我们从Python开源项目中，提取了以下41个代码示例，用于说明如何使用lasagne.layers.MaxPool2DLayer()。
def build_fcae(input_var, channels=1): ret = {} ret['input'] = layer = InputLayer(shape=(None, channels, None, None), input_var=input_var) ret['conv1'] = layer = bn(Conv2DLayer(layer, num_filters=128, filter_size=5, pad='full')) ret['pool1'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['conv2'] = layer = bn(Conv2DLayer(layer, num_filters=256, filter_size=3, pad='full')) ret['pool2'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['conv3'] = layer = bn(Conv2DLayer(layer, num_filters=32, filter_size=3, pad='full')) ret['enc'] = layer = GlobalPoolLayer(layer) ret['ph1'] = layer = NonlinearityLayer(layer, nonlinearity=None) ret['ph2'] = layer = NonlinearityLayer(layer, nonlinearity=None) ret['unenc'] = layer = bn(InverseLayer(layer, ret['enc'])) ret['deconv3'] = layer = bn(Conv2DLayer(layer, num_filters=256, filter_size=3)) ret['depool2'] = layer = InverseLayer(layer, ret['pool2']) ret['deconv2'] = layer = bn(Conv2DLayer(layer, num_filters=128, filter_size=3)) ret['depool1'] = layer = InverseLayer(layer, ret['pool1']) ret['output'] = layer = Conv2DLayer(layer, num_filters=1, filter_size=5, nonlinearity=nn.nonlinearities.sigmoid) return ret
def __build_48_net__(self): network = layers.InputLayer((None, 3, 48, 48), input_var=self.__input_var__) network = layers.Conv2DLayer(network,num_filters=64,filter_size=(5,5),stride=1,nonlinearity=relu) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.batch_norm(network) network = layers.Conv2DLayer(network,num_filters=64,filter_size=(5,5),stride=1,nonlinearity=relu) network = layers.batch_norm(network) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.Conv2DLayer(network,num_filters=64,filter_size=(3,3),stride=1,nonlinearity=relu) network = layers.batch_norm(network) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.DenseLayer(network,num_units = 256,nonlinearity = relu) network = layers.DenseLayer(network,num_units = 2, nonlinearity = softmax) return network
def network_classifier(self, input_var): network = {} network['classifier/input'] = InputLayer(shape=(None, 3, 64, 64), input_var=input_var, name='classifier/input') network['classifier/conv1'] = Conv2DLayer(network['classifier/input'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='classifier/conv1') network['classifier/pool1'] = MaxPool2DLayer(network['classifier/conv1'], pool_size=2, stride=2, pad=0, name='classifier/pool1') network['classifier/conv2'] = Conv2DLayer(network['classifier/pool1'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='classifier/conv2') network['classifier/pool2'] = MaxPool2DLayer(network['classifier/conv2'], pool_size=2, stride=2, pad=0, name='classifier/pool2') network['classifier/conv3'] = Conv2DLayer(network['classifier/pool2'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='classifier/conv3') network['classifier/pool3'] = MaxPool2DLayer(network['classifier/conv3'], pool_size=2, stride=2, pad=0, name='classifier/pool3') network['classifier/conv4'] = Conv2DLayer(network['classifier/pool3'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='classifier/conv4') network['classifier/pool4'] = MaxPool2DLayer(network['classifier/conv4'], pool_size=2, stride=2, pad=0, name='classifier/pool4') network['classifier/dense1'] = DenseLayer(network['classifier/pool4'], num_units=64, nonlinearity=rectify, name='classifier/dense1') network['classifier/output'] = DenseLayer(network['classifier/dense1'], num_units=10, nonlinearity=softmax, name='classifier/output') return network
def build_model(self): ''' Build Acoustic Event Net model :return: ''' # A architecture 41 classes nonlin = lasagne.nonlinearities.rectify net = {} net['input'] = InputLayer((None, feat_shape[0], feat_shape[1], feat_shape[2])) # channel, time. frequency # ----------- 1st layer group --------------- net['conv1a'] = ConvLayer(net['input'], num_filters=64, filter_size=(3, 3), stride=1, nonlinearity=nonlin) net['conv1b'] = ConvLayer(net['conv1a'], num_filters=64, filter_size=(3, 3), stride=1, nonlinearity=nonlin) net['pool1'] = MaxPool2DLayer(net['conv1b'], pool_size=(1, 2)) # (time, freq) # ----------- 2nd layer group --------------- net['conv2a'] = ConvLayer(net['pool1'], num_filters=128, filter_size=(3, 3), stride=1, nonlinearity=nonlin) net['conv2b'] = ConvLayer(net['conv2a'], num_filters=128, filter_size=(3, 3), stride=1, nonlinearity=nonlin) net['pool2'] = MaxPool2DLayer(net['conv2b'], pool_size=(2, 2)) # (time, freq) # ----------- fully connected layer group --------------- net['fc5'] = DenseLayer(net['pool2'], num_units=1024, nonlinearity=nonlin) net['fc6'] = DenseLayer(net['fc5'], num_units=1024, nonlinearity=nonlin) net['prob'] = DenseLayer(net['fc6'], num_units=41, nonlinearity=lasagne.nonlinearities.softmax) return net
def CNN(n_epochs): net1 = NeuralNet( layers=[ ('input', layers.InputLayer), ('conv1', layers.Conv2DLayer), # Convolutional layer. Params defined below ('pool1', layers.MaxPool2DLayer), # Like downsampling, for execution speed ('conv2', layers.Conv2DLayer), ('hidden3', layers.DenseLayer), ('output', layers.DenseLayer), ], input_shape=(None, 1, 6, 5), conv1_num_filters=8, conv1_filter_size=(3, 3), conv1_nonlinearity=lasagne.nonlinearities.rectify, pool1_pool_size=(2, 2), conv2_num_filters=12, conv2_filter_size=(1, 1), conv2_nonlinearity=lasagne.nonlinearities.rectify, hidden3_num_units=1000, output_num_units=2, output_nonlinearity=lasagne.nonlinearities.softmax, update_learning_rate=0.0001, update_momentum=0.9, max_epochs=n_epochs, verbose=0, ) return net1
def _invert_MaxPoolingLayer(self, layer, feeder): assert type(layer) in [L.MaxPool2DLayer, L.MaxPool1DLayer] return L.InverseLayer(feeder, layer)
def _invert_layer(self, layer, feeder): layer_type = type(layer) if L.get_output_shape(feeder) != L.get_output_shape(layer): feeder = L.ReshapeLayer(feeder, (-1,)+L.get_output_shape(layer)[1:]) if layer_type is L.InputLayer: return self._invert_InputLayer(layer, feeder) elif layer_type is L.FlattenLayer: return self._invert_FlattenLayer(layer, feeder) elif layer_type is L.DenseLayer: return self._invert_DenseLayer(layer, feeder) elif layer_type is L.Conv2DLayer: return self._invert_Conv2DLayer(layer, feeder) elif layer_type is L.DropoutLayer: return self._invert_DropoutLayer(layer, feeder) elif layer_type in [L.MaxPool2DLayer, L.MaxPool1DLayer]: return self._invert_MaxPoolingLayer(layer, feeder) elif layer_type is L.PadLayer: return self._invert_PadLayer(layer, feeder) elif layer_type is L.SliceLayer: return self._invert_SliceLayer(layer, feeder) elif layer_type is L.LocalResponseNormalization2DLayer: return self._invert_LocalResponseNormalisation2DLayer(layer, feeder) elif layer_type is L.GlobalPoolLayer: return self._invert_GlobalPoolLayer(layer, feeder) else: return self._invert_UnknownLayer(layer, feeder)
