@H_301_11@import numpy as np pandas as pd tensorflow as tf from tqdm tqdm from tensorflow.keras import * train_token_path = "./data/imdb/train_token.csv" test_token_path = ./data/imdb/test_token.csv MAX_WORDS = 10000 # We will only consider the top 10,000 words in the dataset MAX_LEN = 200 We will cut reviews after 200 words BATCH_SIZE = 20 构建管道 def parse_line(line): t = tf.strings.split(line,\t) label = tf.reshape(tf.cast(tf.strings.to_number(t[0]),tf.int32),(-1,)) features = tf.cast(tf.strings.to_number(tf.strings.split(t[1],1)">" )),tf.int32) return (features,label) ds_train= tf.data.TextLineDataset(filenames = [train_token_path]) \ .map(parse_line,num_parallel_calls = tf.data.experimental.AUTOTUNE) \ .shuffle(buffer_size = 1000).batch(BATCH_SIZE) \ .prefetch(tf.data.experimental.AUTOTUNE) ds_test= tf.data.TextLineDataset(filenames = [test_token_path]) \ .map(parse_line,1)">).batch(BATCH_SIZE) \ .prefetch(tf.data.experimental.AUTOTUNE)

@H_301_11@f.keras.backend.clear_session() 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(1,1)">sigmoid)) model.compile(optimizer='Nadam'binary_crossentropyaccuracy',1)">AUC]) model.summary()

@H_301_11@Model: sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= embedding (Embedding) (None,200,7) 70000 conv1d (Conv1D) (None,196,64) 2304 max_pooling1d (MaxPooling1D) (None,98,64) 0 conv1d_1 (Conv1D) (None,96,32) 6176 max_pooling1d_1 (MaxPooling1 (None,48,32 flatten (Flatten) (None,1536) 0 dense (Dense) (None,1) 1537 ================================================================= Total params: 80,017 Trainable params: 80,1)"> Non-trainable params: 0 _________________________________________________________________

@H_301_11@ datetime baselogger = callbacks.BaseLogger(stateful_metrics=[auc]) logdir = ./data/keras_model/" + datetime.datetime.now().strftime(%Y%m%d-%H%M%S) tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir,histogram_freq=1) history = model.fit(ds_train,validation_data = ds_test,epochs = 6,callbacks=[baselogger,tensorboard_callback]) %matplotlib inline %config InlineBackend.figure_format = svg' matplotlib.pyplot as plt plot_metric(history,metric): train_metrics = history.history[metric] val_metrics = history.history[val_'+metric] epochs = range(1,len(train_metrics) + 1) plt.plot(epochs,train_metrics,bo--ro-) plt.title(Training and validation metric) plt.xlabel(Epochs) plt.ylabel(metric) plt.legend([train_"+metric,1)">metric]) plt.show() plot_metric(history,1)">"auc")

@H_301_11@Epoch 1/6 1000/Unknown - 17s 17ms/step - loss: 0.1133 - accuracy: 0.9588 - auc: 0.9918 --------------------------------------------------------------------------- KeyError Traceback (most recent call last) <ipython-input-17-8cd49fdfb6d8> in <module>() 4 tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir,1)">) 5 history = model.fit(ds_train,----> 6 epochs = 6,tensorboard_callback]) 7 """ 8 %matplotlib inline 3 frames /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in on_epoch_end(self,epoch,logs) 795 def on_epoch_end(self,logs=None): 796 if logs is not None: --> 797 for k in self.params['metrics']: 798 if k in self.totals: 799 # Make value available to next callbacks. KeyError: 'metrics'

@H_301_11@ datetime logdir = @H_301_11@Epoch 1/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.0058 - accuracy: 0.9980 - auc: 0.9999 - val_loss: 1.5239 - val_accuracy: 0.8598 - val_auc: 0.8961 Epoch 2/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.0011 - accuracy: 0.9996 - auc: 1.0000 - val_loss: 1.7804 - val_accuracy: 0.8610 - val_auc: 0.8920 Epoch 3/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.0034 - accuracy: 0.9990 - auc: 0.9999 - val_loss: 1.8452 - val_accuracy: 0.8524 - val_auc: 0.8861 Epoch 4/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.0107 - accuracy: 0.9969 - auc: 0.9995 - val_loss: 1.6515 - val_accuracy: 0.8582 - val_auc: 0.8901 Epoch 5/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.0022 - accuracy: 0.9994 - auc: 1.0000 - val_loss: 1.7680 - val_accuracy: 0.8522 - val_auc: 0.8864 Epoch 6/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.0052 - accuracy: 0.9979 - auc: 0.9999 - val_loss: 1.7506 - val_accuracy: 0.8554 - val_auc: 0.8918

