Example of Loading Pretrained Model

[cancan101]

https://github.com/Lasagne/Recipes (see modelzoo) offers a number of pre-trained models. I suggest providing an example of loading weights for one of the pre-trained model.

See also: Lasagne/Recipes#20

[dnouri]

Here's an example of loading params for a VGG16 net.

• First download the pickle file: https://s3.amazonaws.com/lasagne/recipes/pretrained/imagenet/vgg16.pkl
• Then make sure you have a matching model definition.
• Then do:

from lasagne.layers import set_all_param_values

with open('vgg16.pkl', 'rb') as f:
    params = pickle.load(f)

net.initialize_layers()
set_all_param_values(net.layers_.values(), params['param values'])

I'll try and remember to move this into the documentation at some point.

[xuleiyang]

Hi all, i meet the following error, how to solve? Thanks a lot.

AttributeError: 'dict' object has no attribute 'initialize_layers'

[tdeboissiere]

You can do the following (example with VGG_s model):

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)
output_layer = net['fc8']

import pickle
model = pickle.load(open('vgg_cnn_s.pkl'))
CLASSES = model['synset words']
MEAN_IMAGE = model['mean image']
lasagne.layers.set_all_param_values(output_layer, model['values'])