模型的训练主要有内置fit方法、内置tran_on_batch方法、自定义训练循环。
注：fit_generator方法在tf.keras中不推荐使用，其功能已经被fit包含。
import numpy as np pandas as pd tensorflow as tf from tensorflow.keras import * # 打印时间分割线 @tf.function def printbar(): ts = tf.timestamp() today_ts = ts%(24*60*60) hour = tf.cast(today_ts//3600+8,tf.int32)%tf.constant(24) minite = tf.cast((today_ts%3600)//60,tf.int32) second = tf.cast(tf.floor(today_ts%60),tf.int32) timeformat(m): if tf.strings.length(tf.strings.format("{}",m))==1: return(tf.strings.format(0{}"else tf.strings.join([timeformat(hour),timeformat(minite),timeformat(second)],separator = :) tf.print(=========="*8,end = ""print(timestring) MAX_LEN = 300 BATCH_SIZE = 32 (x_train,y_train),(x_test,y_test) = datasets.reuters.load_data() x_train = preprocessing.sequence.pad_sequences(x_train,maxlen=MAX_LEN) x_test = preprocessing.sequence.pad_sequences(x_test,1)">MAX_LEN) MAX_WORDS = x_train.max()+1 CAT_NUM = y_train.max()+1 ds_train = tf.data.Dataset.from_tensor_slices((x_train,y_train)) \ .shuffle(buffer_size = 1000).batch(BATCH_SIZE) \ .prefetch(tf.data.experimental.AUTOTUNE).cache() ds_test = tf.data.Dataset.from_tensor_slices((x_test,y_test)) \ .shuffle(buffer_size = 1000).batch(BATCH_SIZE) \ .prefetch(tf.data.experimental.AUTOTUNE).cache()
一，内置fit方法
该方法功能非常强大,支持对numpy array,tf.data.Dataset以及 Python generator数据进行训练。
并且可以通过设置回调函数实现对训练过程的复杂控制逻辑。
tf.keras.backend.clear_session() create_model(): model = models.Sequential() model.add(layers.Embedding(MAX_WORDS,7,input_length=MAX_LEN)) model.add(layers.Conv1D(filters = 64,kernel_size = 5,activation = relu)) model.add(layers.MaxPool1D(2)) model.add(layers.Conv1D(filters = 32,kernel_size = 3,1)">)) model.add(layers.Flatten()) model.add(layers.Dense(CAT_NUM,activation = softmax)) return(model) compile_model(model): model.compile(optimizer=optimizers.Nadam(),loss=losses.SparseCategoricalCrossentropy(),metrics=[metrics.SparseCategoricalAccuracy(),metrics.SparseTopKCategoricalAccuracy(5)]) (model) model = create_model() model.summary() model = compile_model(model)
Model: sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= embedding (Embedding) (None,300,7) 216874 conv1d (Conv1D) (None,296,64) 2304 max_pooling1d (MaxPooling1D) (None,148,64) 0 conv1d_1 (Conv1D) (None,146,32) 6176 max_pooling1d_1 (MaxPooling1 (None,73,32) 0 flatten (Flatten) (None,2336) 0 dense (Dense) (None,46) 107502 ================================================================= Total params: 332,856 Trainable params: 332,1)"> Non-trainable params: 0 _________________________________________________________________
history = model.fit(ds_train,validation_data = ds_test,epochs = 10)
Epoch 1/10 281/281 [==============================] - 8s 28ms/step - loss: 1.9854 - sparse_categorical_accuracy: 0.4876 - sparse_top_k_categorical_accuracy: 0.7488 - val_loss: 1.6438 - val_sparse_categorical_accuracy: 0.5841 - val_sparse_top_k_categorical_accuracy: 0.7636 Epoch 2/10 281/281 [==============================] - 8s 28ms/step - loss: 1.4446 - sparse_categorical_accuracy: 0.6294 - sparse_top_k_categorical_accuracy: 0.8037 - val_loss: 1.5316 - val_sparse_categorical_accuracy: 0.6126 - val_sparse_top_k_categorical_accuracy: 0.7925 Epoch 3/10 281/281 [==============================] - 8s 28ms/step - loss: 1.1883 - sparse_categorical_accuracy: 0.6906 - sparse_top_k_categorical_accuracy: 0.8549 - val_loss: 1.6185 - val_sparse_categorical_accuracy: 0.6278 - val_sparse_top_k_categorical_accuracy: 0.8019 Epoch 4/10 281/281 [==============================] - 8s 28ms/step - loss: 0.9406 - sparse_categorical_accuracy: 0.7546 - sparse_top_k_categorical_accuracy: 0.9057 - val_loss: 1.7211 - val_sparse_categorical_accuracy: 0.6153 - val_sparse_top_k_categorical_accuracy: 0.8041 Epoch 5/10 281/281 [==============================] - 8s 29ms/step - loss: 0.7207 - sparse_categorical_accuracy: 0.8108 - sparse_top_k_categorical_accuracy: 0.9404 - val_loss: 