def create_network(): l = 1000 pool_size = 5 test_size1 = 13 test_size2 = 7 test_size3 = 5 kernel1 = 128 kernel2 = 128 kernel3 = 128 layer1 = InputLayer(shape=(None, 1, 4, l+1024)) layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1) layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1) layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2) layer2_f = FlattenLayer(layer2_3) layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1)) layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1)) layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1)) layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size)) layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2)) layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2)) layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2)) layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size)) layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3)) layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3)) layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3)) layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size)) layer14_d = DenseLayer(layer14, num_units= 256) layer3_2 = DenseLayer(layer2_f, num_units = 128) layer15 = ConcatLayer([layer14_d,layer3_2]) layer16 = DropoutLayer(layer15,p=0.5) layer17 = DenseLayer(layer16, num_units=256) network = DenseLayer(layer17, num_units= 2, nonlinearity=softmax) return network #random search to initialize the weights
def create_network(): l = 1000 pool_size = 5 test_size1 = 13 test_size2 = 7 test_size3 = 5 kernel1 = 128 kernel2 = 128 kernel3 = 128 layer1 = InputLayer(shape=(None, 1, 4, l+1024)) layer2_1 = SliceLayer(layer1, indices=slice(0, l), axis = -1) layer2_2 = SliceLayer(layer1, indices=slice(l, None), axis = -1) layer2_3 = SliceLayer(layer2_2, indices = slice(0,4), axis = -2) layer2_f = FlattenLayer(layer2_3) layer3 = Conv2DLayer(layer2_1,num_filters = kernel1, filter_size = (4,test_size1)) layer4 = Conv2DLayer(layer3,num_filters = kernel1, filter_size = (1,test_size1)) layer5 = Conv2DLayer(layer4,num_filters = kernel1, filter_size = (1,test_size1)) layer6 = MaxPool2DLayer(layer5, pool_size = (1,pool_size)) layer7 = Conv2DLayer(layer6,num_filters = kernel2, filter_size = (1,test_size2)) layer8 = Conv2DLayer(layer7,num_filters = kernel2, filter_size = (1,test_size2)) layer9 = Conv2DLayer(layer8,num_filters = kernel2, filter_size = (1,test_size2)) layer10 = MaxPool2DLayer(layer9, pool_size = (1,pool_size)) layer11 = Conv2DLayer(layer10,num_filters = kernel3, filter_size = (1,test_size3)) layer12 = Conv2DLayer(layer11,num_filters = kernel3, filter_size = (1,test_size3)) layer13 = Conv2DLayer(layer12,num_filters = kernel3, filter_size = (1,test_size3)) layer14 = MaxPool2DLayer(layer13, pool_size = (1,pool_size)) layer14_d = DenseLayer(layer14, num_units= 256) layer3_2 = DenseLayer(layer2_f, num_units = 128) layer15 = ConcatLayer([layer14_d,layer3_2]) #layer16 = DropoutLayer(layer15,p=0.5) layer17 = DenseLayer(layer15, num_units=256) network = DenseLayer(layer17, num_units= 1, nonlinearity=None) return network #random search to initialize the weights
def build_nets(input_var, channels=1, do_batchnorm=True, z_dim=100): def ns(shape): ret=list(shape) ret[0]=[0] return tuple(ret) ret = {} bn = batch_norm if do_batchnorm else lambda x:x ret['ae_in'] = layer = InputLayer(shape=(None,channels,28,28), input_var=input_var) ret['ae_conv1'] = layer = bn(Conv2DLayer(layer, num_filters=64, filter_size=5)) ret['ae_pool1'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['ae_conv2'] = layer = bn(Conv2DLayer(layer, num_filters=128, filter_size=3)) ret['ae_pool2'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['ae_enc'] = layer = DenseLayer(layer, num_units=z_dim, nonlinearity=nn.nonlinearities.tanh) ret['ae_unenc'] = layer = bn(nn.layers.DenseLayer(layer, num_units = np.product(nn.layers.get_output_shape(ret['ae_pool2'])[1:]))) ret['ae_resh'] = layer = ReshapeLayer(layer, shape=ns(nn.layers.get_output_shape(ret['ae_pool2']))) ret['ae_depool2'] = layer = Upscale2DLayer(layer, scale_factor=2) ret['ae_deconv2'] = layer = bn(Conv2DLayer(layer, num_filters=64, filter_size=3, pad='full')) ret['ae_depool1'] = layer = Upscale2DLayer(layer, scale_factor=2) ret['ae_out'] = Conv2DLayer(layer, num_filters=1, filter_size=5, pad='full', nonlinearity=nn.nonlinearities.sigmoid) ret['disc_in'] = layer = InputLayer(shape=(None,channels,28,28), input_var=input_var) ret['disc_conv1'] = layer = bn(Conv2DLayer(layer, num_filters=64, filter_size=5)) ret['disc_pool1'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['disc_conv2'] = layer = bn(Conv2DLayer(layer, num_filters=128, filter_size=3)) ret['disc_pool2'] = layer = MaxPool2DLayer(layer, pool_size=2) ret['disc_hid'] = layer = bn(DenseLayer(layer, num_units=100)) ret['disc_out'] = DenseLayer(layer, num_units=1, nonlinearity=nn.nonlinearities.sigmoid) return ret
def __init__(self, x, y, args): self.params_theta = [] self.params_lambda = [] self.params_weight = [] if args.dataset == 'mnist': input_size = (None, 1, 28, 28) elif args.dataset == 'cifar10': input_size = (None, 3, 32, 32) else: raise AssertionError layers = [ll.InputLayer(input_size)] self.penalty = theano.shared(np.array(0.)) #conv1 layers.append(Conv2DLayerWithReg(args, layers[-1], 20, 5)) self.add_params_to_self(args, layers[-1]) layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2)) #conv1 layers.append(Conv2DLayerWithReg(args, layers[-1], 50, 5)) self.add_params_to_self(args, layers[-1]) layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2)) #fc1 layers.append(DenseLayerWithReg(args, layers[-1], num_units=500)) self.add_params_to_self(args, layers[-1]) #softmax layers.append(DenseLayerWithReg(args, layers[-1], num_units=10, nonlinearity=nonlinearities.softmax)) self.add_params_to_self(args, layers[-1]) self.layers = layers self.y = ll.get_output(layers[-1], x, deterministic=False) self.prediction = T.argmax(self.y, axis=1) # self.penalty = penalty if penalty != 0. else T.constant(0.) print(self.params_lambda) # time.sleep(20) # cost function self.loss = T.mean(categorical_crossentropy(self.y, y)) self.lossWithPenalty = T.add(self.loss, self.penalty) print "loss and losswithpenalty", type(self.loss), type(self.lossWithPenalty)
def new(self, image_dim, final_vec_dim): input_dim = (None,) + image_dim # Create initial nets, one per final vector element self.nets = [] self.input_layers = [] for i in range(final_vec_dim): l_input = layers.InputLayer(shape=input_dim) l_conv0 = layers.Conv2DLayer(l_input, 64, (5,5)) l_max0 = layers.MaxPool2DLayer(l_conv0, (5,5), stride=3) l_conv1 = layers.Conv2DLayer(l_max0, 32, (5,5)) l_max1 = layers.MaxPool2DLayer(l_conv1, (5,5), stride=2) l_conv2 = layers.Conv2DLayer(l_conv1, 32, (3,3)) l_pool = layers.MaxPool2DLayer(l_conv2, (3,3), stride=1) l_1d1 = layers.DenseLayer(l_pool, 24) l_1d2 = layers.DenseLayer(l_1d1, 8) l_1d3 = layers.DenseLayer(l_1d2, 1) self.nets.append(l_1d3) self.input_layers.append(l_input) # Train the neural net # @param {Matrix} trainset X # @param {Vector} trainset y # @param {Matrix} validation set X # @param {Vector} validation set y # @param {int} batch size # @param {int} number of epochs to run # @param {list[double]} learning rates (non-negative, non-zero) # @param {str} path to save model