@H_301_11@tf.keras.backend.clear_session() inputs = layers.Input(shape=[MAX_LEN]) x = layers.Embedding(MAX_WORDS,7)(inputs) branch1 = layers.SeparableConv1D(64,3,activation=)(x) branch1 = layers.MaxPool1D(3)(branch1) branch1 = layers.SeparableConv1D(32,1)">)(branch1) branch1 = layers.GlobalMaxPool1D()(branch1) branch2 = layers.SeparableConv1D(64,5,1)">)(x) branch2 = layers.MaxPool1D(5)(branch2) branch2 = layers.SeparableConv1D(32,1)">)(branch2) branch2 = layers.GlobalMaxPool1D()(branch2) branch3 = layers.SeparableConv1D(64,7,1)">)(x) branch3 = layers.MaxPool1D(7)(branch3) branch3 = layers.SeparableConv1D(32,1)">)(branch3) branch3 = layers.GlobalMaxPool1D()(branch3) concat = layers.Concatenate()([branch1,branch2,branch3]) outputs = layers.Dense(1,1)">)(concat) model = models.Model(inputs = inputs,outputs = outputs) model.compile(optimizer=model__________________________________________________________________________________________________ Layer (type) Output Shape Param Connected to ================================================================================================== input_1 (InputLayer) [(None,200)] 0 embedding (Embedding) (None,7) 70000 input_1[0][0] separable_conv1d (SeparableConv (None,198,64) 533 embedding[0][0] separable_conv1d_2 (SeparableCo (None,64) 547 separable_conv1d_4 (SeparableCo (None,194,64) 561 max_pooling1d (MaxPooling1D) (None,66,1)">) 0 separable_conv1d[0][0] max_pooling1d_1 (MaxPooling1D) (None,39,1)">) 0 separable_conv1d_2[0][0] max_pooling1d_2 (MaxPooling1D) (None,27,1)">) 0 separable_conv1d_4[0][0] separable_conv1d_1 (SeparableCo (None,64,32) 2272 max_pooling1d[0][0] separable_conv1d_3 (SeparableCo (None,35,32) 2400 max_pooling1d_1[0][0] separable_conv1d_5 (SeparableCo (None,21,32) 2528 max_pooling1d_2[0][0] global_max_pooling1d (GlobalMax (None,32) 0 separable_conv1d_1[0][0] global_max_pooling1d_1 (GlobalM (None,1)">) 0 separable_conv1d_3[0][0] global_max_pooling1d_2 (GlobalM (None,1)">) 0 separable_conv1d_5[0][0] concatenate (Concatenate) (None,96) 0 global_max_pooling1d[0][0] global_max_pooling1d_1[0][0] global_max_pooling1d_2[0][0] dense (Dense) (None,1) 97 concatenate[0][0] ================================================================================================== Total params: 78,938 Trainable params: 78,1)">__________________________________________________________________________________________________

@H_301_11@ @H_301_11@Epoch 1/6 1000/1000 [==============================] - 28s 28ms/step - loss: 0.5210 - accuracy: 0.7120 - auc: 0.8098 - val_loss: 0.3512 - val_accuracy: 0.8482 - val_auc: 0.9254 Epoch 2/6 1000/1000 [==============================] - 27s 27ms/step - loss: 0.2842 - accuracy: 0.8805 - auc: 0.9510 - val_loss: 0.3302 - val_accuracy: 0.8588 - val_auc: 0.9384 Epoch 3/6 1000/1000 [==============================] - 27s 27ms/step - loss: 0.1931 - accuracy: 0.9265 - auc: 0.9772 - val_loss: 0.3955 - val_accuracy: 0.8512 - val_auc: 0.9336 Epoch 4/6 1000/1000 [==============================] - 27s 27ms/step - loss: 0.1203 - accuracy: 0.9594 - auc: 0.9906 - val_loss: 0.4669 - val_accuracy: 0.8494 - val_auc: 0.9273 Epoch 5/6 1000/1000 [==============================] - 27s 27ms/step - loss: 0.0664 - accuracy: 0.9798 - auc: 0.9965 - val_loss: 0.5963 - val_accuracy: 0.8476 - val_auc: 0.9158 Epoch 6/6 1000/1000 [==============================] - 27s 27ms/step - loss: 0.0305 - accuracy: 0.9934 - auc: 0.9987 - val_loss: 0.7246 - val_accuracy: 0.8440 - val_auc: 0.9063

