Spaces:
Runtime error
Runtime error
File size: 5,684 Bytes
0b7b08a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright (c) Megvii Inc. All rights reserved.
import megengine.module as M
from .network_blocks import BaseConv, CSPLayer, DWConv, Focus, ResLayer, SPPBottleneck
class Darknet(M.Module):
# number of blocks from dark2 to dark5.
depth2blocks = {21: [1, 2, 2, 1], 53: [2, 8, 8, 4]}
def __init__(
self, depth, in_channels=3, stem_out_channels=32, out_features=("dark3", "dark4", "dark5"),
):
"""
Args:
depth (int): depth of darknet used in model, usually use [21, 53] for this param.
in_channels (int): number of input channels, for example, use 3 for RGB image.
stem_out_channels (int): number of output channels of darknet stem.
It decides channels of darknet layer2 to layer5.
out_features (Tuple[str]): desired output layer name.
"""
super().__init__()
assert out_features, "please provide output features of Darknet"
self.out_features = out_features
self.stem = M.Sequential(
BaseConv(in_channels, stem_out_channels, ksize=3, stride=1, act="lrelu"),
*self.make_group_layer(stem_out_channels, num_blocks=1, stride=2),
)
in_channels = stem_out_channels * 2 # 64
num_blocks = Darknet.depth2blocks[depth]
# create darknet with `stem_out_channels` and `num_blocks` layers.
# to make model structure more clear, we don't use `for` statement in python.
self.dark2 = M.Sequential(*self.make_group_layer(in_channels, num_blocks[0], stride=2))
in_channels *= 2 # 128
self.dark3 = M.Sequential(*self.make_group_layer(in_channels, num_blocks[1], stride=2))
in_channels *= 2 # 256
self.dark4 = M.Sequential(*self.make_group_layer(in_channels, num_blocks[2], stride=2))
in_channels *= 2 # 512
self.dark5 = M.Sequential(
*self.make_group_layer(in_channels, num_blocks[3], stride=2),
*self.make_spp_block([in_channels, in_channels * 2], in_channels * 2),
)
def make_group_layer(self, in_channels: int, num_blocks: int, stride: int = 1):
"starts with conv layer then has `num_blocks` `ResLayer`"
return [
BaseConv(in_channels, in_channels * 2, ksize=3, stride=stride, act="lrelu"),
*[(ResLayer(in_channels * 2)) for _ in range(num_blocks)]
]
def make_spp_block(self, filters_list, in_filters):
m = M.Sequential(
*[
BaseConv(in_filters, filters_list[0], 1, stride=1, act="lrelu"),
BaseConv(filters_list[0], filters_list[1], 3, stride=1, act="lrelu"),
SPPBottleneck(
in_channels=filters_list[1],
out_channels=filters_list[0],
activation="lrelu"
),
BaseConv(filters_list[0], filters_list[1], 3, stride=1, act="lrelu"),
BaseConv(filters_list[1], filters_list[0], 1, stride=1, act="lrelu"),
]
)
return m
def forward(self, x):
outputs = {}
x = self.stem(x)
outputs["stem"] = x
x = self.dark2(x)
outputs["dark2"] = x
x = self.dark3(x)
outputs["dark3"] = x
x = self.dark4(x)
outputs["dark4"] = x
x = self.dark5(x)
outputs["dark5"] = x
return {k: v for k, v in outputs.items() if k in self.out_features}
class CSPDarknet(M.Module):
def __init__(
self, dep_mul, wid_mul,
out_features=("dark3", "dark4", "dark5"),
depthwise=False, act="silu",
):
super().__init__()
assert out_features, "please provide output features of Darknet"
self.out_features = out_features
Conv = DWConv if depthwise else BaseConv
base_channels = int(wid_mul * 64) # 64
base_depth = max(round(dep_mul * 3), 1) # 3
# stem
self.stem = Focus(3, base_channels, ksize=3, act=act)
# dark2
self.dark2 = M.Sequential(
Conv(base_channels, base_channels * 2, 3, 2, act=act),
CSPLayer(
base_channels * 2, base_channels * 2,
n=base_depth, depthwise=depthwise, act=act
),
)
# dark3
self.dark3 = M.Sequential(
Conv(base_channels * 2, base_channels * 4, 3, 2, act=act),
CSPLayer(
base_channels * 4, base_channels * 4,
n=base_depth * 3, depthwise=depthwise, act=act,
),
)
# dark4
self.dark4 = M.Sequential(
Conv(base_channels * 4, base_channels * 8, 3, 2, act=act),
CSPLayer(
base_channels * 8, base_channels * 8,
n=base_depth * 3, depthwise=depthwise, act=act,
),
)
# dark5
self.dark5 = M.Sequential(
Conv(base_channels * 8, base_channels * 16, 3, 2, act=act),
SPPBottleneck(base_channels * 16, base_channels * 16, activation=act),
CSPLayer(
base_channels * 16, base_channels * 16, n=base_depth,
shortcut=False, depthwise=depthwise, act=act,
),
)
def forward(self, x):
outputs = {}
x = self.stem(x)
outputs["stem"] = x
x = self.dark2(x)
outputs["dark2"] = x
x = self.dark3(x)
outputs["dark3"] = x
x = self.dark4(x)
outputs["dark4"] = x
x = self.dark5(x)
outputs["dark5"] = x
return {k: v for k, v in outputs.items() if k in self.out_features}
|