def __init__(self, num_classes=10, num_channels=1): super(AlexNet, self).__init__() self.num_classes = num_classes self.input_size = 224 self.dimension = 4 self.conv1 = layer.Conv2d(num_channels, 64, 11, stride=4, padding=2) self.conv2 = layer.Conv2d(64, 192, 5, padding=2) self.conv3 = layer.Conv2d(192, 384, 3, padding=1) self.conv4 = layer.Conv2d(384, 256, 3, padding=1) self.conv5 = layer.Conv2d(256, 256, 3, padding=1) self.linear1 = layer.Linear(4096) self.linear2 = layer.Linear(4096) self.linear3 = layer.Linear(num_classes) self.pooling1 = layer.MaxPool2d(2, 2, padding=0) self.pooling2 = layer.MaxPool2d(2, 2, padding=0) self.pooling3 = layer.MaxPool2d(2, 2, padding=0) self.avg_pooling1 = layer.AvgPool2d(3, 2, padding=0) self.relu1 = layer.ReLU() self.relu2 = layer.ReLU() self.relu3 = layer.ReLU() self.relu4 = layer.ReLU() self.relu5 = layer.ReLU() self.relu6 = layer.ReLU() self.relu7 = layer.ReLU() self.flatten = layer.Flatten() self.dropout1 = layer.Dropout() self.dropout2 = layer.Dropout() self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
def create_net(use_cpu=False): if use_cpu: layer.engine = 'singacpp' net = ffnet.FeedForwardNet(loss.SoftmaxCrossEntropy(), metric.Accuracy()) ConvBnReLU(net, 'conv1_1', 64, (3, 32, 32)) net.add(layer.Dropout('drop1', 0.3)) ConvBnReLU(net, 'conv1_2', 64) net.add(layer.MaxPooling2D('pool1', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv2_1', 128) net.add(layer.Dropout('drop2_1', 0.4)) ConvBnReLU(net, 'conv2_2', 128) net.add(layer.MaxPooling2D('pool2', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv3_1', 256) net.add(layer.Dropout('drop3_1', 0.4)) ConvBnReLU(net, 'conv3_2', 256) net.add(layer.Dropout('drop3_2', 0.4)) ConvBnReLU(net, 'conv3_3', 256) net.add(layer.MaxPooling2D('pool3', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv4_1', 512) net.add(layer.Dropout('drop4_1', 0.4)) ConvBnReLU(net, 'conv4_2', 512) net.add(layer.Dropout('drop4_2', 0.4)) ConvBnReLU(net, 'conv4_3', 512) net.add(layer.MaxPooling2D('pool4', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv5_1', 512) net.add(layer.Dropout('drop5_1', 0.4)) ConvBnReLU(net, 'conv5_2', 512) net.add(layer.Dropout('drop5_2', 0.4)) ConvBnReLU(net, 'conv5_3', 512) net.add(layer.MaxPooling2D('pool5', 2, 2, border_mode='valid')) net.add(layer.Flatten('flat')) net.add(layer.Dropout('drop_flat', 0.5)) net.add(layer.Dense('ip1', 512)) net.add(layer.BatchNormalization('batchnorm_ip1')) net.add(layer.Activation('relu_ip1')) net.add(layer.Dropout('drop_ip2', 0.5)) net.add(layer.Dense('ip2', 10)) print 'Start intialization............' for (p, name) in zip(net.param_values(), net.param_names()): print name, p.shape if 'mean' in name or 'beta' in name: p.set_value(0.0) elif 'var' in name: p.set_value(1.0) elif 'gamma' in name: initializer.uniform(p, 0, 1) elif len(p.shape) > 1: if 'conv' in name: initializer.gaussian(p, 0, 3 * 3 * p.shape[0]) else: p.gaussian(0, 0.02) else: p.set_value(0) print name, p.l1() return net