def __build_12_net__(self): network = layers.InputLayer((None, 3, 12, 12), input_var=self.__input_var__) network = layers.dropout(network, p=0.1) network = layers.Conv2DLayer(network,num_filters=16,filter_size=(3,3),stride=1,nonlinearity=relu) network = layers.batch_norm(network) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.DropoutLayer(network,p=0.3) network = layers.DenseLayer(network,num_units = 16,nonlinearity = relu) network = layers.batch_norm(network) network = layers.DropoutLayer(network,p=0.3) network = layers.DenseLayer(network,num_units = 2, nonlinearity = softmax) return network
def __build_24_net__(self): network = layers.InputLayer((None, 3, 24, 24), input_var=self.__input_var__) network = layers.dropout(network, p=0.1) network = layers.Conv2DLayer(network,num_filters=64,filter_size=(5,5),stride=1,nonlinearity=relu) network = layers.batch_norm(network) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.DropoutLayer(network,p=0.5) network = layers.batch_norm(network) network = layers.DenseLayer(network,num_units = 64,nonlinearity = relu) network = layers.DropoutLayer(network,p=0.5) network = layers.DenseLayer(network,num_units = 2, nonlinearity = softmax) return network
def __build_12_calib_net__(self): network = layers.InputLayer((None, 3, 12, 12), input_var=self.__input_var__) network = layers.Conv2DLayer(network,num_filters=16,filter_size=(3,3),stride=1,nonlinearity=relu) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.DenseLayer(network,num_units = 128,nonlinearity = relu) network = layers.DenseLayer(network,num_units = 45, nonlinearity = softmax) return network
def __build_24_calib_net__(self): network = layers.InputLayer((None, 3, 24, 24), input_var=self.__input_var__) network = layers.Conv2DLayer(network,num_filters=32,filter_size=(5,5),stride=1,nonlinearity=relu) network = layers.MaxPool2DLayer(network, pool_size = (3,3),stride = 2) network = layers.DenseLayer(network,num_units = 64,nonlinearity = relu) network = layers.DenseLayer(network,num_units = 45, nonlinearity = softmax) return network
def build_fcn_segmenter(input_var, shape, version=2): ret = {} if version == 2: ret['input'] = la = InputLayer(shape, input_var) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=8, filter_size=7)) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=16, filter_size=3)) ret['pool%d'%len(ret)] = la = MaxPool2DLayer(la, pool_size=2) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=32, filter_size=3)) ret['pool%d'%len(ret)] = la = MaxPool2DLayer(la, pool_size=2) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=64, filter_size=3)) ret['pool%d'%len(ret)] = la = MaxPool2DLayer(la, pool_size=2) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=64, filter_size=3)) ret['dec%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=64, filter_size=3, pad='full')) ret['ups%d'%len(ret)] = la = Upscale2DLayer(la, scale_factor=2) ret['dec%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=64, filter_size=3, pad='full')) ret['ups%d'%len(ret)] = la = Upscale2DLayer(la, scale_factor=2) ret['dec%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=32, filter_size=7, pad='full')) ret['ups%d'%len(ret)] = la = Upscale2DLayer(la, scale_factor=2) ret['dec%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=16, filter_size=3, pad='full')) ret['conv%d'%len(ret)] = la = bn(Conv2DLayer(la, num_filters=8, filter_size=7)) ret['output'] = la = Conv2DLayer(la, num_filters=1, filter_size=7, pad='full', nonlinearity=nn.nonlinearities.sigmoid) return ret, nn.layers.get_output(ret['output']), \ nn.layers.get_output(ret['output'], deterministic=True)
def network_discriminator(self, features): network = {} network['discriminator/conv2'] = Conv2DLayer(features, num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='discriminator/conv2') network['discriminator/pool2'] = MaxPool2DLayer(network['discriminator/conv2'], pool_size=2, stride=2, pad=0, name='discriminator/pool2') network['discriminator/conv3'] = Conv2DLayer(network['discriminator/pool2'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='discriminator/conv3') network['discriminator/pool3'] = MaxPool2DLayer(network['discriminator/conv3'], pool_size=2, stride=2, pad=0, name='discriminator/pool3') network['discriminator/conv4'] = Conv2DLayer(network['discriminator/pool3'], num_filters=32, filter_size=3, stride=1, pad='valid', nonlinearity=rectify, name='discriminator/conv4') network['discriminator/pool4'] = MaxPool2DLayer(network['discriminator/conv4'], pool_size=2, stride=2, pad=0, name='discriminator/pool4') network['discriminator/dense1'] = DenseLayer(network['discriminator/pool4'], num_units=64, nonlinearity=rectify, name='discriminator/dense1') network['discriminator/output'] = DenseLayer(network['discriminator/dense1'], num_units=2, nonlinearity=softmax, name='discriminator/output') return network
def build_model(self, img_batch, pose_code): img_size = self.options['img_size'] pose_code_size = self.options['pose_code_size'] filter_size = self.options['filter_size'] batch_size = img_batch.shape[0] # image encoding l_in = InputLayer(shape = [None, img_size[0], img_size[1], img_size[2]], input_var=img_batch) l_in_dimshuffle = DimshuffleLayer(l_in, (0,3,1,2)) l_conv1_1 = Conv2DLayer(l_in_dimshuffle, num_filters=64, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_conv1_2 = Conv2DLayer(l_conv1_1, num_filters=64, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_pool1 = MaxPool2DLayer(l_conv1_2, pool_size=(2,2)) # pose encoding l_in_2 = InputLayer(shape=(None, pose_code_size), input_var=pose_code) l_pose_1 = DenseLayer(l_in_2, num_units=512, W=HeNormal(),nonlinearity=rectify) l_pose_2 = DenseLayer(l_pose_1, num_units=pose_code_size*l_pool1.output_shape[2]*l_pool1.output_shape[3], W=HeNormal(),nonlinearity=rectify) l_pose_reshape = ReshapeLayer(l_pose_2, shape=(batch_size, pose_code_size, l_pool1.output_shape[2], l_pool1.output_shape[3])) # deeper fusion l_concat = ConcatLayer([l_pool1, l_pose_reshape], axis=1) l_pose_conv_1 = Conv2DLayer(l_concat, num_filters=128, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_pose_conv_2 = Conv2DLayer(l_pose_conv_1, num_filters=128, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_pool2 = MaxPool2DLayer(l_pose_conv_2, pool_size=(2,2)) l_conv_3 = Conv2DLayer(l_pool2, num_filters=128, filter_size=(1,1), W=HeNormal()) l_unpool1 = Unpool2DLayer(l_conv_3, ds = (2,2)) # image decoding l_deconv_conv1_1 = Conv2DLayer(l_unpool1, num_filters=128, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_deconv_conv1_2 = Conv2DLayer(l_deconv_conv1_1, num_filters=64, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_unpool2 = Unpool2DLayer(l_deconv_conv1_2, ds = (2,2)) l_deconv_conv2_1 = Conv2DLayer(l_unpool2, num_filters=64, filter_size=filter_size, nonlinearity=None, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_deconv_conv2_2 = Conv2DLayer(l_deconv_conv2_1, num_filters=img_size[2], filter_size=filter_size, nonlinearity=None, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) return l_deconv_conv2_2, l_pose_reshape
