量化

import torch
from torch.ao.quantization import (
  get_default_qconfig_mapping,
  get_default_qat_qconfig_mapping,
  QConfigMapping,
)
import torch.ao.quantization.quantize_fx as quantize_fx
import copy

model_fp = UserModel()

#
# post training dynamic/weight_only quantization
#

# we need to deepcopy if we still want to keep model_fp unchanged after quantization since quantization apis change the input model
model_to_quantize = copy.deepcopy(model_fp)
model_to_quantize.eval()
qconfig_mapping = QConfigMapping().set_global(torch.ao.quantization.default_dynamic_qconfig)
# a tuple of one or more example inputs are needed to trace the model
example_inputs = (input_fp32)
# prepare
model_prepared = quantize_fx.prepare_fx(model_to_quantize, qconfig_mapping, example_inputs)
# no calibration needed when we only have dynamic/weight_only quantization
# quantize
model_quantized = quantize_fx.convert_fx(model_prepared)

#
# post training static quantization
#

model_to_quantize = copy.deepcopy(model_fp)
qconfig_mapping = get_default_qconfig_mapping("qnnpack")
model_to_quantize.eval()
# prepare
model_prepared = quantize_fx.prepare_fx(model_to_quantize, qconfig_mapping, example_inputs)
# calibrate (not shown)
# quantize
model_quantized = quantize_fx.convert_fx(model_prepared)

#
# quantization aware training for static quantization
#

model_to_quantize = copy.deepcopy(model_fp)
qconfig_mapping = get_default_qat_qconfig_mapping("qnnpack")
model_to_quantize.train()
# prepare
model_prepared = quantize_fx.prepare_qat_fx(model_to_quantize, qconfig_mapping, example_inputs)
# training loop (not shown)
# quantize
model_quantized = quantize_fx.convert_fx(model_prepared)

#
# fusion
#
model_to_quantize = copy.deepcopy(model_fp)
model_fused = quantize_fx.fuse_fx(model_to_quantize)

import torch
from torch.ao.quantization.quantize_pt2e import prepare_pt2e
from torch._export import capture_pre_autograd_graph
from torch.ao.quantization.quantizer import (
    XNNPACKQuantizer,
    get_symmetric_quantization_config,
)

class M(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = torch.nn.Linear(5, 10)

   def forward(self, x):
       return self.linear(x)

# initialize a floating point model
float_model = M().eval()

# define calibration function
def calibrate(model, data_loader):
    model.eval()
    with torch.no_grad():
        for image, target in data_loader:
            model(image)

# Step 1. program capture
# NOTE: this API will be updated to torch.export API in the future, but the captured
# result should mostly stay the same
m = capture_pre_autograd_graph(m, *example_inputs)
# we get a model with aten ops

# Step 2. quantization
# backend developer will write their own Quantizer and expose methods to allow
# users to express how they
# want the model to be quantized
quantizer = XNNPACKQuantizer().set_global(get_symmetric_quantization_config())
# or prepare_qat_pt2e for Quantization Aware Training
m = prepare_pt2e(m, quantizer)

# run calibration
# calibrate(m, sample_inference_data)
m = convert_pt2e(m)

# Step 3. lowering
# lower to target backend

import torch
import torch.ao.nn.quantized as nnq
from torch.ao.quantization import QConfigMapping
import torch.ao.quantization.quantize_fx

# original fp32 module to replace
class CustomModule(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = torch.nn.Linear(3, 3)

    def forward(self, x):
        return self.linear(x)

# custom observed module, provided by user
class ObservedCustomModule(torch.nn.Module):
    def __init__(self, linear):
        super().__init__()
        self.linear = linear

    def forward(self, x):
        return self.linear(x)

    @classmethod
    def from_float(cls, float_module):
        assert hasattr(float_module, 'qconfig')
        observed = cls(float_module.linear)
        observed.qconfig = float_module.qconfig
        return observed

# custom quantized module, provided by user
class StaticQuantCustomModule(torch.nn.Module):
    def __init__(self, linear):
        super().__init__()
        self.linear = linear

    def forward(self, x):
        return self.linear(x)

