File size: 1,312 Bytes
8fe2e46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
import keras
import tensorflow as tf
from make_dataset import train_dataset, valid_dataset
from src.components.model import get_cnn_model, TransformerEncoderBlock, TransformerDecoderBlock, ImageCaptioningModel, image_augmentation, LRSchedule


EMBED_DIM = 512
FF_DIM = 512
EPOCHS = 30

cnn_model = get_cnn_model()
encoder = TransformerEncoderBlock(
    embed_dim=EMBED_DIM, dense_dim=FF_DIM, num_heads=1)
decoder = TransformerDecoderBlock(
    embed_dim=EMBED_DIM, ff_dim=FF_DIM, num_heads=2)
caption_model = ImageCaptioningModel(
    cnn_model=cnn_model,
    encoder=encoder,
    decoder=decoder,
    image_aug=image_augmentation,
)


early_stopping = keras.callbacks.EarlyStopping(
    patience=3, restore_best_weights=True)




num_train_steps = len(train_dataset) * EPOCHS
num_warmup_steps = num_train_steps // 15
lr_schedule = LRSchedule(post_warmup_learning_rate=1e-4,
                         warmup_steps=num_warmup_steps)

caption_model.compile(optimizer=keras.optimizers.Adam(lr_schedule), loss='sparse_categorical_crossentropy',
                      metrics=['accuracy'])

caption_model.fit(
    train_dataset,
    epochs=EPOCHS,
    validation_data=valid_dataset,
    callbacks=[early_stopping],
)

caption_model.save("./artifacts/caption_model1.keras")