import nncf
import openvino as ov
import torch
from torchvision import datasets, transforms

# Instantiate your uncompressed model
model = ov.Core().read_model("/model_path")

# Provide validation part of the dataset to collect statistics needed for the compression algorithm
val_dataset = datasets.ImageFolder("/path", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(val_dataset, batch_size=1)

# Step 1: Initialize transformation function
def transform_fn(data_item):
    images, _ = data_item
    return images

# Step 2: Initialize NNCF Dataset
calibration_dataset = nncf.Dataset(dataset_loader, transform_fn)
# Step 3: Run the quantization pipeline
quantized_model = nncf.quantize(model, calibration_dataset)

import nncf
import torch
from torchvision import datasets, models

# Instantiate your uncompressed model
model = models.mobilenet_v2()

# Provide validation part of the dataset to collect statistics needed for the compression algorithm
val_dataset = datasets.ImageFolder("/path", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(val_dataset)

# Step 1: Initialize the transformation function
def transform_fn(data_item):
    images, _ = data_item
    return images

# Step 2: Initialize NNCF Dataset
calibration_dataset = nncf.Dataset(dataset_loader, transform_fn)
# Step 3: Run the quantization pipeline
quantized_model = nncf.quantize(model, calibration_dataset)

NOTE If the Post-Training Quantization algorithm does not meet quality requirements you can fine-tune the quantized pytorch model. You can find an example of the Quantization-Aware training pipeline for a pytorch model here.

import nncf
import torch.fx
from torchvision import datasets, models

# Instantiate your uncompressed model
model = models.mobilenet_v2()

# Provide validation part of the dataset to collect statistics needed for the compression algorithm
val_dataset = datasets.ImageFolder("/path", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(val_dataset)

# Step 1: Initialize the transformation function
def transform_fn(data_item):
    images, _ = data_item
    return images

# Step 2: Initialize NNCF Dataset
calibration_dataset = nncf.Dataset(dataset_loader, transform_fn)

# Step 3: Export model to TorchFX
input_shape = (1, 3, 224, 224)
fx_model = torch.export.export_for_training(model, args=(ex_input,)).module()
# or
# fx_model = torch.export.export(model, args=(ex_input,)).module()

# Step 4: Run the quantization pipeline
quantized_fx_model = nncf.quantize(fx_model, calibration_dataset)

import onnx
import nncf
import torch
from torchvision import datasets

# Instantiate your uncompressed model
onnx_model = onnx.load_model("/model_path")

# Provide validation part of the dataset to collect statistics needed for the compression algorithm
val_dataset = datasets.ImageFolder("/path", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(val_dataset, batch_size=1)

# Step 1: Initialize transformation function
input_name = onnx_model.graph.input[0].name
def transform_fn(data_item):
    images, _ = data_item
    return {input_name: images.numpy()}

# Step 2: Initialize NNCF Dataset
calibration_dataset = nncf.Dataset(dataset_loader, transform_fn)
# Step 3: Run the quantization pipeline
quantized_model = nncf.quantize(onnx_model, calibration_dataset)

import nncf
import torch
from torchvision import datasets, models

# Instantiate your uncompressed model
model = models.mobilenet_v2()

# Provide validation part of the dataset to collect statistics needed for the compression algorithm
val_dataset = datasets.ImageFolder("/path", transform=transforms.Compose([transforms.ToTensor()]))
dataset_loader = torch.utils.data.DataLoader(val_dataset)

# Step 1: Initialize the transformation function
def transform_fn(data_item):
    images, _ = data_item
    return images

# Step 2: Initialize NNCF Dataset
calibration_dataset = nncf.Dataset(dataset_loader, transform_fn)
# Step 3: Run the quantization pipeline
quantized_model = nncf.quantize(model, calibration_dataset)

# Now use compressed_model as a usual torch.nn.Module
# to fine-tune compression parameters along with the model weights

# Save quantization modules and the quantized model parameters
checkpoint = {
    'state_dict': model.state_dict(),
    'nncf_config': nncf.torch.get_config(model),
    ... # the rest of the user-defined objects to save
}
torch.save(checkpoint, path_to_checkpoint)

# ...

# Load quantization modules and the quantized model parameters
resuming_checkpoint = torch.load(path_to_checkpoint)
nncf_config = resuming_checkpoint['nncf_config']
state_dict = resuming_checkpoint['state_dict']

quantized_model = nncf.torch.load_from_config(model, nncf_config)
quantized_model.load_state_dict(state_dict)
# ... the rest of the usual PyTorch-powered training pipeline