def main(args):
# Define a convolutional neural network the same as above
net = builder.Sequential(
builder.Convolution((7, 7), 32),
builder.ReLU(),
builder.Pooling('max', (2, 2), (2, 2)),
builder.Reshape((flattened_input_size,))
builder.Affine(hidden_size),
builder.Affine(num_classes),
)
# Cast the definition to a model compatible with minpy solver
model = builder.Model(net, 'softmax', (3 * 32 * 32,))
data = get_CIFAR10_data(args.data_dir)
train_dataiter = NDArrayIter(data['X_train'],
data['y_train'],
batch_size=batch_size,
shuffle=True)
test_dataiter = NDArrayIter(data['X_test'],
data['y_test'],
batch_size=batch_size,
shuffle=False)
solver = Solver(model,
train_dataiter,
test_dataiter,
num_epochs=10,
init_rule='gaussian',
init_config={
'stdvar': 0.001
},
update_rule='sgd_momentum',
optim_config={
'learning_rate': 1e-3,
'momentum': 0.9
},
verbose=True,
print_every=20)
solver.init()
solver.train()
def main(args):
# Define a 2-layer perceptron
MLP = builder.Sequential(
builder.Affine(512),
builder.ReLU(),
builder.Affine(10)
)
# Cast the definition to a model compatible with minpy solver
model = builder.Model(MLP, 'softmax', (3 * 32 * 32,))
data = get_CIFAR10_data(args.data_dir)
data['X_train'] = data['X_train'].reshape([data['X_train'].shape[0], 3 * 32 * 32])
data['X_val'] = data['X_val'].reshape([data['X_val'].shape[0], 3 * 32 * 32])
data['X_test'] = data['X_test'].reshape([data['X_test'].shape[0], 3 * 32 * 32])
train_dataiter = NDArrayIter(data['X_train'],
data['y_train'],
batch_size=100,
shuffle=True)
test_dataiter = NDArrayIter(data['X_test'],
data['y_test'],
batch_size=100,
shuffle=False)
solver = Solver(model,
train_dataiter,
test_dataiter,
num_epochs=10,
init_rule='gaussian',
init_config={
'stdvar': 0.001
},
update_rule='sgd_momentum',
optim_config={
'learning_rate': 1e-5,
'momentum': 0.9
},
verbose=True,
print_every=20)
solver.init()
solver.train()
import minpy.nn.model_builder as builder
'''
Network In Network
Reference:
Min Lin, Qiang Chen, Shuicheng Yan, Network In Network
'''
network_in_network = builder.Sequential(
builder.Reshape((3, 32, 32)),
builder.Convolution((5, 5), 192, pad=(2, 2)),
builder.ReLU(),
builder.Convolution((1, 1), 160),
builder.ReLU(),
builder.Convolution((1, 1), 96),
builder.ReLU(),
builder.Pooling('max', (3, 3), (2, 2), (1, 1)),
builder.Dropout(0.5),
builder.Convolution((5, 5), 192, pad=(2, 2)),
builder.ReLU(),
builder.Convolution((1, 1), 192),
builder.ReLU(),
builder.Convolution((1, 1), 192),
builder.ReLU(),
builder.Pooling('avg', (3, 3), (2, 2), (1, 1)),
builder.Dropout(0.5),
builder.Convolution((3, 3), 192, pad=(1, 1)),
builder.ReLU(),
builder.Convolution((1, 1), 192),
builder.ReLU(),
builder.Convolution((1, 1), 10),
import minpy.nn.model_builder as builder
'''
Network In Network
Reference:
Min Lin, Qiang Chen, Shuicheng Yan, Network In Network
'''
network_in_network = builder.Sequential(
builder.Reshape((3, 32, 32)), builder.Convolution((5, 5), 192, pad=(2, 2)),
builder.ReLU(), builder.Convolution((1, 1), 160), builder.ReLU(),
builder.Convolution((1, 1), 96), builder.ReLU(),
builder.Pooling('max', (3, 3), (2, 2)), builder.Dropout(0.5),
builder.Convolution((5, 5), 192, pad=(2, 2)), builder.ReLU(),
builder.Convolution((1, 1), 192), builder.ReLU(),
builder.Convolution((1, 1), 192), builder.ReLU(),
builder.Pooling('avg', (3, 3), (2, 2)), builder.Dropout(0.5),
builder.Convolution((3, 3), 192, pad=(1, 1)), builder.ReLU(),
builder.Convolution((1, 1), 192), builder.ReLU(),
builder.Convolution((1, 1), 10), builder.ReLU(),
builder.Pooling('avg', (8, 8)), builder.Reshape((10, )))
'''
Residual Network
Reference:
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. "Deep Residual Learning for Image Recognition"
'''
def residual_network(n):
'''
n: the network contains 6 * n + 2 layers, including 6 * n + 1 convolution layers and 1 affine layer