def __init__(self, branch_units, activation=Rectlin(),
bias_init=UniformInit(low=-0.08, high=0.08),
filter_init=XavierInit()):
(p1, p2, p3, p4) = branch_units
self.branch_1 = Convolution((1, 1, p1[0]), activation=activation,
bias_init=bias_init,
filter_init=filter_init)
self.branch_2 = [Convolution((1, 1, p2[0]), activation=activation,
bias_init=bias_init,
filter_init=filter_init),
Convolution((3, 3, p2[1]), activation=activation,
bias_init=bias_init,
filter_init=filter_init, padding=1)]
self.branch_3 = [Convolution((1, 1, p3[0]), activation=activation,
bias_init=bias_init,
filter_init=filter_init),
Convolution((5, 5, p3[1]), activation=activation,
bias_init=bias_init,
filter_init=filter_init, padding=2)]
self.branch_4 = [Pool2D(fshape=3, padding=1, strides=1, op="max"),
Convolution((1, 1, p3[0]), activation=activation,
bias_init=bias_init,
filter_init=filter_init)]
def __init__(self,
number_embeddings_features,
tokens_in_embeddings,
deep_parameters,
deep_activation_fn,
drop_out_rate=0.0):
super(WideDeepClassifier, self).__init__(name="WideAndDeep")
# Embeddings
# Make the axes
self.luts = []
for e in range(len(number_embeddings_features)):
init_uniform = UniformInit(0, 1)
# pad_idx have to be initialize to 0 explicitly.
lut = LookupTable(tokens_in_embeddings[e],
number_embeddings_features[e],
init_uniform,
pad_idx=0,
update=True)
self.luts.append(lut)
# Model specification
init_xavier = XavierInit()
layers = []
for i in range(len(deep_parameters)):
layers.append(
Affine(nout=deep_parameters[i],
weight_init=init_xavier,
activation=deep_activation_fn))
if drop_out_rate > 0.0:
layers.append(Dropout(keep=drop_out_rate))
layers.append(Affine(axes=tuple(), weight_init=init_xavier))
self.deep_layers = Sequential(layers)
self.linear_layer = Affine(axes=tuple(), weight_init=init_xavier)
np.random.seed(args.rng_seed)
# Create the dataloader
train_data, valid_data = MNIST(args.data_dir).load_data()
train_set = ArrayIterator(train_data,
args.batch_size,
total_iterations=args.num_iterations)
valid_set = ArrayIterator(valid_data, args.batch_size)
inputs = train_set.make_placeholders()
ax.Y.length = 10
######################
# Model specification
init_xav = XavierInit()
seq1 = Sequential([
Preprocess(functor=lambda x: x / 255.),
Convolution((5, 5, 16), filter_init=init_xav, activation=Rectlin()),
Pooling((2, 2), strides=2),
Convolution((5, 5, 32), filter_init=init_xav, activation=Rectlin()),
Pooling((2, 2), strides=2),
Affine(nout=500, weight_init=init_xav, activation=Rectlin()),
Affine(axes=ax.Y, weight_init=init_xav, activation=Softmax())
])
optimizer = GradientDescentMomentum(0.01, 0.9)
train_prob = seq1(inputs['image'])
train_loss = ng.cross_entropy_binary(train_prob,
ng.one_hot(inputs['label'], axis=ax.Y))
outputs = [
branch_1_output, branch_2_output, branch_3_output, branch_4_output
]
# This does the equivalent of neon's merge-broadcast
return ng.concat_along_axis(outputs,
branch_1_output.axes.channel_axis())
seq1 = Sequential([
Convolution((7, 7, 64),
padding=3,
strides=2,
activation=Rectlin(),
bias_init=bias_init,
filter_init=XavierInit()),
Pooling(pool_shape=(3, 3), padding=1, strides=2, pool_type='max'),
Convolution((1, 1, 64),
activation=Rectlin(),
bias_init=bias_init,
filter_init=XavierInit()),
Convolution((3, 3, 192),
activation=Rectlin(),
bias_init=bias_init,
filter_init=XavierInit(),
padding=1),
Pooling(pool_shape=(3, 3), padding=1, strides=2, pool_type='max'),
Inception([(64, ), (96, 128), (16, 32), (32, )]),
Inception([(128, ), (128, 192), (32, 96), (64, )]),
Pooling(pool_shape=(3, 3), padding=1, strides=2, pool_type='max'),
Inception([(192, ), (96, 208), (16, 48), (64, )]),
branch_1_output = self.branch_1(in_obj)
branch_2_output = self.branch_2[0](in_obj)
branch_2_output = self.branch_2[1](branch_2_output)
branch_3_output = self.branch_3[0](in_obj)
branch_3_output = self.branch_3[1](branch_3_output)
branch_4_output = self.branch_4[0](in_obj)
branch_4_output = self.branch_4[1](branch_4_output)
outputs = [branch_1_output, branch_2_output, branch_3_output, branch_4_output]
# This does the equivalent of neon's merge-broadcast
return ng.concat_along_axis(outputs, branch_1_output.axes.channel_axis())
seq1 = Sequential([Convolution((7, 7, 64), padding=3, strides=2,
activation=Rectlin(), bias_init=bias_init,
filter_init=XavierInit()),
Pool2D(fshape=3, padding=1, strides=2, op='max'),
Convolution((1, 1, 64), activation=Rectlin(),
bias_init=bias_init, filter_init=XavierInit()),
Convolution((3, 3, 192), activation=Rectlin(),
bias_init=bias_init, filter_init=XavierInit(),
padding=1),
Pool2D(fshape=3, padding=1, strides=2, op='max'),
Inception([(64,), (96, 128), (16, 32), (32,)]),
Inception([(128,), (128, 192), (32, 96), (64,)]),
Pool2D(fshape=3, padding=1, strides=2, op='max'),
Inception([(192,), (96, 208), (16, 48), (64,)]),
Inception([(160,), (112, 224), (24, 64), (64,)]),
Inception([(128,), (128, 256), (24, 64), (64,)]),
Inception([(112,), (144, 288), (32, 64), (64,)]),
Inception([(256,), (160, 320), (32, 128), (128,)]),