def build_model(self, img_batch, img_batch_gen): img_size = self.options['img_size'] pose_code_size = self.options['pose_code_size'] filter_size = self.options['filter_size'] batch_size = img_batch.shape[0] # image encoding l_in_1 = InputLayer(shape = [None, img_size[0], img_size[1], img_size[2]], input_var=img_batch) l_in_1_dimshuffle = DimshuffleLayer(l_in_1, (0,3,1,2)) l_in_2 = InputLayer(shape = [None, img_size[0], img_size[1], img_size[2]], input_var=img_batch_gen) l_in_2_dimshuffle = DimshuffleLayer(l_in_2, (0,3,1,2)) l_in_concat = ConcatLayer([l_in_1_dimshuffle, l_in_2_dimshuffle], axis=1) l_conv1_1 = Conv2DLayer(l_in_concat, num_filters=64, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_conv1_2 = Conv2DLayer(l_conv1_1, num_filters=64, filter_size=filter_size, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_pool1 = MaxPool2DLayer(l_conv1_2, pool_size=(2,2)) l_conv2_1 = Conv2DLayer(l_pool1, num_filters=128, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_conv2_2 = Conv2DLayer(l_conv2_1, num_filters=128, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_pool2 = MaxPool2DLayer(l_conv2_2, pool_size=(2,2)) l_conv_3 = Conv2DLayer(l_pool2, num_filters=128, filter_size=(1,1), W=HeNormal()) l_unpool1 = Unpool2DLayer(l_conv_3, ds = (2,2)) # image decoding l_deconv_conv1_1 = Conv2DLayer(l_unpool1, num_filters=128, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_deconv_conv1_2 = Conv2DLayer(l_deconv_conv1_1, num_filters=64, filter_size=filter_size, nonlinearity=rectify,W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_unpool2 = Unpool2DLayer(l_deconv_conv1_2, ds = (2,2)) l_deconv_conv2_1 = Conv2DLayer(l_unpool2, num_filters=64, filter_size=filter_size, nonlinearity=None, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) l_deconv_conv2_2 = Conv2DLayer(l_deconv_conv2_1, num_filters=img_size[2], filter_size=filter_size, nonlinearity=None, W=HeNormal(), pad=(filter_size[0]//2, filter_size[1]//2)) return l_deconv_conv2_2
def create_model(input_var, input_shape, options): conv_num_filters1 = 100 conv_num_filters2 = 150 conv_num_filters3 = 200 filter_size1 = 5 filter_size2 = 5 filter_size3 = 3 pool_size = 2 encode_size = options['BOTTLENECK'] dense_mid_size = options['DENSE'] pad_in = 'valid' pad_out = 'full' scaled_tanh = create_scaled_tanh() input = InputLayer(shape=input_shape, input_var=input_var, name='input') conv2d1 = Conv2DLayer(input, num_filters=conv_num_filters1, filter_size=filter_size1, pad=pad_in, name='conv2d1', nonlinearity=scaled_tanh) maxpool2d2 = MaxPool2DLayer(conv2d1, pool_size=pool_size, name='maxpool2d2') conv2d3 = Conv2DLayer(maxpool2d2, num_filters=conv_num_filters2, filter_size=filter_size2, pad=pad_in, name='conv2d3', nonlinearity=scaled_tanh) maxpool2d4 = MaxPool2DLayer(conv2d3, pool_size=pool_size, name='maxpool2d4', pad=(1,0)) conv2d5 = Conv2DLayer(maxpool2d4, num_filters=conv_num_filters3, filter_size=filter_size3, pad=pad_in, name='conv2d5', nonlinearity=scaled_tanh) reshape6 = ReshapeLayer(conv2d5, shape=([0], -1), name='reshape6') # 3000 reshape6_output = reshape6.output_shape[1] dense7 = DenseLayer(reshape6, num_units=dense_mid_size, name='dense7', nonlinearity=scaled_tanh) bottleneck = DenseLayer(dense7, num_units=encode_size, name='bottleneck', nonlinearity=linear) # print_network(bottleneck) dense8 = DenseLayer(bottleneck, num_units=dense_mid_size, W=bottleneck.W.T, name='dense8', nonlinearity=linear) dense9 = DenseLayer(dense8, num_units=reshape6_output, W=dense7.W.T, nonlinearity=scaled_tanh, name='dense9') reshape10 = ReshapeLayer(dense9, shape=([0], conv_num_filters3, 3, 5), name='reshape10') # 32 x 4 x 7 deconv2d11 = Deconv2DLayer(reshape10, conv2d5.input_shape[1], conv2d5.filter_size, stride=conv2d5.stride, W=conv2d5.W, flip_filters=not conv2d5.flip_filters, name='deconv2d11', nonlinearity=scaled_tanh) upscale2d12 = Upscale2DLayer(deconv2d11, scale_factor=pool_size, name='upscale2d12') deconv2d13 = Deconv2DLayer(upscale2d12, conv2d3.input_shape[1], conv2d3.filter_size, stride=conv2d3.stride, W=conv2d3.W, flip_filters=not conv2d3.flip_filters, name='deconv2d13', nonlinearity=scaled_tanh) upscale2d14 = Upscale2DLayer(deconv2d13, scale_factor=pool_size, name='upscale2d14') deconv2d15 = Deconv2DLayer(upscale2d14, conv2d1.input_shape[1], conv2d1.filter_size, stride=conv2d1.stride, crop=(1, 0), W=conv2d1.W, flip_filters=not conv2d1.flip_filters, name='deconv2d14', nonlinearity=scaled_tanh) reshape16 = ReshapeLayer(deconv2d15, ([0], -1), name='reshape16') print_network(reshape16) return reshape16
def create_model(incoming, options): conv_num_filters1 = 100 conv_num_filters2 = 150 conv_num_filters3 = 200 filter_size1 = 5 filter_size2 = 5 filter_size3 = 3 pool_size = 2 encode_size = options['BOTTLENECK'] dense_mid_size = options['DENSE'] pad_in = 'valid' pad_out = 'full' scaled_tanh = create_scaled_tanh() conv2d1 = Conv2DLayer(incoming, num_filters=conv_num_filters1, filter_size=filter_size1, pad=pad_in, name='conv2d1', nonlinearity=scaled_tanh) maxpool2d3 = MaxPool2DLayer(conv2d1, pool_size=pool_size, name='maxpool2d3') bn2 = BatchNormLayer(maxpool2d3, name='batchnorm2') conv2d4 = Conv2DLayer(bn2, num_filters=conv_num_filters2, filter_size=filter_size2, pad=pad_in, name='conv2d4', nonlinearity=scaled_tanh) maxpool2d6 = MaxPool2DLayer(conv2d4, pool_size=pool_size, name='maxpool2d6', pad=(1,0)) bn3 = BatchNormLayer(maxpool2d6, name='batchnorm3') conv2d7 = Conv2DLayer(bn3, num_filters=conv_num_filters3, filter_size=filter_size3, pad=pad_in, name='conv2d7', nonlinearity=scaled_tanh) reshape9 = ReshapeLayer(conv2d7, shape=([0], -1), name='reshape9') # 3000 reshape9_output = reshape9.output_shape[1] bn8 = BatchNormLayer(reshape9, name='batchnorm8') dense10 = DenseLayer(bn8, num_units=dense_mid_size, name='dense10', nonlinearity=scaled_tanh) bn11 = BatchNormLayer(dense10, name='batchnorm11') bottleneck = DenseLayer(bn11, num_units=encode_size, name='bottleneck', nonlinearity=linear) # print_network(bottleneck) dense12 = DenseLayer(bottleneck, num_units=dense_mid_size, W=bottleneck.W.T, name='dense12', nonlinearity=linear) dense13 = DenseLayer(dense12, num_units=reshape9_output, W=dense10.W.T, nonlinearity=scaled_tanh, name='dense13') reshape14 = ReshapeLayer(dense13, shape=([0], conv_num_filters3, 3, 5), name='reshape14') # 32 x 4 x 7 deconv2d19 = Deconv2DLayer(reshape14, conv2d7.input_shape[1], conv2d7.filter_size, stride=conv2d7.stride, W=conv2d7.W, flip_filters=not conv2d7.flip_filters, name='deconv2d19', nonlinearity=scaled_tanh) upscale2d16 = Upscale2DLayer(deconv2d19, scale_factor=pool_size, name='upscale2d16') deconv2d17 = Deconv2DLayer(upscale2d16, conv2d4.input_shape[1], conv2d4.filter_size, stride=conv2d4.stride, W=conv2d4.W, flip_filters=not conv2d4.flip_filters, name='deconv2d17', nonlinearity=scaled_tanh) upscale2d18 = Upscale2DLayer(deconv2d17, scale_factor=pool_size, name='upscale2d18') deconv2d19 = Deconv2DLayer(upscale2d18, conv2d1.input_shape[1], conv2d1.filter_size, stride=conv2d1.stride, crop=(1, 0), W=conv2d1.W, flip_filters=not conv2d1.flip_filters, name='deconv2d14', nonlinearity=scaled_tanh) reshape20 = ReshapeLayer(deconv2d19, ([0], -1), name='reshape20') return reshape20, bottleneck