def create_net(input_shape, use_cpu=False): if use_cpu: layer.engine = 'singacpp' net = ffnet.FeedForwardNet(loss.SoftmaxCrossEntropy(), metric.Accuracy()) ConvBnReLUPool(net, 'conv1', 32, input_shape) ConvBnReLUPool(net, 'conv2', 64) ConvBnReLUPool(net, 'conv3', 128) ConvBnReLUPool(net, 'conv4', 128) ConvBnReLUPool(net, 'conv5', 256) ConvBnReLUPool(net, 'conv6', 256) ConvBnReLUPool(net, 'conv7', 512) ConvBnReLUPool(net, 'conv8', 512) net.add(layer.Flatten('flat')) net.add(layer.Dense('ip1', 256)) net.add(layer.BatchNormalization('bn1')) net.add(layer.Activation('relu1')) net.add(layer.Dropout('dropout1', 0.2)) net.add(layer.Dense('ip2', 16)) net.add(layer.BatchNormalization('bn2')) net.add(layer.Activation('relu2')) net.add(layer.Dropout('dropout2', 0.2)) net.add(layer.Dense('ip3', 2)) print 'Parameter intialization............' for (p, name) in zip(net.param_values(), net.param_names()): print name, p.shape if 'mean' in name or 'beta' in name: p.set_value(0.0) elif 'var' in name: p.set_value(1.0) elif 'gamma' in name: initializer.uniform(p, 0, 1) elif len(p.shape) > 1: if 'conv' in name: initializer.gaussian(p, 0, p.size()) else: p.gaussian(0, 0.02) else: p.set_value(0) print name, p.l1() return net
def create_net(depth, nb_classes, dense=0, use_cpu=True): if use_cpu: layer.engine = 'singacpp' net = densenet_base(depth) # this part was not included in the pytorch model if dense > 0: net.add(layer.Dense('hidden-dense', dense)) net.add(layer.Activation('act-dense')) net.add(layer.Dropout('dropout')) net.add(layer.Dense('sigmoid', nb_classes)) return net
def build_net(self): if self.use_cpu: layer.engine = 'singacpp' else: layer.engine = 'cudnn' self.net = ffnet.FeedForwardNet(loss.SoftmaxCrossEntropy(), metric.Accuracy()) self.net.add( Reshape('reshape1', (self.vocab_size, ), input_sample_shape=(self.maxlen, self.vocab_size))) self.net.add(layer.Dense('embed', self.embed_size)) # output: (embed_size, ) self.net.add(layer.Dropout('dropout')) self.net.add(Reshape('reshape2', (1, self.maxlen, self.embed_size))) self.net.add( layer.Conv2D('conv', self.filters, (self.kernel_size, self.embed_size), border_mode='valid')) # output: (filter, embed_size) if self.use_cpu == False: self.net.add(layer.BatchNormalization('batchNorm')) self.net.add(layer.Activation('activ')) # output: (filter, embed_size) self.net.add(layer.MaxPooling2D('max', stride=self.pool_size)) self.net.add(layer.Flatten('flatten')) self.net.add(layer.Dense('dense', 2))
def create_net(input_shape, use_cpu=False): if use_cpu: layer.engine = 'singacpp' net = ffnet.FeedForwardNet(loss.SoftmaxCrossEntropy(), metric.Accuracy()) net.add( layer.Conv2D('conv1', nb_kernels=32, kernel=7, stride=3, pad=1, input_sample_shape=input_shape)) net.add(layer.Activation('relu1')) net.add(layer.BatchNormalization('bn1')) net.add(layer.MaxPooling2D('pool1', 2, 2, border_mode='valid')) net.add(layer.Conv2D('conv2', nb_kernels=64, kernel=5, stride=3)) net.add(layer.Activation('relu2')) net.add(layer.BatchNormalization('bn2')) net.add(layer.MaxPooling2D('pool2', 2, 2, border_mode='valid')) net.add(layer.Conv2D('conv3', nb_kernels=128, kernel=3, stride=1, pad=2)) net.add(layer.Activation('relu3')) net.add(layer.BatchNormalization('bn3')) net.add(layer.MaxPooling2D('pool3', 2, 2, border_mode='valid')) net.add(layer.Conv2D('conv4', nb_kernels=256, kernel=3, stride=1)) net.add(layer.Activation('relu4')) net.add(layer.BatchNormalization('bn4')) net.add(layer.MaxPooling2D('pool4', 2, 2, border_mode='valid')) net.add(layer.Conv2D('conv5', nb_kernels=512, kernel=3, stride=1, pad=1)) net.add(layer.Activation('relu5')) net.add(layer.BatchNormalization('bn5')) net.add(layer.MaxPooling2D('pool5', 2, 2, border_mode='valid')) net.add(layer.Flatten('flat')) net.add(layer.Dense('ip6', 2048)) net.add(layer.Activation('relu6')) net.add(layer.BatchNormalization('bn6')) net.add(layer.Dropout('dropout6', 