The reason to create this repo is that there are not many online resources that provide sample codes for performing fine-tuning, and that there is not a centralized place where we can easily download ImageNet pretrained models for common ConvNet architectures such as VGG, Inception, ResNet, and DenseNet.
See this for a comprehensive treatment of fine-tuning Deep Learning Models in Keras
|VGG-16|
model = vgg16_model(img_rows, img_cols, channel, nb_classes, freeze)
|VGG-19|
model = vgg19_model(img_rows, img_cols, channel, nb_classes)
|Inception-V3|
model = inception_v3_model(img_rows, img_cols, channel, nb_classes)
|Inception-V4|
model = inception_v4_model(img_rows, img_cols, channel, nb_classes, dropout_keep_prob=0.2)
|ResNet-50/ResNet-101/ResNet-152|
model = resnet50_model(img_rows, img_cols, channel, nb_classes)
|DenseNet-121/DenseNet-161/DenseNet-169|
model = densenet121_model(img_rows, img_cols, color_type=channel, num_classes=nb_classes)
| Network | Theano | Tensorflow |
|---|---|---|
| VGG-16 | model (553 MB) | model (553 MB) |
| VGG-19 | model (575 MB) | model (575 MB) |
| GoogLeNet (Inception-V1) | model (54 MB) | - |
| Inception-V3 | model (95 MB) | model (95 MB) |
| Inception-V4 | model (172 MB) | model (172 MB) |
| ResNet-50 | model (103 MB) | model (103 MB) |
| ResNet-101 | model (179 MB) | model (179 MB) |
| ResNet-152 | model (243 MB) | model (243 MB) |
| DenseNet-121 | model (32 MB) | model (32 MB) |
| DenseNet-169 | model (56 MB) | model (56 MB) |
| DenseNet-161 | model (112 MB) | model (112 MB) |
- Keras 2.0.3
- TensorFlow 1.1.0