Classification models Zoo

Pretrained classification models for Keras

Models:

• ResNet models converted from MXNet:
  • ResNet18
  • ResNet34
  • ResNet50
  • ResNet101
  • ResNet152
• ResNeXt models converted from MXNet:
  • ResNeXt50
  • ResNeXt101

Example

Imagenet inference example:

import numpy as np
from skimage.io import imread
from keras.applications.imagenet_utils import decode_predictions

from classification_models import ResNet18
from classification_models.resnet import preprocess_input

# read and prepare image
x = imread('./imgs/tests/seagull.jpg')
x = preprocess_input(x, size=(224,224))
x = np.expand_dims(x, 0)

# load model
model = ResNet18(input_shape=(224,224,3), weights='imagenet', classes=1000)

# processing image
y = model.predict(x)

# result
print(decode_predictions(y))

Model fine-tuning example:

import keras
from classification_models import ResNet18

# prepare your data
X = ...
y = ...

n_classes = 10

# build model
base_model = ResNet18(input_shape=(224,224,3), weights='imagenet', include_top=False)
x = keras.layers.AveragePooling2D((7,7))(base_model.output)
x = keras.layers.Dropout(0.3)(x)
output = keras.layers.Dense(n_classes)(x)
model = keras.models.Model(inputs=[base_model.input], outputs=[output])

# train
model.compile(optimizer='SGD', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(X, y)