Home

Awesome

Fine-tune pretrained Convolutional Neural Networks with PyTorch.

PyPI CircleCI codecov.io

Features

Supported architectures and models

From the torchvision package:

From the Pretrained models for PyTorch package:

Requirements

Installation

pip install cnn_finetune

Major changes:

Version 0.4

Example usage:

Make a model with ImageNet weights for 10 classes

from cnn_finetune import make_model

model = make_model('resnet18', num_classes=10, pretrained=True)

Make a model with Dropout

model = make_model('nasnetalarge', num_classes=10, pretrained=True, dropout_p=0.5)

Make a model with Global Max Pooling instead of Global Average Pooling

import torch.nn as nn

model = make_model('inceptionresnetv2', num_classes=10, pretrained=True, pool=nn.AdaptiveMaxPool2d(1))

Make a VGG16 model that takes images of size 256x256 pixels

VGG and AlexNet models use fully-connected layers, so you have to additionally pass the input size of images when constructing a new model. This information is needed to determine the input size of fully-connected layers.

model = make_model('vgg16', num_classes=10, pretrained=True, input_size=(256, 256))

Make a VGG16 model that takes images of size 256x256 pixels and uses a custom classifier

import torch.nn as nn

def make_classifier(in_features, num_classes):
    return nn.Sequential(
        nn.Linear(in_features, 4096),
        nn.ReLU(inplace=True),
        nn.Linear(4096, num_classes),
    )

model = make_model('vgg16', num_classes=10, pretrained=True, input_size=(256, 256), classifier_factory=make_classifier)

Show preprocessing that was used to train the original model on ImageNet

>> model = make_model('resnext101_64x4d', num_classes=10, pretrained=True)
>> print(model.original_model_info)
ModelInfo(input_space='RGB', input_size=[3, 224, 224], input_range=[0, 1], mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
>> print(model.original_model_info.mean)
[0.485, 0.456, 0.406]

CIFAR10 Example

See examples/cifar10.py file (requires PyTorch 1.1+).