][1].data.squeeze())
# make theano model
print 'building theano model'
model_theano = collections.OrderedDict()
model_theano['data'] = T.tensor4()
model_theano['conv1'] = layers.convolution_layer(model_theano['data'],
conv1_W,
conv1_b,
subsample=(4, 4))
model_theano['relu1'] = layers.relu_layer(model_theano['conv1'])
model_theano['norm1'] = layers.lrn_layer(model_theano['relu1'])
model_theano['pool1'] = layers.pooling_layer(model_theano['norm1'])
model_theano['conv2'] = layers.convolution_layer(model_theano['pool1'],
conv2_W,
conv2_b,
border='same',
group=2)
model_theano['relu2'] = layers.relu_layer(model_theano['conv2'])
model_theano['norm2'] = layers.lrn_layer(model_theano['relu2'])
model_theano['pool2'] = layers.pooling_layer(model_theano['norm2'])
model_theano['conv3'] = layers.convolution_layer(model_theano['pool2'],
conv3_W,
conv3_b,
border='same')
model_theano['relu3'] = layers.relu_layer(model_theano['conv3'])
model_theano['conv4'] = layers.convolution_layer(model_theano['relu3'],
conv4_W,
conv4_b,
border='same',
group=2)
model_theano['relu4'] = layers.relu_layer(model_theano['conv4'])
model_theano['conv5'] = layers.convolution_layer(model_theano['relu4'],
conv5_W,
conv5_b,
border='same',
group=2)
model_theano['relu5'] = layers.relu_layer(model_theano['conv5'])
model_theano['pool5'] = layers.pooling_layer(model_theano['relu5'])
model_theano['fc6'] = layers.inner_product_layer(model_theano['pool5'],
fc6_W, fc6_b)
model_theano['relu6'] = layers.relu_layer(model_theano['fc6'])
model_theano['fc7'] = layers.inner_product_layer(model_theano['relu6'],
fc7_W, fc7_b)
model_theano['relu7'] = layers.relu_layer(model_theano['fc7'])
model_theano['fc8'] = layers.inner_product_layer(model_theano['relu7'],
fc8_W, fc8_b)
model_theano['prob'] = layers.softmax_layer(model_theano['fc8'])
# check
print 'checking model'
data = np.random.randn(*model_caffe.blobs['data'].data.shape)
data = data.astype(np.float32) * 10
model_caffe.blobs['data'].data[:] = data
model_caffe.forward()
theano_output = theano.function(
[model_theano['data']],
model_theano['prob'],
)(data)
error = (theano_output.squeeze() -
model_caffe.blobs['prob'].data.squeeze()).max()
assert error < 1e-6
# save
print 'saving'
if not os.path.exists(directory_theano):
os.mkdir(directory_theano)
sys.setrecursionlimit(100000)
pickle.dump(
model_theano,
open(filename_theanomodel, 'wb'),
protocol=pickle.HIGHEST_PROTOCOL,
)
print 'done'
def run():
model_name = "vggnet"
directory_caffe = "./caffemodel"
directory_theano = "./theanomodel"
url_prototxt = "https://gist.githubusercontent.com/ksimonyan/3785162f95cd2d5fee77/raw/f02f8769e64494bcd3d7e97d5d747ac275825721/VGG_ILSVRC_19_layers_deploy.prototxt"
url_caffemodel = "http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_19_layers.caffemodel"
filename_prototxt = "%s/%s.prototxt" % (directory_caffe, model_name)
filename_caffemodel = "%s/%s.caffemodel" % (directory_caffe, model_name)
filename_theanomodel = "%s/%s.model" % (directory_theano, model_name)
# download caffemodel
print "downloading caffemodel"
if not os.path.exists(directory_caffe):
os.mkdir(directory_caffe)
if not os.path.exists(filename_prototxt):
p = subprocess.Popen(("wget", url_prototxt, "-O", filename_prototxt))
p.wait()
if not os.path.exists(filename_caffemodel):
p = subprocess.Popen(("wget", url_caffemodel, "-O", filename_caffemodel))
p.wait()
# load caffe model
model_caffe = caffe.Net(filename_prototxt, filename_caffemodel, True)
conv1_1_W = theano.shared(model_caffe.params["conv1_1"][0].data[:, :, ::-1, ::-1])
conv1_2_W = theano.shared(model_caffe.params["conv1_2"][0].data[:, :, ::-1, ::-1])
