在Tensorflow的MobileNetV1的FasterRCNN实现中，此功能可获取层定义
def _get_mobilenet_conv_no_last_stride_defs(conv_depth_ratio_in_percentage):
if conv_depth_ratio_in_percentage not in [25, 50, 75, 100]:
raise ValueError(
'Only the following ratio percentages are supported: 25, 50, 75, 100')
conv_depth_ratio_in_percentage = float(conv_depth_ratio_in_percentage) / 100.0
channels = np.array([
32, 16, 24, 24, 32, 32, 32, 64, 64, 64, 64, 96, 96, 96, 160, 160, 160, 320, 1280
], dtype=np.float32)
channels = (channels * conv_depth_ratio_in_percentage).astype(np.int32)
return [
mobilenet_v1.Conv(kernel=[3, 3], stride=2, depth=channels[0]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[1]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=2, depth=channels[2]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[3]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=2, depth=channels[4]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[5]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=2, depth=channels[6]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[7]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[8]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[9]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[10]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[11]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[12]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[13])
]
该函数被调用，并获取层定义作为参数和
params['conv_defs'] = _get_mobilenet_conv_no_last_stride_defs(
conv_depth_ratio_in_percentage=self.
_conv_depth_ratio_in_percentage)
传递到另一个api获取建议
_, activations = mobilenet_v1.mobilenet_v1_base(
preprocessed_inputs,
final_endpoint='Conv2d_11_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
scope=scope,
**params)
我喜欢对MobileNetv2做同样的事情。
MobileNetV2的层定义如下。
V2_DEF = dict(
defaults={
# Note: these parameters of batch norm affect the architecture
# that's why they are here and not in training_scope.
(slim.batch_norm,): {'center': True, 'scale': True},
(slim.conv2d, slim.fully_connected, slim.separable_conv2d): {
'normalizer_fn': slim.batch_norm, 'activation_fn': tf.nn.relu6
},
(ops.expanded_conv,): {
'expansion_size': expand_input(6),
'split_expansion': 1,
'normalizer_fn': slim.batch_norm,
'residual': True
},
(slim.conv2d, slim.separable_conv2d): {'padding': 'SAME'}
},
spec=[
op(slim.conv2d, stride=2, num_outputs=32, kernel_size=[3, 3]),
op(ops.expanded_conv,
expansion_size=expand_input(1, divisible_by=1),
num_outputs=16),
op(ops.expanded_conv, stride=2, num_outputs=24),
op(ops.expanded_conv, stride=1, num_outputs=24),
op(ops.expanded_conv, stride=2, num_outputs=32),
op(ops.expanded_conv, stride=1, num_outputs=32),
op(ops.expanded_conv, stride=1, num_outputs=32),
op(ops.expanded_conv, stride=2, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=2, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=320),
op(slim.conv2d, stride=1, kernel_size=[1, 1], num_outputs=1280)
],
)
如何像MobileNetv1一样返回层定义
return [mobilenet_v1.Conv(kernel=[3, 3], stride=2, depth=channels[0]),
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[1]),
.....
mobilenet_v1.DepthSepConv(kernel=[3, 3], stride=1, depth=channels[13])]
对于MobileNetv2？ 我可以像下面这样返回吗？
return [
op(slim.conv2d, stride=2, num_outputs=32, kernel_size=[3, 3]),
op(ops.expanded_conv,
expansion_size=expand_input(1, divisible_by=1),
num_outputs=16),
op(ops.expanded_conv, stride=2, num_outputs=24),
op(ops.expanded_conv, stride=1, num_outputs=24),
op(ops.expanded_conv, stride=2, num_outputs=32),
op(ops.expanded_conv, stride=1, num_outputs=32),
op(ops.expanded_conv, stride=1, num_outputs=32),
op(ops.expanded_conv, stride=2, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=64),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=1, num_outputs=96),
op(ops.expanded_conv, stride=2, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=160),
op(ops.expanded_conv, stride=1, num_outputs=320),
op(slim.conv2d, stride=1, kernel_size=[1, 1], num_outputs=1280)
]