def __init__(self, in_channel, out_channel, stride=1):
super(ResidualBlock, self).__init__()
channel = out_channel // self.expansion
self.conv1 = ConvBNReLU(in_channel, channel, kernel_size=1, stride=1)
self.conv2 = ConvBNReLU(channel, channel, kernel_size=3, stride=stride)
self.conv3 = nn.SequentialCell([
Conv2dBnFoldQuant(channel,
out_channel,
fake=_fake,
quant_config=_quant_config,
kernel_size=1,
stride=1,
pad_mode='same',
padding=0),
FakeQuantWithMinMaxObserver(
ema=True, ema_decay=_ema_decay, symmetric=False)
]) if _fake else Conv2dBnFoldQuant(channel,
out_channel,
fake=_fake,
quant_config=_quant_config,
kernel_size=1,
stride=1,
pad_mode='same',
padding=0)
self.down_sample = False
if stride != 1 or in_channel != out_channel:
self.down_sample = True
self.down_sample_layer = None
if self.down_sample:
self.down_sample_layer = nn.SequentialCell([
Conv2dBnFoldQuant(in_channel,
out_channel,
quant_config=_quant_config,
kernel_size=1,
stride=stride,
pad_mode='same',
padding=0),
FakeQuantWithMinMaxObserver(
ema=True, ema_decay=_ema_decay, symmetric=False)
]) if _fake else Conv2dBnFoldQuant(in_channel,
out_channel,
fake=_fake,
quant_config=_quant_config,
kernel_size=1,
stride=stride,
pad_mode='same',
padding=0)
self.add = nn.TensorAddQuant()
self.relu = P.ReLU()
def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1):
super(ConvBNReLU, self).__init__()
padding = (kernel_size - 1) // 2
conv = Conv2dBnFoldQuant(in_planes, out_planes, kernel_size, stride, pad_mode='pad', padding=padding,
group=groups, fake=_fake, quant_config=_quant_config)
layers = [conv, nn.ActQuant(nn.ReLU())] if _fake else [conv, nn.ReLU()]
self.features = nn.SequentialCell(layers)