0.5)) net.add(layer.Dense('ip7', 128)) net.add(layer.Activation('relu7')) net.add(layer.BatchNormalization('bn7')) net.add(layer.Dropout('dropout7', 0.2)) net.add(layer.Dense('ip8', 2)) print 'Parameter intialization............' for (p, name) in zip(net.param_values(), net.param_names()): print name, p.shape if 'mean' in name or 'beta' in name: p.set_value(0.0) elif 'var' in name: p.set_value(1.0) elif 'gamma' in name: initializer.uniform(p, 0, 1) elif len(p.shape) > 1: if 'conv' in name: initializer.gaussian(p, 0, p.size()) else: p.gaussian(0, 0.02) else: p.set_value(0) print name, p.l1() return net
def test_dropout(self): input_sample_shape = (64, 1, 12) dropout = layer.Dropout('drop', input_sample_shape=input_sample_shape) out_sample_shape = dropout.get_output_sample_shape() self.check_shape(out_sample_shape, input_sample_shape)
def create_net(input_shape, use_cpu=False): if use_cpu: layer.engine = 'singacpp' net = ffnet.FeedForwardNet(loss.SoftmaxCrossEntropy(), metric.Accuracy()) ConvBnReLU(net, 'conv1_1', 64, input_shape) #net.add(layer.Dropout('drop1', 0.3)) net.add(layer.MaxPooling2D('pool0', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv1_2', 128) net.add(layer.MaxPooling2D('pool1', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv2_1', 128) net.add(layer.Dropout('drop2_1', 0.4)) ConvBnReLU(net, 'conv2_2', 128) net.add(layer.MaxPooling2D('pool2', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv3_1', 256) net.add(layer.Dropout('drop3_1', 0.4)) ConvBnReLU(net, 'conv3_2', 256) net.add(layer.Dropout('drop3_2', 0.4)) ConvBnReLU(net, 'conv3_3', 256) net.add(layer.MaxPooling2D('pool3', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv4_1', 256) net.add(layer.Dropout('drop4_1', 0.4)) ConvBnReLU(net, 'conv4_2', 256) net.add(layer.Dropout('drop4_2', 0.4)) ConvBnReLU(net, 'conv4_3', 256) net.add(layer.MaxPooling2D('pool4', 2, 2, border_mode='valid')) ConvBnReLU(net, 'conv5_1', 512) net.add(layer.Dropout('drop5_1', 0.4)) ConvBnReLU(net, 'conv5_2', 512) net.add(layer.Dropout('drop5_2', 0.4)) ConvBnReLU(net, 'conv5_3', 512) net.add(layer.MaxPooling2D('pool5', 2, 2, border_mode='valid')) #ConvBnReLU(net, 'conv6_1', 512) #net.add(layer.Dropout('drop6_1', 0.4)) #ConvBnReLU(net, 'conv6_2', 512) #net.add(layer.Dropout('drop6_2', 0.4)) #ConvBnReLU(net, 'conv6_3', 512) #net.add(layer.MaxPooling2D('pool6', 2, 2, border_mode='valid')) #ConvBnReLU(net, 'conv7_1', 512) #net.add(layer.Dropout('drop7_1', 0.4)) #ConvBnReLU(net, 'conv7_2', 512) #net.add(layer.Dropout('drop7_2', 0.4)) #ConvBnReLU(net, 'conv7_3', 512) #net.add(layer.MaxPooling2D('pool7', 2, 2, border_mode='valid')) net.add(layer.Flatten('flat')) net.add(layer.Dense('ip1', 256)) net.add(layer.BatchNormalization('bn1')) net.add(layer.Activation('relu1')) net.add(layer.Dropout('dropout1', 0.2)) net.add(layer.Dense('ip2', 16)) net.add(layer.BatchNormalization('bn2')) net.add(layer.Activation('relu2')) net.add(layer.Dropout('dropout2', 0.2)) net.add(layer.Dense('ip3', 2)) print 'Parameter intialization............' for (p, name) in zip(net.param_values(), net.param_names()): print name, p.shape if 'mean' in name or 'beta' in name: p.set_value(0.0) elif 'var' in name: p.set_value(1.0) elif 'gamma' in name: initializer.uniform(p, 0, 1) elif len(p.shape) > 1: if 'conv' in name: initializer.gaussian(p, 0, p.size()) else: p.gaussian(0, 0.02) else: p.set_value(0) print name, p.l1() return net