def __init__(self, block_args, global_params, image_size=None):
super().__init__()
self._block_args = block_args
self._bn_mom = 1 - global_params.batch_norm_momentum # pytorch's difference from tensorflow
self._bn_eps = global_params.batch_norm_epsilon
self.has_se = (self._block_args.se_ratio is not None) and (0 < self._block_args.se_ratio <= 1)
self.id_skip = block_args.id_skip # whether to use skip connection and drop connect
# Expansion phase (Inverted Bottleneck)
inp = self._block_args.input_filters # number of input channels
oup = self._block_args.input_filters * self._block_args.expand_ratio # number of output channels
if self._block_args.expand_ratio != 1:
Conv2d = get_same_padding_conv2d(image_size=image_size)
self._expand_conv = Conv2d(in_channels=inp, out_channels=oup, kernel_size=1, bias=False)
self._bn0 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)
# Depthwise convolution phase
k = self._block_args.kernel_size
s = self._block_args.stride
Conv2d = get_same_padding_conv2d(image_size=image_size)
self._depthwise_conv = Conv2d(
in_channels=oup, out_channels=oup, groups=oup, # groups makes it depthwise
kernel_size=k, stride=s, bias=False)
self._bn1 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps)
image_size = calculate_output_image_size(image_size, s)
# Pointwise convolution phase
final_oup = self._block_args.output_filters
Conv2d = get_same_padding_conv2d(image_size=image_size)
self._project_conv = Conv2d(in_channels=oup, out_channels=final_oup, kernel_size=1, bias=False)
self._bn2 = nn.BatchNorm2d(num_features=final_oup, momentum=self._bn_mom, eps=self._bn_eps)
self._act = nn.ReLU6()
def __init__(self, blocks_args=None, global_params=None):
super().__init__()
assert isinstance(blocks_args, list), 'blocks_args should be a list'
assert len(blocks_args) > 0, 'block args must be greater than 0'
self._global_params = global_params
self._blocks_args = blocks_args
# Batch norm parameters
bn_mom = 1 - self._global_params.batch_norm_momentum
bn_eps = self._global_params.batch_norm_epsilon
# Get stem static or dynamic convolution depending on image size
image_size = global_params.image_size
Conv2d = get_same_padding_conv2d(image_size=image_size)
# Stem
in_channels = 3 # rgb
out_channels = round_filters(32, self._global_params) # number of output channels
self._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
self._bn0 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)
image_size = calculate_output_image_size(image_size, 2)
# Build blocks
self._blocks = nn.ModuleList([])
for block_args in self._blocks_args:
# Update block input and output filters based on depth multiplier.
block_args = block_args._replace(
input_filters=round_filters(block_args.input_filters, self._global_params),
output_filters=round_filters(block_args.output_filters, self._global_params),
num_repeat=round_repeats(block_args.num_repeat, self._global_params)
)
# The first block needs to take care of stride and filter size increase.
self._blocks.append(MBConvBlock(block_args, self._global_params, image_size=image_size))
image_size = calculate_output_image_size(image_size, block_args.stride)
if block_args.num_repeat > 1: # modify block_args to keep same output size
block_args = block_args._replace(input_filters=block_args.output_filters, stride=1)
for _ in range(block_args.num_repeat - 1):
self._blocks.append(MBConvBlock(block_args, self._global_params, image_size=image_size))
# Head
in_channels = block_args.output_filters # output of final block
out_channels = round_filters(1280, self._global_params)
Conv2d = get_same_padding_conv2d(image_size=image_size)
self._conv_head = Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
self._bn1 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)
# Final linear layer
self._avg_pooling = nn.AdaptiveAvgPool2d(1)
self._dropout = nn.Dropout(self._global_params.dropout_rate)
self._fc = nn.Linear(out_channels, self._global_params.num_classes)
self._act = nn.ReLU6()
def _change_in_channels(self, in_channels):
"""Adjust model's first convolution layer to in_channels, if in_channels not equals 3.
Args:
in_channels (int): Input data's channel number.
"""
if in_channels != 3:
Conv2d = get_same_padding_conv2d(image_size=self._global_params.image_size)
out_channels = round_filters(32, self._global_params)
self._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)