tensorflow2 Iris數據集分類

訓練並保存模型參數

import tensorflow as tf
import numpy as np
from sklearn.datasets import load_iris
data = load_iris()
#數據的形式
iris_data = np.float32(data.data)			#數據讀取
iris_target = (data.target)
iris_target = np.float32(tf.keras.utils.to_categorical(iris_target,num_classes=3))
input_xs  = tf.keras.Input(shape=(4), name='input_xs')
out = tf.keras.layers.Dense(32, activation='relu', name='dense_1')(input_xs)
out = tf.keras.layers.Dense(64, activation='relu', name='dense_2')(out)
logits = tf.keras.layers.Dense(3, activation="softmax",name='predictions')(out)
model = tf.keras.Model(inputs=input_xs, outputs=logits)
opt = tf.optimizers.Adam(1e-3)
model.compile(optimizer=tf.optimizers.Adam(1e-3), loss=tf.losses.categorical_crossentropy,metrics = ['accuracy'])
model.fit(x=iris_data,y=iris_target,batch_size=128, epochs=500)		#fit函數載入數據
score = model.evaluate(iris_data, iris_target)
print("last score:",score)
model.save('saver/the_saver_model.h5')

或者代碼

import tensorflow as tf
import numpy as np
from sklearn.datasets import load_iris
data = load_iris()
iris_target = data.target
iris_data = np.float32(data.data)
iris_target = np.float32(tf.keras.utils.to_categorical(iris_target,num_classes=3))
print(iris_target)
iris_data = tf.data.Dataset.from_tensor_slices(iris_data).batch(50)
iris_target = tf.data.Dataset.from_tensor_slices(iris_target).batch(50)
inputs = tf.keras.layers.Input(shape=(4), name='input_xs')
# 層的實例是可調用的，它以張量爲參數，並且返回一個張量
x = tf.keras.layers.Dense(32, activation='relu',name='dense_1')(inputs)
x = tf.keras.layers.Dense(64, activation='relu',name='dense_2')(x)
predictions = tf.keras.layers.Dense(3, activation='softmax',name='predictions')(x)
# 這部分創建了一個包含輸入層和三個全連接層的模型
model = tf.keras.Model(inputs=inputs, outputs=predictions)
opt = tf.optimizers.Adam(1e-3)
for epoch in range(1000):
    for _data,lable in zip(iris_data,iris_target):
        with tf.GradientTape() as tape:
            logits = model(_data)
            loss_value = tf.reduce_mean(tf.keras.losses.categorical_crossentropy(y_true = lable,y_pred = logits))
            grads = tape.gradient(loss_value, model.trainable_variables)
            opt.apply_gradients(zip(grads, model.trainable_variables))
print('Training loss is :', loss_value.numpy())
model.save('./saver/the_saver_model.h5')

模型的複用

import tensorflow as tf
import numpy as np
from sklearn.datasets import load_iris
data = load_iris()
iris_data = np.float32(data.data)
iris_target = (data.target)
iris_target = np.float32(tf.keras.utils.to_categorical(iris_target,num_classes=3))
new_model = tf.keras.models.load_model('./saver/the_save_model.h5')	#載入模型
new_prediction = new_model.predict(iris_data)	#進行預測
		
print(tf.argmax(new_prediction,axis=-1))	#打印預測結果

出現過一次報錯：

報錯 ValueError: You are trying to load a weight file containing 3 layers into a model with 0 layers.

錯誤原因：構建網絡時，沒有加名字

x = tf.keras.layers.Dense(32, activation='relu')(inputs)
x = tf.keras.layers.Dense(64, activation='relu')(x)