how can i retrian the efficientnet model？ about efficientnet HOT 5 CLOSED

Hi @songxh2

import keras
from efficientnet import EfficinetNetB0, preprocess_input

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

X = preprocess_input(X)

n_classes = 10

# build model
base_model = EfficinetNetB0(input_shape=(224,224,3), weights='imagenet', include_top=False)
x = keras.layers.GlobalAveragePooling2D()(base_model.output)
output = keras.layers.Dense(n_classes, activation='softmax')(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)

from efficientnet.

finetune on my own datasetes

from efficientnet.

Hi @songxh2

import keras
from efficientnet import EfficinetNetB0, preprocess_input

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

X = preprocess_input(X)

n_classes = 10

# build model
base_model = EfficinetNetB0(input_shape=(224,224,3), weights='imagenet', include_top=False)
x = keras.layers.GlobalAveragePooling2D()(base_model.output)
output = keras.layers.Dense(n_classes, activation='softmax')(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)

thanks a lot, good luck for your !

from efficientnet.

what format should y follow?

from efficientnet.

what format should x and y follow?

from efficientnet.