conv2_1_W = theano.shared(model_caffe.params["conv2_1"][0].data[:, :, ::-1, ::-1])
conv2_2_W = theano.shared(model_caffe.params["conv2_2"][0].data[:, :, ::-1, ::-1])
conv3_1_W = theano.shared(model_caffe.params["conv3_1"][0].data[:, :, ::-1, ::-1])
conv3_2_W = theano.shared(model_caffe.params["conv3_2"][0].data[:, :, ::-1, ::-1])
conv3_3_W = theano.shared(model_caffe.params["conv3_3"][0].data[:, :, ::-1, ::-1])
conv3_4_W = theano.shared(model_caffe.params["conv3_4"][0].data[:, :, ::-1, ::-1])
conv4_1_W = theano.shared(model_caffe.params["conv4_1"][0].data[:, :, ::-1, ::-1])
conv4_2_W = theano.shared(model_caffe.params["conv4_2"][0].data[:, :, ::-1, ::-1])
conv4_3_W = theano.shared(model_caffe.params["conv4_3"][0].data[:, :, ::-1, ::-1])
conv4_4_W = theano.shared(model_caffe.params["conv4_4"][0].data[:, :, ::-1, ::-1])
conv5_1_W = theano.shared(model_caffe.params["conv5_1"][0].data[:, :, ::-1, ::-1])
conv5_2_W = theano.shared(model_caffe.params["conv5_2"][0].data[:, :, ::-1, ::-1])
conv5_3_W = theano.shared(model_caffe.params["conv5_3"][0].data[:, :, ::-1, ::-1])
conv5_4_W = theano.shared(model_caffe.params["conv5_4"][0].data[:, :, ::-1, ::-1])
conv1_1_b = theano.shared(model_caffe.params["conv1_1"][1].data.squeeze())
conv1_2_b = theano.shared(model_caffe.params["conv1_2"][1].data.squeeze())
conv2_1_b = theano.shared(model_caffe.params["conv2_1"][1].data.squeeze())
conv2_2_b = theano.shared(model_caffe.params["conv2_2"][1].data.squeeze())
conv3_1_b = theano.shared(model_caffe.params["conv3_1"][1].data.squeeze())
conv3_2_b = theano.shared(model_caffe.params["conv3_2"][1].data.squeeze())
conv3_3_b = theano.shared(model_caffe.params["conv3_3"][1].data.squeeze())
conv3_4_b = theano.shared(model_caffe.params["conv3_4"][1].data.squeeze())
conv4_1_b = theano.shared(model_caffe.params["conv4_1"][1].data.squeeze())
conv4_2_b = theano.shared(model_caffe.params["conv4_2"][1].data.squeeze())
conv4_3_b = theano.shared(model_caffe.params["conv4_3"][1].data.squeeze())
conv4_4_b = theano.shared(model_caffe.params["conv4_4"][1].data.squeeze())
conv5_1_b = theano.shared(model_caffe.params["conv5_1"][1].data.squeeze())
conv5_2_b = theano.shared(model_caffe.params["conv5_2"][1].data.squeeze())
conv5_3_b = theano.shared(model_caffe.params["conv5_3"][1].data.squeeze())
conv5_4_b = theano.shared(model_caffe.params["conv5_4"][1].data.squeeze())
fc6_W = theano.shared(model_caffe.params["fc6"][0].data.squeeze())
fc7_W = theano.shared(model_caffe.params["fc7"][0].data.squeeze())
fc8_W = theano.shared(model_caffe.params["fc8"][0].data.squeeze())
fc6_b = theano.shared(model_caffe.params["fc6"][1].data.squeeze())
fc7_b = theano.shared(model_caffe.params["fc7"][1].data.squeeze())
fc8_b = theano.shared(model_caffe.params["fc8"][1].data.squeeze())
# make theano model
model_theano = collections.OrderedDict()
model_theano["data"] = T.tensor4()
model_theano["conv1_1"] = layers.convolution_layer(model_theano["data"], conv1_1_W, conv1_1_b, border="same")
model_theano["relu1_1"] = layers.relu_layer(model_theano["conv1_1"])
model_theano["conv1_2"] = layers.convolution_layer(model_theano["relu1_1"], conv1_2_W, conv1_2_b, border="same")
model_theano["relu1_2"] = layers.relu_layer(model_theano["conv1_2"])
model_theano["pool1"] = layers.pooling_layer(model_theano["relu1_2"], size=(2, 2), stride=(2, 2))
model_theano["conv2_1"] = layers.convolution_layer(model_theano["pool1"], conv2_1_W, conv2_1_b, border="same")
model_theano["relu2_1"] = layers.relu_layer(model_theano["conv2_1"])
model_theano["conv2_2"] = layers.convolution_layer(model_theano["relu2_1"], conv2_2_W, conv2_2_b, border="same")