@H_301_11@plot_metric(history,1)">")

@H_301_11@ 先自定义一个残差模块，为自定义Layer class ResBlock(layers.Layer): def __init__(self,kernel_size,**kwargs): super(ResBlock,self).__init__(**kwargs) self.kernel_size = kernel_size build(self,input_shape): self.conv1 = layers.Conv1D(filters=64,kernel_size=self.kernel_size,activation = ",padding=same) self.conv2 = layers.Conv1D(filters=32,1)">) self.conv3 = layers.Conv1D(filters=input_shape[-1],kernel_size=self.kernel_size,1)">) self.maxpool = layers.MaxPool1D(2) super(ResBlock,self).build(input_shape) 相当于设置self.built = True call(self,inputs): x = self.conv1(inputs) x = self.conv2(x) x = self.conv3(x) x = layers.Add()([inputs,x]) x = self.maxpool(x) x 如果要让自定义的Layer通过Functional API 组合成模型时可以序列化，需要自定义get_config方法。 get_config(self): config = super(ResBlock,self).get_config() config.update({kernel_size: self.kernel_size}) config 测试ResBlock resblock = ResBlock(kernel_size = 3) resblock.build(input_shape = (None,200,1)">)) resblock.compute_output_shape(input_shape=(None,1)">)) 自定义模型，实际上也可以使用Sequential或者FunctionalAPI ImdbModel(models.Model): __init__(self): super(ImdbModel,1)">() ) self.block1 = ResBlock(7) self.block2 = ResBlock(5) self.dense = layers.Dense(1,1)">) super(ImdbModel,self).build(input_shape) self.embedding(x) x = self.block1(x) x = self.block2(x) x = layers.Flatten()(x) x = self.dense(x) (x) tf.keras.backend.clear_session() model = ImdbModel() model.build(input_shape =(None,200)) model.summary() model.compile(optimizer=]) datetime logdir = ./tflogs/keras_model/[tensorboard_callback]) plot_metric(history,1)">")

@H_301_11@odel: imdb_model embedding (Embedding) multiple 70000 res_block (ResBlock) multiple 19143 res_block_1 (ResBlock) multiple 13703 dense (Dense) multiple 351 ================================================================= Total params: 103,197 Trainable params: 103,1)"> Epoch 1/6 1000/1000 [==============================] - 44s 44ms/step - loss: 0.5311 - accuracy: 0.6953 - auc: 0.7931 - val_loss: 0.3333 - val_accuracy: 0.8522 - val_auc: 0.9352 Epoch 2/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.2507 - accuracy: 0.8985 - auc: 0.9619 - val_loss: 0.3906 - val_accuracy: 0.8404 - val_auc: 0.9427 Epoch 3/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.1448 - accuracy: 0.9465 - auc: 0.9868 - val_loss: 0.3965 - val_accuracy: 0.8742 - val_auc: 0.9403 Epoch 4/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.0758 - accuracy: 0.9745 - auc: 0.9958 - val_loss: 0.5496 - val_accuracy: 0.8648 - val_auc: 0.9279 Epoch 5/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.0296 - accuracy: 0.9898 - auc: 0.9990 - val_loss: 0.8675 - val_accuracy: 0.8592 - val_auc: 0.9111 Epoch 6/6 1000/1000 [==============================] - 43s 43ms/step - loss: 0.0208 - accuracy: 0.9927 - auc: 0.9995 - val_loss: 0.9153 - val_accuracy: 0.8578 - val_auc: 0.9094