def create_model(incoming, options): conv_num_filters1 = 100 conv_num_filters2 = 150 conv_num_filters3 = 200 filter_size1 = 5 filter_size2 = 5 filter_size3 = 3 pool_size = 2 encode_size = options['BOTTLENECK'] dense_mid_size = options['DENSE'] pad_in = 'valid' pad_out = 'full' scaled_tanh = create_scaled_tanh() conv2d1 = Conv2DLayer(incoming, num_filters=conv_num_filters1, filter_size=filter_size1, pad=pad_in, name='conv2d1', nonlinearity=scaled_tanh) maxpool2d2 = MaxPool2DLayer(conv2d1, pool_size=pool_size, name='maxpool2d2') conv2d3 = Conv2DLayer(maxpool2d2, num_filters=conv_num_filters2, filter_size=filter_size2, pad=pad_in, name='conv2d3', nonlinearity=scaled_tanh) maxpool2d4 = MaxPool2DLayer(conv2d3, pool_size=pool_size, name='maxpool2d4', pad=(1,0)) conv2d5 = Conv2DLayer(maxpool2d4, num_filters=conv_num_filters3, filter_size=filter_size3, pad=pad_in, name='conv2d5', nonlinearity=scaled_tanh) reshape6 = ReshapeLayer(conv2d5, shape=([0], -1), name='reshape6') # 3000 reshape6_output = reshape6.output_shape[1] dense7 = DenseLayer(reshape6, num_units=dense_mid_size, name='dense7', nonlinearity=scaled_tanh) bottleneck = DenseLayer(dense7, num_units=encode_size, name='bottleneck', nonlinearity=linear) # print_network(bottleneck) dense8 = DenseLayer(bottleneck, num_units=dense_mid_size, W=bottleneck.W.T, name='dense8', nonlinearity=linear) dense9 = DenseLayer(dense8, num_units=reshape6_output, W=dense7.W.T, nonlinearity=scaled_tanh, name='dense9') reshape10 = ReshapeLayer(dense9, shape=([0], conv_num_filters3, 3, 5), name='reshape10') # 32 x 4 x 7 deconv2d11 = Deconv2DLayer(reshape10, conv2d5.input_shape[1], conv2d5.filter_size, stride=conv2d5.stride, W=conv2d5.W, flip_filters=not conv2d5.flip_filters, name='deconv2d11', nonlinearity=scaled_tanh) upscale2d12 = Upscale2DLayer(deconv2d11, scale_factor=pool_size, name='upscale2d12') deconv2d13 = Deconv2DLayer(upscale2d12, conv2d3.input_shape[1], conv2d3.filter_size, stride=conv2d3.stride, W=conv2d3.W, flip_filters=not conv2d3.flip_filters, name='deconv2d13', nonlinearity=scaled_tanh) upscale2d14 = Upscale2DLayer(deconv2d13, scale_factor=pool_size, name='upscale2d14') deconv2d15 = Deconv2DLayer(upscale2d14, conv2d1.input_shape[1], conv2d1.filter_size, stride=conv2d1.stride, crop=(1, 0), W=conv2d1.W, flip_filters=not conv2d1.flip_filters, name='deconv2d14', nonlinearity=scaled_tanh) reshape16 = ReshapeLayer(deconv2d15, ([0], -1), name='reshape16') return reshape16, bottleneck
def build_cnn(self, input_var=None): # Building the network layer_in = InputLayer(shape=(None, 3, 32, 32), input_var=input_var) # Conv1 # [NOTE]: normal vs. truncated normal? # [NOTE]: conv in lasagne is not same as it in TensorFlow. layer = ConvLayer(layer_in, num_filters=64, filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=lasagne.init.HeNormal(), flip_filters=False) # Pool1 layer = MaxPool2DLayer(layer, pool_size=(3, 3), stride=(2, 2)) # Norm1 layer = LocalResponseNormalization2DLayer(layer, alpha=0.001 / 9.0, k=1.0, beta=0.75) # Conv2 layer = ConvLayer(layer, num_filters=64, filter_size=(5, 5), stride=(1, 1), nonlinearity=rectify, pad='same', W=lasagne.init.HeNormal(), flip_filters=False) # Norm2 # [NOTE]: n must be odd, but n in Chang's code is 4? layer = LocalResponseNormalization2DLayer(layer, alpha=0.001 / 9.0, k=1.0, beta=0.75) # Pool2 layer = MaxPool2DLayer(layer, pool_size=(3, 3), stride=(2, 2)) # Reshape layer = lasagne.layers.ReshapeLayer(layer, shape=([0], -1)) # Dense3 layer = DenseLayer(layer, num_units=384, W=lasagne.init.HeNormal(), b=lasagne.init.Constant(0.1)) # Dense4 layer = DenseLayer(layer, num_units=192, W=lasagne.init.Normal(std=0.04), b=lasagne.init.Constant(0.1)) # Softmax layer = DenseLayer(layer, num_units=self.output_size, W=lasagne.init.Normal(std=1. / 192.0), nonlinearity=softmax) return layer
def gen_layers(self): """Construct the layers""" # Init <TODO> pad_in = 'valid' self.layers = [] # input layer l_input = (InputLayer, {'shape': (None, self.X_in.shape[1], self.X_in.shape[2], self.X_in.shape[3])}) self.layers.append(l_input) # Conv and pool layers rows, cols = self.X_in.shape[2:] for i in range(len(self.kernel_size)): # conv l_conv = (Conv2DLayer, {'num_filters': self.kernel_num[i], 'filter_size': self.kernel_size[i], 'nonlinearity': lasagne.nonlinearities.rectify, 'W': lasagne.init.GlorotUniform(), 'pad': pad_in}) self.layers.append(l_conv) rows = rows - self.kernel_size[i] + 1 cols = cols - self.kernel_size[i] + 1 # pool if self.pool_flag[i]: l_pool = (MaxPool2DLayer, {'pool_size': self.pool_size}) self.layers.append(l_pool) rows = rows // 2 cols = cols // 2 # dropout if not self.dropflag: self.droprate = 0 l_drop = (DropoutLayer, {'p': self.droprate}) # self.layers.append(l_drop) # full connected layer num_fc = rows * cols * self.kernel_num[-1] l_fc = (DenseLayer, {'num_units': num_fc, 'nonlinearity': lasagne.nonlinearities.rectify, 'W': lasagne.init.GlorotUniform(), 'b': lasagne.init.Constant(0.)} ) self.layers.append(l_fc) # dense if not self.fc_nodes is None: for i in range(len(self.fc_nodes)): self.layers.append(l_drop) l_dense = (DenseLayer, {'num_units': self.fc_nodes[i]}) self.layers.append(l_dense) # output layer self.layers.append(l_drop) l_out = (DenseLayer, {'name': 'output', 'num_units': self.numclass, 'nonlinearity': lasagne.nonlinearities.softmax}) self.layers.append(l_out)
def buildModel(mtype=1): print "BUILDING MODEL TYPE", mtype, "..." #default settings (Model 1) filters = 64 first_stride = 2 last_filter_multiplier = 16 #specific model type settings (see working notes for details) if mtype == 2: first_stride = 1 elif mtype == 3: filters = 32 last_filter_multiplier = 8 #input layer net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0])) #conv layers net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) if mtype == 2: net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net) #dense layers net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.DropoutLayer(net, DROPOUT) net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.DropoutLayer(net, DROPOUT) #Classification Layer if MULTI_LABEL: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1)) else: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1)) print "...DONE!" #model stats print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS" print "MODEL HAS", l.count_params(net), "PARAMS" return net