    @classmethod
    def from_observed(cls, observed_module):
        assert hasattr(observed_module, 'qconfig')
        assert hasattr(observed_module, 'activation_post_process')
        observed_module.linear.activation_post_process = \
            observed_module.activation_post_process
        quantized = cls(nnq.Linear.from_float(observed_module.linear))
        return quantized

#
# example API call (Eager mode quantization)
#

m = torch.nn.Sequential(CustomModule()).eval()
prepare_custom_config_dict = {
    "float_to_observed_custom_module_class": {
        CustomModule: ObservedCustomModule
    }
}
convert_custom_config_dict = {
    "observed_to_quantized_custom_module_class": {
        ObservedCustomModule: StaticQuantCustomModule
    }
}
m.qconfig = torch.ao.quantization.default_qconfig
mp = torch.ao.quantization.prepare(
    m, prepare_custom_config_dict=prepare_custom_config_dict)
# calibration (not shown)
mq = torch.ao.quantization.convert(
    mp, convert_custom_config_dict=convert_custom_config_dict)
#
# example API call (FX graph mode quantization)
#
m = torch.nn.Sequential(CustomModule()).eval()
qconfig_mapping = QConfigMapping().set_global(torch.ao.quantization.default_qconfig)
prepare_custom_config_dict = {
    "float_to_observed_custom_module_class": {
        "static": {
            CustomModule: ObservedCustomModule,
        }
    }
}
convert_custom_config_dict = {
    "observed_to_quantized_custom_module_class": {
        "static": {
            ObservedCustomModule: StaticQuantCustomModule,
        }
    }
}
mp = torch.ao.quantization.quantize_fx.prepare_fx(
    m, qconfig_mapping, torch.randn(3,3), prepare_custom_config=prepare_custom_config_dict)
# calibration (not shown)
mq = torch.ao.quantization.quantize_fx.convert_fx(
    mp, convert_custom_config=convert_custom_config_dict)

RuntimeError: Could not run 'quantized::some_operator' with arguments from the 'CPU' backend...

class M(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.quant = torch.ao.quantization.QuantStub()
        self.conv = torch.nn.Conv2d(1, 1, 1)

    def forward(self, x):
        # during the convert step, this will be replaced with a
        # `quantize_per_tensor` call
        x = self.quant(x)
        x = self.conv(x)
        return x

RuntimeError: Could not run 'aten::thnn_conv2d_forward' with arguments from the 'QuantizedCPU' backend.

class M(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.quant = torch.ao.quantization.QuantStub()
        self.conv1 = torch.nn.Conv2d(1, 1, 1)
        # this module will not be quantized (see `qconfig = None` logic below)
        self.conv2 = torch.nn.Conv2d(1, 1, 1)
        self.dequant = torch.ao.quantization.DeQuantStub()

    def forward(self, x):
        # during the convert step, this will be replaced with a
        # `quantize_per_tensor` call
        x = self.quant(x)
        x = self.conv1(x)
        # during the convert step, this will be replaced with a
        # `dequantize` call
        x = self.dequant(x)
        x = self.conv2(x)
        return x

m = M()
m.qconfig = some_qconfig
# turn off quantization for conv2
m.conv2.qconfig = None

AttributeError: 'LinearPackedParams' object has no attribute '_modules'

class M(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(5, 5)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.linear(x)
        x = self.relu(x)
        return x

m = M().eval()
prepare_orig = prepare_fx(m, {'' : default_qconfig})
prepare_orig(torch.rand(5, 5))
quantized_orig = convert_fx(prepare_orig)

# Save/load using state_dict
b = io.BytesIO()
torch.save(quantized_orig.state_dict(), b)

m2 = M().eval()
prepared = prepare_fx(m2, {'' : default_qconfig})
quantized = convert_fx(prepared)
b.seek(0)
quantized.load_state_dict(torch.load(b))

# Note: using the same model M from previous example
m = M().eval()
prepare_orig = prepare_fx(m, {'' : default_qconfig})
prepare_orig(torch.rand(5, 5))
quantized_orig = convert_fx(prepare_orig)

# save/load using scripted model
scripted = torch.jit.script(quantized_orig)
b = io.BytesIO()
torch.jit.save(scripted, b)
b.seek(0)
scripted_quantized = torch.jit.load(b)

torch.fx.proxy.TraceError: symbolically traced variables cannot be used as inputs to control flow