mirror of https://github.com/Jittor/Jittor
113 lines
4.6 KiB
Python
113 lines
4.6 KiB
Python
# ***************************************************************
|
|
# Copyright (c) 2021 Jittor. All Rights Reserved.
|
|
# Maintainers:
|
|
# Wenyang Zhou <576825820@qq.com>
|
|
# Dun Liang <randonlang@gmail.com>.
|
|
#
|
|
# This file is subject to the terms and conditions defined in
|
|
# file 'LICENSE.txt', which is part of this source code package.
|
|
# ***************************************************************
|
|
# This model is generated by pytorch converter.
|
|
|
|
import jittor as jt
|
|
from jittor import nn
|
|
__all__ = ['MNASNet', 'mnasnet0_5', 'mnasnet0_75', 'mnasnet1_0', 'mnasnet1_3']
|
|
_BN_MOMENTUM = (1 - 0.9997)
|
|
|
|
class _InvertedResidual(nn.Module):
|
|
|
|
def __init__(self, in_ch, out_ch, kernel_size, stride, expansion_factor, bn_momentum=0.1):
|
|
super(_InvertedResidual, self).__init__()
|
|
assert (stride in [1, 2])
|
|
assert (kernel_size in [3, 5])
|
|
mid_ch = (in_ch * expansion_factor)
|
|
self.apply_residual = ((in_ch == out_ch) and (stride == 1))
|
|
self.layers = nn.Sequential(nn.Conv(in_ch, mid_ch, 1, bias=False), nn.BatchNorm(mid_ch, momentum=bn_momentum), nn.Relu(), nn.Conv(mid_ch, mid_ch, kernel_size, padding=(kernel_size // 2), stride=stride, groups=mid_ch, bias=False), nn.BatchNorm(mid_ch, momentum=bn_momentum), nn.Relu(), nn.Conv(mid_ch, out_ch, 1, bias=False), nn.BatchNorm(out_ch, momentum=bn_momentum))
|
|
|
|
def execute(self, input):
|
|
if self.apply_residual:
|
|
return (self.layers(input) + input)
|
|
else:
|
|
return self.layers(input)
|
|
|
|
def _stack(in_ch, out_ch, kernel_size, stride, exp_factor, repeats, bn_momentum):
|
|
assert (repeats >= 1)
|
|
first = _InvertedResidual(in_ch, out_ch, kernel_size, stride, exp_factor, bn_momentum=bn_momentum)
|
|
remaining = []
|
|
for _ in range(1, repeats):
|
|
remaining.append(_InvertedResidual(out_ch, out_ch, kernel_size, 1, exp_factor, bn_momentum=bn_momentum))
|
|
return nn.Sequential(first, *remaining)
|
|
|
|
def _round_to_multiple_of(val, divisor, round_up_bias=0.9):
|
|
assert (0.0 < round_up_bias < 1.0)
|
|
new_val = max(divisor, ((int((val + (divisor / 2))) // divisor) * divisor))
|
|
return (new_val if (new_val >= (round_up_bias * val)) else (new_val + divisor))
|
|
|
|
def _get_depths(alpha):
|
|
depths = [24, 40, 80, 96, 192, 320]
|
|
return [_round_to_multiple_of((depth * alpha), 8) for depth in depths]
|
|
|
|
class MNASNet(nn.Module):
|
|
""" MNASNet model architecture. version=2.
|
|
|
|
Args:
|
|
|
|
* alpha: Depth multiplier.
|
|
* num_classes: Number of classes. Default: 1000.
|
|
* dropout: Dropout probability of dropout layer.
|
|
"""
|
|
_version = 2
|
|
|
|
def __init__(self, alpha, num_classes=1000, dropout=0.2):
|
|
super(MNASNet, self).__init__()
|
|
assert (alpha > 0.0)
|
|
self.alpha = alpha
|
|
self.num_classes = num_classes
|
|
depths = _get_depths(alpha)
|
|
layers = [
|
|
nn.Conv(3, 32, 3, padding=1, stride=2, bias=False),
|
|
nn.BatchNorm(32, momentum=_BN_MOMENTUM),
|
|
nn.Relu(),
|
|
nn.Conv(32, 32, 3, padding=1, stride=1, groups=32, bias=False),
|
|
nn.BatchNorm(32, momentum=_BN_MOMENTUM),
|
|
nn.Relu(),
|
|
nn.Conv(32, 16, 1, padding=0, stride=1, bias=False),
|
|
nn.BatchNorm(16, momentum=_BN_MOMENTUM),
|
|
_stack(16, depths[0], 3, 2, 3, 3, _BN_MOMENTUM),
|
|
_stack(depths[0], depths[1], 5, 2, 3, 3, _BN_MOMENTUM),
|
|
_stack(depths[1], depths[2], 5, 2, 6, 3, _BN_MOMENTUM),
|
|
_stack(depths[2], depths[3], 3, 1, 6, 2, _BN_MOMENTUM),
|
|
_stack(depths[3], depths[4], 5, 2, 6, 4, _BN_MOMENTUM),
|
|
_stack(depths[4], depths[5], 3, 1, 6, 1, _BN_MOMENTUM),
|
|
nn.Conv(depths[5], 1280, 1, padding=0, stride=1, bias=False),
|
|
nn.BatchNorm(1280, momentum=_BN_MOMENTUM),
|
|
nn.Relu()
|
|
]
|
|
self.layers = nn.Sequential(*layers)
|
|
self.classifier = nn.Sequential(nn.Dropout(p=dropout), nn.Linear(1280, num_classes))
|
|
|
|
def execute(self, x):
|
|
x = self.layers(x)
|
|
x = x.mean([2, 3])
|
|
return self.classifier(x)
|
|
|
|
def mnasnet0_5(pretrained=False, **kwargs):
|
|
model = MNASNet(0.5, **kwargs)
|
|
if pretrained: model.load("jittorhub://mnasnet0_5.pkl")
|
|
return model
|
|
|
|
def mnasnet0_75(pretrained=False, **kwargs):
|
|
model = MNASNet(0.75, **kwargs)
|
|
if pretrained: model.load("jittorhub://mnasnet0_75.pkl")
|
|
return model
|
|
|
|
def mnasnet1_0(pretrained=False, **kwargs):
|
|
model = MNASNet(1.0, **kwargs)
|
|
if pretrained: model.load("jittorhub://mnasnet1_0.pkl")
|
|
return model
|
|
|
|
def mnasnet1_3(pretrained=False, **kwargs):
|
|
model = MNASNet(1.3, **kwargs)
|
|
if pretrained: model.load("jittorhub://mnasnet1_3.pkl")
|
|
return model
|