def buildModel(mtype=1): print "BUILDING MODEL TYPE", mtype, "..." #default settings (Model 1) filters = 64 first_stride = 2 last_filter_multiplier = 16 #specific model type settings (see working notes for details) if mtype == 2: first_stride = 1 elif mtype == 3: filters = 32 last_filter_multiplier = 8 #input layer net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0])) #conv layers net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) if mtype == 2: net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net) #dense layers net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) #Classification Layer if MULTI_LABEL: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1)) else: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1)) print "...DONE!" #model stats print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS" print "MODEL HAS", l.count_params(net), "PARAMS" return net
def network_discriminator(self, input, network_weights=None): layers = [] if isinstance(input, lasagne.layers.Layer): layers.append(input) # First convolution layers.append(conv_layer(input, n_filters=self.n_filters, stride=1, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) else: # Input layer layers.append(InputLayer(shape=(None, 3, self.input_size, self.input_size), input_var=input, name='discriminator/encoder/input')) # First convolution layers.append(conv_layer(layers[-1], n_filters=self.n_filters, stride=1, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) # Convolutional blocks (encoder)self.n_filters*i_block n_blocks = int(np.log2(self.input_size/8)) + 1 # end up with 8x8 output for i_block in range(1, n_blocks+1): layers.append(conv_layer(layers[-1], n_filters=self.n_filters*i_block, stride=1, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) layers.append(conv_layer(layers[-1], n_filters=self.n_filters*i_block, stride=1, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) if i_block != n_blocks: # layers.append(conv_layer(layers[-1], n_filters=self.n_filters*(i_block+1), stride=2, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) layers.append(MaxPool2DLayer(layers[-1], pool_size=2, stride=2, name='discriminator/encoder/pooling%d' % len(layers))) # else: # layers.append(conv_layer(layers[-1], n_filters=self.n_filters*(i_block), stride=1, name='discriminator/encoder/conv%d' % len(layers), network_weights=network_weights)) # Dense layers (linear outputs) layers.append(dense_layer(layers[-1], n_units=self.hidden_size, name='discriminator/encoder/dense%d' % len(layers), network_weights=network_weights)) # Dense layer up (from h to n*8*8) layers.append(dense_layer(layers[-1], n_units=(8 * 8 * self.n_filters), name='discriminator/decoder/dense%d' % len(layers), network_weights=network_weights)) layers.append(ReshapeLayer(layers[-1], (-1, self.n_filters, 8, 8), name='discriminator/decoder/reshape%d' % len(layers))) # Convolutional blocks (decoder) for i_block in range(1, n_blocks+1): layers.append(conv_layer(layers[-1], n_filters=self.n_filters, stride=1, name='discriminator/decoder/conv%d' % len(layers), network_weights=network_weights)) layers.append(conv_layer(layers[-1], n_filters=self.n_filters, stride=1, name='discriminator/decoder/conv%d' % len(layers), network_weights=network_weights)) if i_block != n_blocks: layers.append(Upscale2DLayer(layers[-1], scale_factor=2, name='discriminator/decoder/upsample%d' % len(layers))) # Final layer (make sure input images are in the range [-1, 1] layers.append(conv_layer(layers[-1], n_filters=3, stride=1, name='discriminator/decoder/output', network_weights=network_weights, nonlinearity=sigmoid)) # Network in dictionary form network = {layer.name: layer for layer in layers} return network
def main(): ################ # LOAD DATASET # ################ dataset = './data/ubiquitous_aug.hkl' kfd = './data/ubiquitous_kfold.hkl' print('Loading dataset {}...'.format(dataset)) X, y = hkl.load(open(dataset, 'r')) X = X.reshape(-1, 4, 1, 400).astype(floatX) y = y.astype('int32') print('X shape: {}, y shape: {}'.format(X.shape, y.shape)) kf = hkl.load(open(kfd, 'r')) kfold = [(train, test) for train, test in kf] (train, test) = kfold[0] print('train_set size: {}, test_set size: {}'.format(len(train), len(test))) # shuffle +/- labels in minibatch print('shuffling train_set and test_set') shuffle(train) shuffle(test) X_train = X[train] X_test = X[test] y_train = y[train] y_test = y[test] print('data prepared!') layers = [ (InputLayer, {'shape': (None, 4, 1, 400)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 4)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 3)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 3)}), (MaxPool2DLayer, {'pool_size': (1, 2)}), (Conv2DLayer, {'num_filters': 32, 'filter_size': (1, 2)}), (Conv2DLayer, {'num_filters': 32, 'filter_size': (1, 2)}), (Conv2DLayer, {'num_filters': 32, 'filter_size': (1, 2)}), (MaxPool2DLayer, {'pool_size': (1, 2)}), (DenseLayer, {'num_units': 64}), (DropoutLayer, {}), (DenseLayer, {'num_units': 64}), (DenseLayer, {'num_units': 2, 'nonlinearity': softmax})] net = NeuralNet( layers=layers, max_epochs=100, update=adam, update_learning_rate=1e-4, train_split=TrainSplit(eval_size=0.1), on_epoch_finished=[ AdjustVariable(1e-4, target=0, half_life=20)], verbose=2) net.fit(X_train, y_train) plot_loss(net)
def main(resume=None): l = 300 dataset = './data/ubiquitous_train.hkl' print('Loading dataset {}...'.format(dataset)) X_train, y_train = hkl.load(dataset) X_train = X_train.reshape(-1, 4, 1, l).astype(floatX) y_train = np.array(y_train, dtype='int32') indice = np.arange(X_train.shape[0]) np.random.shuffle(indice) X_train = X_train[indice] y_train = y_train[indice] print('X_train shape: {}, y_train shape: {}'.format(X_train.shape, y_train.shape)) layers = [ (InputLayer, {'shape': (None, 4, 1, l)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 4)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 3)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 3)}), (MaxPool2DLayer, {'pool_size': (1, 2)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 2)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 2)}), (Conv2DLayer, {'num_filters': 64, 'filter_size': (1, 2)}), (MaxPool2DLayer, {'pool_size': (1, 2)}), (DenseLayer, {'num_units': 64}), (DropoutLayer, {}), (DenseLayer, {'num_units': 64}), (DenseLayer, {'num_units': 2, 'nonlinearity': softmax})] lr = theano.shared(np.float32(1e-4)) net = NeuralNet( layers=layers, max_epochs=100, update=adam, update_learning_rate=lr, train_split=TrainSplit(eval_size=0.1), on_epoch_finished=[ AdjustVariable(lr, target=1e-8, half_life=20)], verbose=4) if resume != None: net.load_params_from(resume) net.fit(X_train, y_train) net.save_params_to('./models/net_params.pkl')