1.9749 - val_sparse_categorical_accuracy: 0.6233 - val_sparse_top_k_categorical_accuracy: 0.7996 Epoch 6/10 281/281 [==============================] - 8s 28ms/step - loss: 0.5558 - sparse_categorical_accuracy: 0.8540 - sparse_top_k_categorical_accuracy: 0.9643 - val_loss: 2.2560 - val_sparse_categorical_accuracy: 0.6269 - val_sparse_top_k_categorical_accuracy: 0.7947 Epoch 7/10 281/281 [==============================] - 8s 28ms/step - loss: 0.4438 - sparse_categorical_accuracy: 0.8916 - sparse_top_k_categorical_accuracy: 0.9781 - val_loss: 2.4731 - val_sparse_categorical_accuracy: 0.6238 - val_sparse_top_k_categorical_accuracy: 0.7965 Epoch 8/10 281/281 [==============================] - 8s 29ms/step - loss: 0.3710 - sparse_categorical_accuracy: 0.9086 - sparse_top_k_categorical_accuracy: 0.9837 - val_loss: 2.6960 - val_sparse_categorical_accuracy: 0.6175 - val_sparse_top_k_categorical_accuracy: 0.7939 Epoch 9/10 281/281 [==============================] - 8s 28ms/step - loss: 0.3201 - sparse_categorical_accuracy: 0.9203 - sparse_top_k_categorical_accuracy: 0.9894 - val_loss: 3.1160 - val_sparse_categorical_accuracy: 0.6193 - val_sparse_top_k_categorical_accuracy: 0.7898 Epoch 10/10 281/281 [==============================] - 8s 28ms/step - loss: 0.2827 - sparse_categorical_accuracy: 0.9262 - sparse_top_k_categorical_accuracy: 0.9922 - val_loss: 2.9516 - val_sparse_categorical_accuracy: 0.6264 - val_sparse_top_k_categorical_accuracy: 0.7974
二，内置train_on_batch方法
该内置方法相比较fit方法更加灵活，可以不通过回调函数而直接在批次层次上更加精细地控制训练的过程。
tf.keras.backend.clear_session() create_model(): model = models.Sequential() model.add(layers.Embedding(MAX_WORDS,1)">_________________________________________________________________
train_model(model,ds_train,ds_valid,epoches): for epoch in tf.range(1,epoches+1): model.reset_metrics() 在后期降低学习率 if epoch == 5: model.optimizer.lr.assign(model.optimizer.lr/2.0) tf.Lowering optimizer Learning Rate...\n\n) for x,y in ds_train: train_result = model.train_on_batch(x,y) ds_valid: valid_result = model.test_on_batch(x,y,reset_metrics=False) if epoch%1 ==0: printbar() tf.epoch = train:valid:) train_model(model,ds_test,10)
================================================================================11:49:43 epoch = 1 train: {'loss': 2.0567171573638916,sparse_categorical_accuracy': 0.4545454680919647,1)">sparse_top_k_categorical_accuracy': 0.6818181872367859} valid: {': 1.6894209384918213,1)">': 0.5605521202087402,1)">': 0.7617987394332886} ================================================================================11:49:53 epoch = 2': 1.4644863605499268,1)">': 0.6363636255264282,1)">': 0.7727272510528564': 1.5152910947799683,1)">': 0.6157613396644592,1)">': 0.7938557267189026} ================================================================================11:50:01 epoch = 3': 1.0017579793930054,1)">': 0.7727272510528564,1)">': 0.9545454382896423': 1.5588842630386353,1)">': 0.6228851079940796,1)">': 0.8058770895004272} ================================================================================11:50:10 epoch = 4': 0.6004871726036072,1)">': 0.9090909361839294,1)">': 1.0': 1.7447566986083984,1)">': 0.6233303546905518,1)">': 0.8174532651901245} Lowering optimizer Learning Rate... ================================================================================11:50:19 epoch = 5': 0.3866238594055176,1)">': 0.9545454382896423,1)">': 1.8871253728866577,1)">': 0.6308993697166443,1)">': 0.816117525100708} ================================================================================11:50:28 epoch = 6': 0.27341774106025696,1)">': 2.0595862865448,1)">': 0.6273375153541565,1)">': 0.8089937567710876} ================================================================================11:50:37 epoch = 7': 0.1923554539680481,1)">': 2.2238168716430664,1)">': 0.6251112818717957,1)">': 0.8085485100746155} ================================================================================11:50:46 epoch = 8': 0.12688547372817993,1)">': 2.3778438568115234,1)">': 0.6175423264503479,1)">': 0.8072128295898438} ================================================================================11:50:55 epoch = 9': 0.08024053275585175,1)">': 2.501840829849243,1)">': 0.6135351657867432,1)">': 0.8081033229827881} ================================================================================11:51:04 epoch = 10': 0.05211604759097099,1)">': 1.0,1)">': 2.61771559715271,1)">': 0.6126446723937988,1)">': 0.8085485100746155}
