[英]How can i speed up my model training process using tensorflow and keras
我的批量大小 = 128 時期數 = 15
單個 epoch 需要 4 個小時才能完成任務,因此完整的訓練過程需要大量時間。 就我而言,我需要提高 model 訓練過程的速度以保存我的體重值我該怎么做
# Training Process
results = model.fit_generator(generate_batch(orig_train, forg_train, batch_sz),
steps_per_epoch = num_train_samples//batch_sz,
epochs = 15,
validation_data = generate_batch(orig_val, forg_val, batch_sz),
validation_steps = num_val_samples//batch_sz,
callbacks = callbacks)
我的回調數組定義如下,
callbacks = [
EarlyStopping(patience=12, verbose=1),
ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.000001, verbose=1),
ModelCheckpoint('./Weights/model-weight-{epoch:03d}.h5', verbose=1, save_weights_only=True)
]
你可以做兩件事:
import tensorflow as tf
tf.config.optimizer.set_jit(True)
from tensorflow.keras.mixed_precision import experimental as mixed_precision
policy = mixed_precision.Policy('mixed_float16')
mixed_precision.set_policy(policy)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.