def Pooling(op, # PoolingType_Max or _Average
filter_shape, # e.g. (3,3)
strides=1,
pad=False):
x = Placeholder(name='pooling_arg')
apply_x = pooling (x, op, filter_shape, strides=_as_tuple(strides), auto_padding=_as_tuple(pad))
if op == PoolingType_Average:
op_name = 'AveragePooling'
elif op == PoolingType_Max:
op_name = 'MaxPooling'
else:
raise ValueError('Pooling: op must be PoolingType_Max or PoolingType_average')
return Block(apply_x, op_name)
def create_resnet_model(input, num_classes):
bn_time_const = 4096
c_map1 = 16
feat_scale = 0.00390625
input_norm = element_times(feat_scale, input)
conv = conv_bn_relu_layer(input_norm, c_map1, [3, 3], [1, 1],
bn_time_const)
r1_1 = resnet_basic_stack3(conv, c_map1, bn_time_const)
c_map2 = 32
r2_1 = resnet_basic_inc(r1_1, c_map2, [2, 2], bn_time_const)
r2_2 = resnet_basic_stack2(r2_1, c_map2, bn_time_const)
c_map3 = 64
r3_1 = resnet_basic_inc(r2_2, c_map3, [2, 2], bn_time_const)
r3_2 = resnet_basic_stack2(r3_1, c_map3, bn_time_const)
# Global average pooling
poolw = 8
poolh = 8
poolh_stride = 1
poolv_stride = 1
pool = pooling(r3_2, AVG_POOLING, (1, poolh, poolw),
(1, poolv_stride, poolh_stride))
return linear_layer(pool, num_classes)
def create_resnet_model(input, num_classes):
bn_time_const = 4096
c_map1 = 16
feat_scale = 0.00390625
input_norm = element_times(feat_scale, input)
conv = conv_bn_relu_layer(input, c_map1, [3, 3], [1, 1], bn_time_const)
r1_1 = resnet_basic_stack3(conv, c_map1, bn_time_const)
c_map2 = 32
r2_1 = resnet_basic_inc(r1_1, c_map2, [2, 2], bn_time_const)
r2_2 = resnet_basic_stack2(r2_1, c_map2, bn_time_const)
c_map3 = 64
r3_1 = resnet_basic_inc(r2_2, c_map3, [2, 2], bn_time_const)
r3_2 = resnet_basic_stack2(r3_1, c_map3, bn_time_const)
# Global average pooling
poolw = 8
poolh = 8
poolh_stride = 1
poolv_stride = 1
pool = pooling(r3_2, AVG_POOLING, (1, poolh, poolw), (1, poolv_stride, poolh_stride))
return linear_layer(pool, num_classes)
def resnet_classifer(input, num_classes):
conv_w_scale = 7.07
conv_b_value = 0
fc1_w_scale = 0.4
fc1_b_value = 0
sc_value = 1
bn_time_const = 4096
kernel_width = 3
kernel_height = 3
conv1_w_scale = 0.26
c_map1 = 16
conv1 = conv_bn_relu_layer(input, c_map1, kernel_width, kernel_height, 1,
1, conv1_w_scale, conv_b_value, sc_value,
bn_time_const)
rn1_1 = resnet_node2(conv1, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn1_2 = resnet_node2(rn1_1, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn1_3 = resnet_node2(rn1_2, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
c_map2 = 32
rn2_1_wProj = get_projection_map(c_map2, c_map1)
rn2_1 = resnet_node2_inc(rn1_3, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value,
bn_time_const, rn2_1_wProj)
rn2_2 = resnet_node2(rn2_1, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn2_3 = resnet_node2(rn2_2, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
c_map3 = 64
rn3_1_wProj = get_projection_map(c_map3, c_map2)
rn3_1 = resnet_node2_inc(rn2_3, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value,
bn_time_const, rn3_1_wProj)
rn3_2 = resnet_node2(rn3_1, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn3_3 = resnet_node2(rn3_2, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
# Global average pooling
poolw = 8
poolh = 8
poolh_stride = 1
poolv_stride = 1
pool = pooling(rn3_3, AVG_POOLING, (1, poolh, poolw),
(1, poolv_stride, poolh_stride))
out_times_params = parameter(shape=(c_map3, 1, 1, num_classes),
init=glorot_uniform())
out_bias_params = parameter(shape=(num_classes), init=0)
t = times(pool, out_times_params)
return t + out_bias_params
def resnet_classifer(input, num_classes):
conv_w_scale = 7.07
conv_b_value = 0
fc1_w_scale = 0.4
fc1_b_value = 0
sc_value = 1
bn_time_const = 4096
kernel_width = 3
kernel_height = 3
conv1_w_scale = 0.26
c_map1 = 16
conv1 = conv_bn_relu_layer(input, c_map1, kernel_width, kernel_height,
1, 1, conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn1_1 = resnet_node2(conv1, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn1_2 = resnet_node2(rn1_1, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn1_3 = resnet_node2(rn1_2, c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
c_map2 = 32
rn2_1_wProj = get_projection_map(c_map2, c_map1)
rn2_1 = resnet_node2_inc(rn1_3, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const, rn2_1_wProj)
rn2_2 = resnet_node2(rn2_1, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn2_3 = resnet_node2(rn2_2, c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
c_map3 = 64
rn3_1_wProj = get_projection_map(c_map3, c_map2)
rn3_1 = resnet_node2_inc(rn2_3, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const, rn3_1_wProj)
rn3_2 = resnet_node2(rn3_1, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