三，自定义训练循环
自定义训练循环无需编译模型，直接利用优化器根据损失函数反向传播迭代参数，拥有最高的灵活性。
create_model() model.summary() optimizer = optimizers.Nadam() loss_func = losses.SparseCategoricalCrossentropy() train_loss = metrics.Mean(name=train_loss') train_metric = metrics.SparseCategoricalAccuracy(name=train_accuracy) valid_loss = metrics.Mean(name=valid_loss) valid_metric = metrics.SparseCategoricalAccuracy(name=valid_accuracy) @tf.function train_step(model,features,labels): with tf.GradientTape() as tape: predictions = model(features,training = True) loss = loss_func(labels,predictions) gradients = tape.gradient(loss,model.trainable_variables) optimizer.apply_gradients(zip(gradients,model.trainable_variables)) train_loss.update_state(loss) train_metric.update_state(labels,predictions) @tf.function valid_step(model,labels): predictions = model(features) batch_loss =): for features,labels ds_train: train_step(model,labels) ds_valid: valid_step(model,labels) logs = Epoch={},Loss:{},Accuracy:{},Valid Loss:{},Valid Accuracy:{}' (tf.strings.format(logs,(epoch,train_loss.result(),train_metric.result(),valid_loss.result(),valid_metric.result()))) tf.) train_loss.reset_states() valid_loss.reset_states() train_metric.reset_states() valid_metric.reset_states() train_model(model,10)
Model: _________________________________________________________________
================================================================================11:52:04 Epoch=1,Loss:2.02564383,Accuracy:0.464707196,Valid Loss:1.68035507,Valid Accuracy:0.55921638 ================================================================================11:52:11 Epoch=2,Loss:1.48306167,Accuracy:0.612781107,Valid Loss:1.52322364,Valid Accuracy:0.606411397 ================================================================================11:52:18 Epoch=3,Loss:1.20491719,Accuracy:0.677243352,Valid Loss:1.56225574,Valid Accuracy:0.624666095 ================================================================================11:52:25 Epoch=4,Loss:0.944778264,Accuracy:0.749387681,Valid Loss:1.7202934,Valid Accuracy:0.620658934 ================================================================================11:52:32 Epoch=5,Loss:0.701866329,Accuracy:0.817635298,Valid Loss:1.97179747,Valid Accuracy:0.61843276 ================================================================================11:52:39 Epoch=6,Loss:0.531810164,Accuracy:0.866844773,Valid Loss:2.25338316,Valid Accuracy:0.605075717 ================================================================================11:52:46 Epoch=7,Loss:0.425013304,Accuracy:0.896236897,Valid Loss:2.47035336,Valid Accuracy:0.601068556 ================================================================================11:52:53 Epoch=8,Loss:0.355143964,Accuracy:0.915609,Valid Loss:2.67822,Valid Accuracy:0.591718614 ================================================================================11:53:00 Epoch=9,Loss:0.30812338,Accuracy:0.92785573,Valid Loss:2.86121941,Valid Accuracy:0.583704352 ================================================================================11:53:07 Epoch=10,Loss:0.275565386,Accuracy:0.934535742,Valid Loss:2.99354172,Valid Accuracy:0.579252
参考：
开源电子书地址：https://lyhue1991.github.io/eat_tensorflow2_in_30_days/
GitHub 项目地址：https://github.com/lyhue1991/eat_tensorflow2_in_30_days
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。