def Conv(data,
num_filter,
kernel=(1, 1),
stride=(1, 1),
pad=(0, 0),
name=None,
suffix=''):
if pad[0] != 0 or pad[1] != 0:
data = sym.pad(data=data,
pad_width=((0, 0), (pad[0], pad[0]),
(pad[1], pad[1]), (0, 0)))
conv = sym.conv2d(data=data,
channels=num_filter,
kernel_size=kernel,
strides=stride,
padding=(0, 0),
use_bias=False,
layout='NHWC',
kernel_layout='HWOI',
name="%s%s_conv2d" % (name, suffix))
bn = sym.batch_norm(data=conv,
name="%s%s_batchnorm" % (name, suffix),
epsilon=2e-5,
axis=3)
act = sym.relu(data=bn, name="%s%s_relu" % (name, suffix))
return act
def test_pad():
x = sym.Variable("x")
y = sym.pad(x, pad_width=((0, 0), (0, 0), (0, 1), (2, 3)), pad_value=1.)
def forward(x):
return np.pad(x,
pad_width=((0, 0), (0, 0), (0, 1), (2, 3)),
mode='constant', constant_values=1.)
shape = {'x': (1, 3, 28, 28)}
check_function(y, forward, shape=shape)
def test_pad():
x = sym.Variable("x")
y = sym.pad(x, pad_width=((0, 0), (0, 0), (0, 1), (2, 3)), pad_value=1.)
def forward(x):
return np.pad(x,
pad_width=((0, 0), (0, 0), (0, 1), (2, 3)),
mode='constant', constant_values=1.)
shape = {'x': (1, 3, 28, 28)}
check_function(y, forward, shape=shape)
def test_pad():
x = sym.Variable("x")
y = sym.pad(x, pad_width=((0, 0), (0, 0), (0, 1), (2, 3)), pad_value=1.)
def forward(x):
return np.pad(x,
pad_width=((0, 0), (0, 0), (0, 1), (2, 3)),
mode='constant', constant_values=1.)
dtype = "float32"
inputs = {'x': ((1, 3, 28, 28), x)}
helper(y, inputs, dtype, forward)
def test_pad():
x = sym.Variable("x")
y = sym.pad(x, pad_width=((0, 0), (0, 0), (0, 1), (2, 3)), pad_value=1.)
def forward(x):
return np.pad(x,
pad_width=((0, 0), (0, 0), (0, 1), (2, 3)),
mode='constant',
constant_values=1.)
dtype = "float32"
inputs = [('x', (1, 3, 28, 28), x)]
helper(y, inputs, dtype, forward)
def test_pad():
x = sym.Variable("x")
y = sym.pad(x, pad_width=((0, 0), (0, 0), (0, 1), (2, 3)), pad_value=1.)
dtype = "float32"
dshape = (1, 3, 28, 28)
oshape = (1, 3, 29, 33)
shape_dict = {"x": dshape}
for target, ctx in ctx_list():
graph, lib, _ = nnvm.compiler.build(y, target, shape_dict)
m = graph_runtime.create(graph, lib, ctx)
data = tvm.nd.array(np.random.uniform(size=dshape).astype(dtype))
m.run(x=data)
out = m.get_output(0, tvm.nd.empty(oshape, dtype))
b_np = np.pad(data.asnumpy(), pad_width=((0, 0), (0, 0), (0, 1), (2, 3)),
mode='constant', constant_values=1.)
np.testing.assert_allclose(out.asnumpy(), b_np, rtol=1e-5)
def Pooling(data, kernel, stride, pad, pool_type, name):
if pad[0] != 0 or pad[1] != 0:
data = sym.pad(data=data,
pad_width=((0, 0), (pad[0], pad[0]),
(pad[1], pad[1]), (0, 0)))
if pool_type == 'max':
return sym.max_pool2d(data=data,
pool_size=kernel,
strides=stride,
name=name,
layout='NHWC')
if pool_type == 'avg':
return sym.avg_pool2d(data=data,
pool_size=kernel,
strides=stride,
name=name,
layout='NHWC')
raise ValueError("Invalid pooling type: " + pool_type)
def get_feature(internel_layer, layers, filters, batch_norm=False):
"""
Get VGG feature body as stacks of convoltions.
layers : [1, 1, 2, 2, 2]
filters : [64, 128, 256, 512, 512]
"""
for i, num in enumerate(layers):
"""
i = 0, num = 1
i = 1, num = 1
i = 2, num = 2
i = 3, num = 2
i = 4, num = 2
"""
for j in range(num):
internel_layer = sym.pad(data=internel_layer,
pad_width=((0, 0), (1, 1), (1, 1),
(0, 0)))
internel_layer = sym.conv2d(data=internel_layer,
kernel_size=(3, 3),
channels=filters[i],
layout='NHWC',
kernel_layout='HWOI',
name="conv%s_%s" % (i + 1, j + 1))
if batch_norm:
internel_layer = sym.batch_norm(data=internel_layer,
axis=3,
name="bn%s_%s" %
(i + 1, j + 1))
internel_layer = sym.relu(data=internel_layer,
name="relu%s_%s" % (i + 1, j + 1))
internel_layer = sym.max_pool2d(data=internel_layer,
pool_size=(2, 2),
strides=(2, 2),
layout="NHWC",
name="pool%s" % (i + 1))
return internel_layer
