def __init__(self, params):
specs = ResNet.specs[params['model']]
Model.check_parameters(
params, {
'name': specs['name'],
'num_classes': 1000,
'phase': 'training',
'dtype': 'float32',
'input_layout': 'NCHW',
'model_layout': 'NCHW',
'nvidia_layers': False,
'workspace': 1024
})
params['input_shape'] = Model.conv_shape(3, (224, 224),
params['input_layout'])
Model.__init__(self, params)
self.params = params
self.layers = Layers(params)
# Adapted from https://github.com/tornadomeet/ResNet/blob/master/train_resnet.py
# Original author Wei Wu
# Some optimizations are taken from NVIDIA code from NGC containers.
if specs['num_layers'] >= 50:
filter_list = [64, 256, 512, 1024, 2048]
bottle_neck = True
else:
filter_list = [64, 64, 128, 256, 512]
bottle_neck = False
self.__output = self.resnet(units=specs['units'],
num_stages=4,
filter_list=filter_list,
bottle_neck=bottle_neck,
workspace=params['workspace'],
fuse_bn_add_relu=params['nvidia_layers'],
fuse_bn_relu=params['nvidia_layers'])
def __init__(self, params):
Model.check_parameters(
params, {
'name': 'AlexNetOWT',
'num_classes': 1000,
'phase': 'training',
'dtype': 'float32',
'input_layout': 'NCHW',
'model_layout': 'NCHW',
'nvidia_layers': False
})
params['input_shape'] = Model.conv_shape(3, (227, 227),
params['input_layout'])
Model.__init__(self, params)
layers = Layers(params)
data = self.add_data_node()
data = Layers.conv_transform_layout(data, params['input_layout'],
params['model_layout'])
conv1 = layers.Convolution(name='conv1',
data=data,
kernel=(11, 11),
stride=(4, 4),
num_filter=64)
relu1 = layers.Activation(name='relu1', data=conv1, act_type='relu')
pool1 = layers.Pooling(name='pool1',
data=relu1,
pool_type="max",
kernel=(3, 3),
stride=(2, 2))
conv2 = layers.Convolution(name='conv2',
data=pool1,
kernel=(5, 5),
pad=(2, 2),
num_filter=192)
relu2 = layers.Activation(name='relu2', data=conv2, act_type="relu")
pool2 = layers.Pooling(name='pool2',
data=relu2,
kernel=(3, 3),
stride=(2, 2),
pool_type="max")
conv3 = layers.Convolution(name='conv3',
data=pool2,
kernel=(3, 3),
pad=(1, 1),
num_filter=384)
relu3 = layers.Activation(name='relu3', data=conv3, act_type="relu")
conv4 = layers.Convolution(name='conv4',
data=relu3,
kernel=(3, 3),
pad=(1, 1),
num_filter=256)
relu4 = layers.Activation(name='relu4', data=conv4, act_type="relu")
conv5 = layers.Convolution(name='conv5',
data=relu4,
kernel=(3, 3),
pad=(1, 1),
num_filter=256)
relu5 = layers.Activation(name='relu5', data=conv5, act_type="relu")
pool5 = layers.Pooling(name='pool5',
data=relu5,
kernel=(3, 3),
stride=(2, 2),
pool_type="max")
flatten = mx.symbol.Flatten(data=pool5)
fc6 = mx.symbol.FullyConnected(name='fc6',
data=flatten,
num_hidden=4096)
relu6 = layers.Activation(name='relu6', data=fc6, act_type="relu")
drop6 = layers.Dropout(name='drop6', data=relu6, p=0.5)
fc7 = mx.symbol.FullyConnected(name='fc7', data=drop6, num_hidden=4096)
relu7 = layers.Activation(name='relu7', data=fc7, act_type="relu")
drop7 = layers.Dropout(name='drop7', data=relu7, p=0.5)
self.__output = self.add_head_nodes(drop7)