def __init__(self, args): self.args = args rng = np.random.RandomState(self.args.seed) # fixed random seeds theano_rng = MRG_RandomStreams(rng.randint(2 ** 15)) lasagne.random.set_rng(np.random.RandomState(rng.randint(2 ** 15))) data_rng = np.random.RandomState(self.args.seed_data) ''' specify pre-trained generator E ''' self.enc_layers = [LL.InputLayer(shape=(None, 3, 32, 32), input_var=None)] enc_layer_conv1 = dnn.Conv2DDNNLayer(self.enc_layers[-1], 64, (5,5), pad=0, stride=1, W=Normal(0.01), nonlinearity=nn.relu) self.enc_layers.append(enc_layer_conv1) enc_layer_pool1 = LL.MaxPool2DLayer(self.enc_layers[-1], pool_size=(2, 2)) self.enc_layers.append(enc_layer_pool1) enc_layer_conv2 = dnn.Conv2DDNNLayer(self.enc_layers[-1], 128, (5,5), pad=0, stride=1, W=Normal(0.01), nonlinearity=nn.relu) self.enc_layers.append(enc_layer_conv2) enc_layer_pool2 = LL.MaxPool2DLayer(self.enc_layers[-1], pool_size=(2, 2)) self.enc_layers.append(enc_layer_pool2) self.enc_layer_fc3 = LL.DenseLayer(self.enc_layers[-1], num_units=256, nonlinearity=T.nnet.relu) self.enc_layers.append(self.enc_layer_fc3) self.enc_layer_fc4 = LL.DenseLayer(self.enc_layers[-1], num_units=10, nonlinearity=T.nnet.softmax) self.enc_layers.append(self.enc_layer_fc4) ''' load pretrained weights for encoder ''' weights_toload = np.load('pretrained/encoder.npz') weights_list_toload = [weights_toload['arr_{}'.format(k)] for k in range(len(weights_toload.files))] LL.set_all_param_values(self.enc_layers[-1], weights_list_toload) ''' input tensor variables ''' #self.G_weights #self.D_weights self.dummy_input = T.scalar() self.G_layers = [] self.z = theano_rng.uniform(size=(self.args.batch_size, self.args.z0dim)) self.x = T.tensor4() self.meanx = T.tensor3() self.Gen_x = T.tensor4() self.D_layers = [] self.D_layer_adv = [] self.D_layer_z_recon = [] self.gen_lr = T.scalar() # learning rate self.disc_lr = T.scalar() # learning rate self.y = T.ivector() self.y_1hot = T.matrix() self.Gen_x_list = [] self.y_recon_list = [] self.mincost = T.scalar() #self.enc_layer_fc3 = self.get_enc_layer_fc3() self.real_fc3 = LL.get_output(self.enc_layer_fc3, self.x, deterministic=True)
def build_network(): conv_defs = { 'W': lasagne.init.HeNormal('relu'), 'b': lasagne.init.Constant(0.0), 'filter_size': (3, 3), 'stride': (1, 1), 'nonlinearity': lasagne.nonlinearities.LeakyRectify(0.1) } nin_defs = { 'W': lasagne.init.HeNormal('relu'), 'b': lasagne.init.Constant(0.0), 'nonlinearity': lasagne.nonlinearities.LeakyRectify(0.1) } dense_defs = { 'W': lasagne.init.HeNormal(1.0), 'b': lasagne.init.Constant(0.0), 'nonlinearity': lasagne.nonlinearities.softmax } wn_defs = { 'momentum': .999 } net = InputLayer ( name='input', shape=(None, 3, 32, 32)) net = GaussianNoiseLayer(net, name='noise', sigma=.15) net = WN(Conv2DLayer (net, name='conv1a', num_filters=128, pad='same', **conv_defs), **wn_defs) net = WN(Conv2DLayer (net, name='conv1b', num_filters=128, pad='same', **conv_defs), **wn_defs) net = WN(Conv2DLayer (net, name='conv1c', num_filters=128, pad='same', **conv_defs), **wn_defs) net = MaxPool2DLayer (net, name='pool1', pool_size=(2, 2)) net = DropoutLayer (net, name='drop1', p=.5) net = WN(Conv2DLayer (net, name='conv2a', num_filters=256, pad='same', **conv_defs), **wn_defs) net = WN(Conv2DLayer (net, name='conv2b', num_filters=256, pad='same', **conv_defs), **wn_defs) net = WN(Conv2DLayer (net, name='conv2c', num_filters=256, pad='same', **conv_defs), **wn_defs) net = MaxPool2DLayer (net, name='pool2', pool_size=(2, 2)) net = DropoutLayer (net, name='drop2', p=.5) net = WN(Conv2DLayer (net, name='conv3a', num_filters=512, pad=0, **conv_defs), **wn_defs) net = WN(NINLayer (net, name='conv3b', num_units=256, **nin_defs), **wn_defs) net = WN(NINLayer (net, name='conv3c', num_units=128, **nin_defs), **wn_defs) net = GlobalPoolLayer (net, name='pool3') net = WN(DenseLayer (net, name='dense', num_units=10, **dense_defs), **wn_defs) return net
def create_model(incoming, options): input_p = 0.2 hidden_p = 0.5 conv_num_filters1 = int(100 / (1.0 - input_p)) conv_num_filters2 = int(150 / (1.0 - hidden_p)) conv_num_filters3 = int(200 / (1.0 - hidden_p)) filter_size1 = 5 filter_size2 = 5 filter_size3 = 3 pool_size = 2 encode_size = int(options['BOTTLENECK'] / 0.5) dense_mid_size = int(options['DENSE'] / 0.5) pad_in = 'valid' pad_out = 'full' scaled_tanh = create_scaled_tanh() dropout0 = DropoutLayer(incoming, p=0.2, name='dropout0') conv2d1 = Conv2DLayer(dropout0, num_filters=conv_num_filters1, filter_size=filter_size1, pad=pad_in, name='conv2d1', nonlinearity=scaled_tanh) maxpool2d2 = MaxPool2DLayer(conv2d1, pool_size=pool_size, name='maxpool2d2') dropout1 = DropoutLayer(maxpool2d2, name='dropout1') conv2d3 = Conv2DLayer(dropout1, num_filters=conv_num_filters2, filter_size=filter_size2, pad=pad_in, name='conv2d3', nonlinearity=scaled_tanh) maxpool2d4 = MaxPool2DLayer(conv2d3, pool_size=pool_size, name='maxpool2d4', pad=(1,0)) dropout2 = DropoutLayer(maxpool2d4, name='dropout2') conv2d5 = Conv2DLayer(dropout2, num_filters=conv_num_filters3, filter_size=filter_size3, pad=pad_in, name='conv2d5', nonlinearity=scaled_tanh) reshape6 = ReshapeLayer(conv2d5, shape=([0], -1), name='reshape6') # 3000 reshape6_output = reshape6.output_shape[1] dropout3 = DropoutLayer(reshape6, name='dropout3') dense7 = DenseLayer(dropout3, num_units=dense_mid_size, name='dense7', nonlinearity=scaled_tanh) dropout4 = DropoutLayer(dense7, name='dropout4') bottleneck = DenseLayer(dropout4, num_units=encode_size, name='bottleneck', nonlinearity=linear) # print_network(bottleneck) dense8 = DenseLayer(bottleneck, num_units=dense_mid_size, W=bottleneck.W.T, name='dense8', nonlinearity=linear) dense9 = DenseLayer(dense8, num_units=reshape6_output, W=dense7.W.T, nonlinearity=scaled_tanh, name='dense9') reshape10 = ReshapeLayer(dense9, shape=([0], conv_num_filters3, 3, 5), name='reshape10') # 32 x 4 x 7 deconv2d11 = Deconv2DLayer(reshape10, conv2d5.input_shape[1], conv2d5.filter_size, stride=conv2d5.stride, W=conv2d5.W, flip_filters=not conv2d5.flip_filters, name='deconv2d11', nonlinearity=scaled_tanh) upscale2d12 = Upscale2DLayer(deconv2d11, scale_factor=pool_size, name='upscale2d12') deconv2d13 = Deconv2DLayer(upscale2d12, conv2d3.input_shape[1], conv2d3.filter_size, stride=conv2d3.stride, W=conv2d3.W, flip_filters=not conv2d3.flip_filters, name='deconv2d13', nonlinearity=scaled_tanh) upscale2d14 = Upscale2DLayer(deconv2d13, scale_factor=pool_size, name='upscale2d14') deconv2d15 = Deconv2DLayer(upscale2d14, conv2d1.input_shape[1], conv2d1.filter_size, stride=conv2d1.stride, crop=(1, 0), W=conv2d1.W, flip_filters=not conv2d1.flip_filters, name='deconv2d14', nonlinearity=scaled_tanh) reshape16 = ReshapeLayer(deconv2d15, ([0], -1), name='reshape16') return reshape16, bottleneck