model_theano["relu2_2"] = layers.relu_layer(model_theano["conv2_2"])
model_theano["pool2"] = layers.pooling_layer(model_theano["relu2_2"], size=(2, 2), stride=(2, 2))
model_theano["conv3_1"] = layers.convolution_layer(model_theano["pool2"], conv3_1_W, conv3_1_b, border="same")
model_theano["relu3_1"] = layers.relu_layer(model_theano["conv3_1"])
model_theano["conv3_2"] = layers.convolution_layer(model_theano["relu3_1"], conv3_2_W, conv3_2_b, border="same")
model_theano["relu3_2"] = layers.relu_layer(model_theano["conv3_2"])
model_theano["conv3_3"] = layers.convolution_layer(model_theano["relu3_2"], conv3_3_W, conv3_3_b, border="same")
model_theano["relu3_3"] = layers.relu_layer(model_theano["conv3_3"])
model_theano["conv3_4"] = layers.convolution_layer(model_theano["relu3_3"], conv3_4_W, conv3_4_b, border="same")
model_theano["relu3_4"] = layers.relu_layer(model_theano["conv3_4"])
model_theano["pool3"] = layers.pooling_layer(model_theano["relu3_4"], size=(2, 2), stride=(2, 2))
model_theano["conv4_1"] = layers.convolution_layer(model_theano["pool3"], conv4_1_W, conv4_1_b, border="same")
model_theano["relu4_1"] = layers.relu_layer(model_theano["conv4_1"])
model_theano["conv4_2"] = layers.convolution_layer(model_theano["relu4_1"], conv4_2_W, conv4_2_b, border="same")
model_theano["relu4_2"] = layers.relu_layer(model_theano["conv4_2"])
model_theano["conv4_3"] = layers.convolution_layer(model_theano["relu4_2"], conv4_3_W, conv4_3_b, border="same")
model_theano["relu4_3"] = layers.relu_layer(model_theano["conv4_3"])
model_theano["conv4_4"] = layers.convolution_layer(model_theano["relu4_3"], conv4_4_W, conv4_4_b, border="same")
model_theano["relu4_4"] = layers.relu_layer(model_theano["conv4_4"])
model_theano["pool4"] = layers.pooling_layer(model_theano["relu4_4"], size=(2, 2), stride=(2, 2))
model_theano["conv5_1"] = layers.convolution_layer(model_theano["pool4"], conv5_1_W, conv5_1_b, border="same")
model_theano["relu5_1"] = layers.relu_layer(model_theano["conv5_1"])
model_theano["conv5_2"] = layers.convolution_layer(model_theano["relu5_1"], conv5_2_W, conv5_2_b, border="same")
model_theano["relu5_2"] = layers.relu_layer(model_theano["conv5_2"])
model_theano["conv5_3"] = layers.convolution_layer(model_theano["relu5_2"], conv5_3_W, conv5_3_b, border="same")
model_theano["relu5_3"] = layers.relu_layer(model_theano["conv5_3"])
model_theano["conv5_4"] = layers.convolution_layer(model_theano["relu5_3"], conv5_4_W, conv5_4_b, border="same")
model_theano["relu5_4"] = layers.relu_layer(model_theano["conv5_4"])
model_theano["pool5"] = layers.pooling_layer(model_theano["relu5_4"], size=(2, 2), stride=(2, 2))
model_theano["fc6"] = layers.inner_product_layer(model_theano["pool5"], fc6_W, fc6_b)
model_theano["relu6"] = layers.relu_layer(model_theano["fc6"])
model_theano["fc7"] = layers.inner_product_layer(model_theano["relu6"], fc7_W, fc7_b)
model_theano["relu7"] = layers.relu_layer(model_theano["fc7"])
model_theano["fc8"] = layers.inner_product_layer(model_theano["relu7"], fc8_W, fc8_b)
model_theano["prob"] = layers.softmax_layer(model_theano["fc8"])
# check
data = np.random.randn(*model_caffe.blobs["data"].data.shape).astype(np.float32) * 10
model_caffe.blobs["data"].data[:] = data
model_caffe.forward()
theano_output = theano.function([model_theano["data"]], model_theano["prob"])(data)
error = (theano_output.squeeze() - model_caffe.blobs["prob"].data.squeeze()).max()
assert error < 1e-6
# save
print "saving"
if not os.path.exists(directory_theano):
os.mkdir(directory_theano)
sys.setrecursionlimit(100000)
pickle.dump(model_theano, open(filename_theanomodel, "wb"), protocol=pickle.HIGHEST_PROTOCOL)
print "done"
