I am trying to replicate the quantization aware training process as explained in the pytorch example (beta) Static Quantization with Eager Mode in PyTorch — PyTorch Tutorials 1.10.1+cu102 documentation. The python notebook can be found here. The model code with slight modification is
from torch.quantization import QuantStub, DeQuantStub
def _make_divisible(v, divisor, min_value=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
:param v:
:param divisor:
:param min_value:
:return:
"""
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
class ConvBNReLU(nn.Sequential):
def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1):
padding = (kernel_size - 1) // 2
super(ConvBNReLU, self).__init__(
nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
nn.BatchNorm2d(out_planes, momentum=0.1),
# Replace with ReLU
nn.ReLU(inplace=False)
)
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, expand_ratio):
super(InvertedResidual, self).__init__()
self.stride = stride
assert stride in [1, 2]
hidden_dim = int(round(inp * expand_ratio))
self.use_res_connect = self.stride == 1 and inp == oup
layers = []
if expand_ratio != 1:
# pw
layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1))
layers.extend([
# dw
ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup, momentum=0.1),
])
self.conv = nn.Sequential(*layers)
# Replace torch.add with floatfunctional
self.skip_add = nn.quantized.FloatFunctional()
def forward(self, x):
if self.use_res_connect:
# return x+self.conv(x)
return self.skip_add.add_scalar(x, self.conv(x))
else:
return self.conv(x)
class MobileNetV2(nn.Module):
def __init__(self, num_classes=1000, width_mult=1.0, inverted_residual_setting=None, round_nearest=8):
"""
MobileNet V2 main class
Args:
num_classes (int): Number of classes
width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
inverted_residual_setting: Network structure
round_nearest (int): Round the number of channels in each layer to be a multiple of this number
Set to 1 to turn off rounding
"""
super(MobileNetV2, self).__init__()
block = InvertedResidual
input_channel = 32
last_channel = 1280
if inverted_residual_setting is None:
inverted_residual_setting = [
# t, c, n, s
[1, 16, 1, 1],
[6, 24, 2, 2],
[6, 32, 3, 2],
[6, 64, 4, 2],
[6, 96, 3, 1],
[6, 160, 3, 2],
[6, 320, 1, 1],
]
# only check the first element, assuming user knows t,c,n,s are required
if len(inverted_residual_setting) == 0 or len(inverted_residual_setting[0]) != 4:
raise ValueError("inverted_residual_setting should be non-empty "
"or a 4-element list, got {}".format(inverted_residual_setting))
# building first layer
input_channel = _make_divisible(input_channel * width_mult, round_nearest)
self.last_channel = _make_divisible(last_channel * max(1.0, width_mult), round_nearest)
features = [ConvBNReLU(3, input_channel, stride=2)]
# building inverted residual blocks
for t, c, n, s in inverted_residual_setting:
output_channel = _make_divisible(c * width_mult, round_nearest)
for i in range(n):
stride = s if i == 0 else 1
features.append(block(input_channel, output_channel, stride, expand_ratio=t))
input_channel = output_channel
# building last several layers
features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1))
# make it nn.Sequential
self.features = nn.Sequential(*features)
self.quant = QuantStub()
self.dequant = DeQuantStub()
# building classifier
self.classifier = nn.Sequential(
nn.Dropout(0.2),
nn.Linear(self.last_channel, num_classes),
)
# weight initialization
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out')
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.BatchNorm2d):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def forward(self, x):
x = self.quant(x)
x = self.features(x)
x = x.mean([2, 3])
x = self.classifier(x)
x = self.dequant(x)
return x
# Fuse Conv+BN and Conv+BN+Relu modules prior to quantization
# This operation does not change the numerics
def fuse_model(self):
for m in self.modules():
if type(m) == ConvBNReLU:
torch.quantization.fuse_modules(m, ['0', '1', '2'], inplace=True)
if type(m) == InvertedResidual:
for idx in range(len(m.conv)):
if type(m.conv[idx]) == nn.Conv2d:
torch.quantization.fuse_modules(m.conv, [str(idx), str(idx + 1)], inplace=True)
I am getting the error
/home/canservers/anaconda3/envs/torch/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
<ipython-input-11-a1ec4d8dc579> in forward(self, x)
140 x = x.mean([2, 3])
141 x = self.classifier(x)
--> 142 x = self.dequant(x)
143 return x
144
/home/canservers/anaconda3/envs/torch/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
/home/canservers/anaconda3/envs/torch/lib/python3.7/site-packages/torch/nn/quantized/modules/__init__.py in forward(self, Xq)
78
79 def forward(self, Xq):
---> 80 return Xq.dequantize()
81
82 @staticmethod
RuntimeError: Could not run 'aten::dequantize.self' with arguments from the 'CPU' backend. 'aten::dequantize.self' is only available for these backends: [QuantizedCPU, QuantizedCUDA, BackendSelect, Named, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode].
I am not sure what the issue is as the implementation is exactly similar to what has been shown on the official pytorch tutorial. The changes that I made are using qnnpack instead of fbgemm and setting the qconfig
qat_model.qconfig = torch.quantization.get_default_qat_qconfig('qnnpack')