def create_model(incoming, options): conv_num_filters1 = 100 conv_num_filters2 = 150 conv_num_filters3 = 200 filter_size1 = 5 filter_size2 = 5 filter_size3 = 3 pool_size = 2 encode_size = options['BOTTLENECK'] dense_mid_size = options['DENSE'] pad_in = 'valid' pad_out = 'full' scaled_tanh = create_scaled_tanh() dropout0 = DropoutLayer(incoming, p=0.2, name='dropout0') conv2d1 = Conv2DLayer(dropout0, num_filters=conv_num_filters1, filter_size=filter_size1, pad=pad_in, name='conv2d1', nonlinearity=scaled_tanh) bn1 = BatchNormLayer(conv2d1, name='batchnorm1') maxpool2d2 = MaxPool2DLayer(bn1, pool_size=pool_size, name='maxpool2d2') dropout1 = DropoutLayer(maxpool2d2, name='dropout1') conv2d3 = Conv2DLayer(dropout1, num_filters=conv_num_filters2, filter_size=filter_size2, pad=pad_in, name='conv2d3', nonlinearity=scaled_tanh) bn2 = BatchNormLayer(conv2d3, name='batchnorm2') maxpool2d4 = MaxPool2DLayer(bn2, pool_size=pool_size, name='maxpool2d4', pad=(1,0)) dropout2 = DropoutLayer(maxpool2d4, name='dropout2') conv2d5 = Conv2DLayer(dropout2, num_filters=conv_num_filters3, filter_size=filter_size3, pad=pad_in, name='conv2d5', nonlinearity=scaled_tanh) bn3 = BatchNormLayer(conv2d5, name='batchnorm3') reshape6 = ReshapeLayer(bn3, shape=([0], -1), name='reshape6') # 3000 reshape6_output = reshape6.output_shape[1] dropout3 = DropoutLayer(reshape6, name='dropout3') dense7 = DenseLayer(dropout3, num_units=dense_mid_size, name='dense7', nonlinearity=scaled_tanh) bn4 = BatchNormLayer(dense7, name='batchnorm4') dropout4 = DropoutLayer(bn4, name='dropout4') bottleneck = DenseLayer(dropout4, num_units=encode_size, name='bottleneck', nonlinearity=linear) # print_network(bottleneck) dense8 = DenseLayer(bottleneck, num_units=dense_mid_size, W=bottleneck.W.T, name='dense8', nonlinearity=linear) dense9 = DenseLayer(dense8, num_units=reshape6_output, W=dense7.W.T, nonlinearity=scaled_tanh, name='dense9') reshape10 = ReshapeLayer(dense9, shape=([0], conv_num_filters3, 3, 5), name='reshape10') # 32 x 4 x 7 deconv2d11 = Deconv2DLayer(reshape10, conv2d5.input_shape[1], conv2d5.filter_size, stride=conv2d5.stride, W=conv2d5.W, flip_filters=not conv2d5.flip_filters, name='deconv2d11', nonlinearity=scaled_tanh) upscale2d12 = Upscale2DLayer(deconv2d11, scale_factor=pool_size, name='upscale2d12') deconv2d13 = Deconv2DLayer(upscale2d12, conv2d3.input_shape[1], conv2d3.filter_size, stride=conv2d3.stride, W=conv2d3.W, flip_filters=not conv2d3.flip_filters, name='deconv2d13', nonlinearity=scaled_tanh) upscale2d14 = Upscale2DLayer(deconv2d13, scale_factor=pool_size, name='upscale2d14') deconv2d15 = Deconv2DLayer(upscale2d14, conv2d1.input_shape[1], conv2d1.filter_size, stride=conv2d1.stride, crop=(1, 0), W=conv2d1.W, flip_filters=not conv2d1.flip_filters, name='deconv2d14', nonlinearity=scaled_tanh) reshape16 = ReshapeLayer(deconv2d15, ([0], -1), name='reshape16') return reshape16, bottleneck
def get_net(): return NeuralNet( layers=[ ('input', layers.InputLayer), ('conv1', Conv2DLayer), ('pool1', MaxPool2DLayer), ('dropout1', layers.DropoutLayer), ('conv2', Conv2DLayer), ('pool2', MaxPool2DLayer), ('dropout2', layers.DropoutLayer), ('conv3', Conv2DLayer), ('pool3', MaxPool2DLayer), ('dropout3', layers.DropoutLayer), ('hidden4', layers.DenseLayer), ('dropout4', layers.DropoutLayer), ('hidden5', layers.DenseLayer), ('output', layers.DenseLayer), ], input_shape=(None, 1, 96, 96), conv1_num_filters=32, conv1_filter_size=(3, 3), pool1_pool_size=(2, 2), dropout1_p=0.1, conv2_num_filters=64, conv2_filter_size=(2, 2), pool2_pool_size=(2, 2), dropout2_p=0.2, conv3_num_filters=128, conv3_filter_size=(2, 2), pool3_pool_size=(2, 2), dropout3_p=0.3, hidden4_num_units=1000, dropout4_p=0.5, hidden5_num_units=1000, output_num_units=30, output_nonlinearity=None, update_learning_rate=theano.shared(float32(0.03)), update_momentum=theano.shared(float32(0.9)), regression=True, batch_iterator_train=FlipBatchIterator(batch_size=128), on_epoch_finished=[ AdjustVariable('update_learning_rate', start=0.03, stop=0.0001), AdjustVariable('update_momentum', start=0.9, stop=0.999), EarlyStopping(patience=200), ], max_epochs=3000, verbose=1, )
def build_model(self, input_var, forward, dropout): net = dict() net['input'] = InputLayer((None, 3, None, None), input_var=input_var) net['conv1/7x7_s2'] = ConvLayer( net['input'], 64, 7, stride=2, pad=3, flip_filters=False) net['pool1/3x3_s2'] = PoolLayer( net['conv1/7x7_s2'], pool_size=3, stride=2, ignore_border=False) net['pool1/norm1'] = LRNLayer(net['pool1/3x3_s2'], alpha=0.00002, k=1) net['conv2/3x3_reduce'] = ConvLayer( net['pool1/norm1'], 64, 1, flip_filters=False) net['conv2/3x3'] = ConvLayer( net['conv2/3x3_reduce'], 192, 3, pad=1, flip_filters=False) net['conv2/norm2'] = LRNLayer(net['conv2/3x3'], alpha=0.00002, k=1) net['pool2/3x3_s2'] = PoolLayerDNN(net['conv2/norm2'], pool_size=3, stride=2) net.update(self.build_inception_module('inception_3a', net['pool2/3x3_s2'], [32, 64, 96, 128, 16, 32])) net.update(self.build_inception_module('inception_3b', net['inception_3a/output'], [64, 128, 128, 192, 32, 96])) net['pool3/3x3_s2'] = PoolLayerDNN(net['inception_3b/output'], pool_size=3, stride=2) net.update(self.build_inception_module('inception_4a', net['pool3/3x3_s2'], [64, 192, 96, 208, 16, 48])) net.update(self.build_inception_module('inception_4b', net['inception_4a/output'], [64, 160, 112, 224, 24, 64])) net.update(self.build_inception_module('inception_4c', net['inception_4b/output'], [64, 128, 128, 256, 24, 64])) net.update(self.build_inception_module('inception_4d', net['inception_4c/output'], [64, 112, 144, 288, 32, 64])) net.update(self.build_inception_module('inception_4e', net['inception_4d/output'], [128, 256, 160, 320, 32, 128])) net['pool4/3x3_s2'] = PoolLayerDNN(net['inception_4e/output'], pool_size=3, stride=2) net.update(self.build_inception_module('inception_5a', net['pool4/3x3_s2'], [128, 256, 160, 320, 32, 128])) net.update(self.build_inception_module('inception_5b', net['inception_5a/output'], [128, 384, 192, 384, 48, 128])) net['pool5/7x7_s1'] = GlobalPoolLayer(net['inception_5b/output']) if forward: #net['fc6'] = DenseLayer(net['pool5/7x7_s1'], num_units=1000) net['prob'] = DenseLayer(net['pool5/7x7_s1'], num_units=4, nonlinearity=softmax) else: net['dropout1'] = DropoutLayer(net['pool5/7x7_s1'], p=dropout) #net['fc6'] = DenseLayer(net['dropout1'], num_units=1000) #net['dropout2'] = DropoutLayer(net['fc6'], p=dropout) net['prob'] = DenseLayer(net['dropout1'], num_units=4, nonlinearity=softmax) return net
def buildModel(): print "BUILDING MODEL TYPE..." #default settings filters = 64 first_stride = 2 last_filter_multiplier = 16 #input layer net = l.InputLayer((None, IM_DIM, IM_SIZE[1], IM_SIZE[0])) #conv layers net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters, filter_size=7, pad='same', stride=first_stride, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 2, filter_size=5, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 4, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * 8, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) net = l.batch_norm(l.Conv2DLayer(net, num_filters=filters * last_filter_multiplier, filter_size=3, pad='same', stride=1, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.MaxPool2DLayer(net, pool_size=2) print "\tFINAL POOL OUT SHAPE:", l.get_output_shape(net) #dense layers net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.DropoutLayer(net, DROPOUT) net = l.batch_norm(l.DenseLayer(net, 512, W=init.HeNormal(gain=INIT_GAIN), nonlinearity=NONLINEARITY)) net = l.DropoutLayer(net, DROPOUT) #Classification Layer if MULTI_LABEL: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.sigmoid, W=init.HeNormal(gain=1)) else: net = l.DenseLayer(net, NUM_CLASSES, nonlinearity=nonlinearities.softmax, W=init.HeNormal(gain=1)) print "...DONE!" #model stats print "MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS" print "MODEL HAS", l.count_params(net), "PARAMS" return net
