Classification models 1D Zoo - Keras and TF.Keras
This repository contains 1D variants of popular CNN models for classification like ResNets, DenseNets, VGG, etc. It also contains weights obtained by converting ImageNet weights from the same 2D models. It can be useful for classification of audio or some timeseries data.
This repository is based on great classification_models repo by @qubvel
Architectures:
- VGG [16, 19]
- ResNet [18, 34, 50, 101, 152]
- ResNeXt [50, 101]
- SE-ResNet [18, 34, 50, 101, 152]
- SE-ResNeXt [50, 101]
- SE-Net [154]
- DenseNet [121, 169, 201]
- Inception ResNet V2
- Inception V3
- MobileNet
- MobileNet v2
- EfficientNet
- EfficientNet v2
Installation
pip install classification-models-1D
Examples
Loading model:
from classification_models_1D.tfkeras import Classifiers
ResNet18, preprocess_input = Classifiers.get('resnet18')
model = ResNet18(input_shape=(224*224, 2), weights='imagenet')
All possible nets for Classifiers.get() method: 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'seresnet18', 'seresnet34', 'seresnet50', 'seresnet101', 'seresnet152', 'seresnext50', 'seresnext101', 'senet154', 'resnext50', 'resnext101', 'vgg16', 'vgg19', 'densenet121', 'densenet169', 'densenet201', 'mobilenet', 'mobilenetv2', 'inceptionresnetv2', 'inceptionv3', 'EfficientNetB0', 'EfficientNetB1', 'EfficientNetB2', 'EfficientNetB3', 'EfficientNetB4', 'EfficientNetB5', 'EfficientNetB6', 'EfficientNetB7', 'EfficientNetV2B0', 'EfficientNetV2B1', 'EfficientNetV2B2', 'EfficientNetV2B3', 'EfficientNetV2S', 'EfficientNetV2M', 'EfficientNetV2L'
Convert imagenet weights (2D -> 1D)
Code to convert 2D imagenet weights to 1D variant is available here: convert_imagenet_weights_to_1D_models.py.
How to choose input shape
If initial 2D model had shape (224, 224, 3) then you can use shape (W, 3) where W ~= 224*224, so something like (224*224, 2) will be ok.
Additional features
- Default pooling/stride size for 1D models set equal to 4 to match (2, 2) pooling for 2D nets. Kernel size by default is 9 to match (3, 3) kernels. You can change it for your needs using parameters
stride_sizeandkernel_size. Example:
from classification_models_1D.tfkeras import Classifiers
ResNet18, preprocess_input = Classifiers.get('resnet18')
model = ResNet18(
input_shape=(224*224, 2),
stride_size=6,
kernel_size=3,
weights=None
)
- You can set different pooling for each pooling block. For example you don't need pooling at first convolution. You can do it using tuple as value for
stride_size:
from classification_models_1D.tfkeras import Classifiers
ResNet18, preprocess_input = Classifiers.get('resnet34')
model = ResNet18(
input_shape=(65536, 2),
stride_size=(1, 4, 4, 8, 8),
kernel_size=9,
weights='imagenet'
)
- For some models like (resnet, resnext, senet, vgg16, vgg19, densenet) it's possible to change number of blocks/poolings. For example if you want to switch to pooling/stride = 2 but make more poolings overall. You can do it like that:
from classification_models_1D.tfkeras import Classifiers
ResNet18, preprocess_input = Classifiers.get('resnet34')
model = ResNet18(
input_shape=(224*224, 2),
include_top=False,
weights=None,
stride_size=(2, 4, 4, 4, 2, 2, 2, 2),
kernel_size=3,
repetitions=(2, 2, 2, 2, 2, 2, 2),
init_filters=16,
)
Note: Since number of filters grows 2 times, you can set initial number of filters with init_filters parameter.
Pretrained weights
Imagenet
Imagenet weights available for all models except ('inceptionresnetv2', 'inceptionv3'). They available only for kernel_size == 3 or kernel_size == 9 and 2 channel input (e.g. stereo sound). Weights were converted from 2D models to 1D variant. Weights can be loaded with any pooling scheme.
Related repositories
- https://github.com/qubvel/classification_models - original 2D repo
- https://github.com/ZFTurbo/classification_models_3D - 3D variant repo
ToDo List
- Create pretrained weights obtained on AudioSet
14 Sep 13, 2022
7 Jan 24, 2022
8 Nov 2, 2022
19 Dec 10, 2022
8 Oct 29, 2022
})
3 Dec 1, 2022
5.7k Jan 9, 2023
1.8k Jan 8, 2023
72 Nov 30, 2022
105 Dec 16, 2022
4 Sep 16, 2022
49 Dec 17, 2022
4 Sep 20, 2022
152 Dec 27, 2022
64 Nov 15, 2022
37 Jan 07, 2023
0 Nov 25, 2021
20 Sep 09, 2022
3 Aug 31, 2022
2 Apr 18, 2022
5 Aug 13, 2022
5 Nov 28, 2022
24 Dec 03, 2022
165 Oct 25, 2022
32 Oct 24, 2022
1.6k Jan 08, 2023
14 Nov 10, 2022
75 Dec 27, 2022
8 Sep 30, 2022