rn3_3 = resnet_node2(rn3_2, c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const)
# Global average pooling
poolw = 8
poolh = 8
poolh_stride = 1
poolv_stride = 1
pool = pooling(rn3_3, AVG_POOLING, (1, poolh, poolw), (1, poolv_stride, poolh_stride))
out_times_params = parameter(shape=(c_map3, 1, 1, num_classes), init=glorot_uniform())
out_bias_params = parameter(shape=(num_classes), init=0)
t = times(pool, out_times_params)
return t + out_bias_params
def Pooling(op, # PoolingType_Max or _Average
filter_shape, # e.g. (3,3)
strides=1,
pad=False):
x = Placeholder(name='pooling_arg')
apply_x = pooling (x, op, filter_shape, strides=_as_tuple(strides), auto_padding=_as_tuple(pad))
if op == PoolingType_Average:
op_name = 'AveragePooling'
elif op == PoolingType_Max:
op_name = 'MaxPooling'
else:
raise ValueError('Pooling: op must be PoolingType_Max or PoolingType_average')
return Block(apply_x, op_name)
def pooling(cntk_layer, inputs):
'''
Setup pooling op with given parameters
Args:
cntk_layer (:class:`~cntk.contrib.crosstalkcaffe.unimodel.cntkmodel.CntkLayersDefinition`):
the layer definition of pooling op
inputs (list): a list contains all :class:`~cntk.ops.functions.Function` or
:class:`~cntk.input`
Return:
:func:`~cntk.ops.functions.Function`: instaced cntk pooling op
'''
sanitize_input = internal.sanitize_input(inputs[0])
pooling_type = ops.PoolingType_Average if cntk_layer.parameters.pooling_type else ops.PoolingType_Max
return ops.pooling(sanitize_input, pooling_type, tuple(cntk_layer.parameters.kernel),
strides=tuple(cntk_layer.parameters.stride),
auto_padding=[cntk_layer.parameters.auto_pad],
ceil_out_dim=True,
name=cntk_layer.op_name)
def pooling(cntk_layer, inputs):
'''
Setup pooling op with given parameters
Args:
cntk_layer (:class:`~cntk.contrib.crosstalkcaffe.unimodel.cntkmodel.CntkLayersDefinition`):
the layer definition of pooling op
inputs (list): a list contains all :class:`~cntk.ops.functions.Function` or
:class:`~cntk.input`
Return:
:func:`~cntk.ops.functions.Function`: instaced cntk pooling op
'''
sanitize_input = internal.sanitize_input(inputs[0])
pooling_type = ops.PoolingType_Average if cntk_layer.parameters.pooling_type else ops.PoolingType_Max
return ops.pooling(sanitize_input,
pooling_type,
tuple(cntk_layer.parameters.kernel),
strides=tuple(cntk_layer.parameters.stride),
auto_padding=[cntk_layer.parameters.auto_pad],
ceil_out_dim=True,
name=cntk_layer.op_name)
def resnet_classifer(input, num_classes, device, output_name):
conv_w_scale = 7.07
conv_b_value = 0
fc1_w_scale = 0.4
fc1_b_value = 0
sc_value = 1
bn_time_const = 4096
kernel_width = 3
kernel_height = 3
conv1_w_scale = 0.26
c_map1 = 16
conv1 = conv_bn_relu_layer(input, c_map1, kernel_width, kernel_height, 1,
1, conv1_w_scale, conv_b_value, sc_value,
bn_time_const, device)
rn1_1 = resnet_node2(conv1.output(), c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
rn1_2 = resnet_node2(rn1_1.output(), c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
rn1_3 = resnet_node2(rn1_2.output(), c_map1, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
c_map2 = 32
rn2_1_wProj = get_projection_map(c_map2, c_map1, device)
rn2_1 = resnet_node2_inc(rn1_3.output(), c_map2, kernel_width,
kernel_height, conv1_w_scale, conv_b_value,
sc_value, bn_time_const, rn2_1_wProj, device)
rn2_2 = resnet_node2(rn2_1.output(), c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
rn2_3 = resnet_node2(rn2_2.output(), c_map2, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
c_map3 = 64
rn3_1_wProj = get_projection_map(c_map3, c_map2, device)
rn3_1 = resnet_node2_inc(rn2_3.output(), c_map3, kernel_width,
kernel_height, conv1_w_scale, conv_b_value,
sc_value, bn_time_const, rn3_1_wProj, device)
rn3_2 = resnet_node2(rn3_1.output(), c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
rn3_3 = resnet_node2(rn3_2.output(), c_map3, kernel_width, kernel_height,
conv1_w_scale, conv_b_value, sc_value, bn_time_const,
device)
# Global average pooling
poolw = 8
poolh = 8
poolh_stride = 1
poolv_stride = 1
pool = pooling(rn3_3.output(), AVG_POOLING, (1, poolh, poolw),
(1, poolv_stride, poolh_stride))
out_times_params = parameter(shape=(c_map3, 1, 1, num_classes),
device_id=device)
out_bias_params = parameter(shape=(num_classes, ), device_id=device)
t = times(pool.output(), out_times_params)
return plus(t.output(), out_bias_params, output_name)
def pooling(input, **kwargs):
dim = len(input.output.shape)
input = cntk.transpose(input, [dim - 1] + list(range(0, dim - 1)))
layer = ops.pooling(input, **kwargs)
layer = cntk.transpose(layer, list(range(1, dim)) + [0])
return layer
def max_pool_layer(input, pool_size, stride):
return pooling(input, PoolingType_Max, (1, pool_size[0], pool_size[1]), (1, stride[0], stride[1]))
