保存与读取模型

main.py

@@ -1,60 +0,0 @@
-import os
-import tensorflow as tf
-import matplotlib.pyplot as plt
-from tensorflow import keras
-import numpy as np
-config = tf.compat.v1.ConfigProto(gpu_options=tf.compat.v1.GPUOptions(allow_growth=True))
-sess = tf.compat.v1.Session(config=config)
-
-num_mnist = keras.datasets.mnist
-(train_images, train_labels), (test_images, test_labels) = num_mnist.load_data()
-
-print(train_images.shape)
-print(train_labels.shape)
-print(test_images.shape)
-print(test_labels.shape)
-
-model = keras.Sequential()
-model.add(keras.layers.Conv2D(8, (3,3), activation = 'relu', input_shape = (28,28,1)))
-model.add(keras.layers.MaxPooling2D(2,2))
-model.add(keras.layers.Conv2D(8, (3,3), activation = 'relu'))
-model.add(keras.layers.MaxPooling2D(2,2))
-
-model.add(keras.layers.Flatten())
-model.add(keras.layers.Dense(128, activation = tf.nn.relu))
-model.add(keras.layers.Dense(10, activation = tf.nn.softmax))
-
-checkpoint_path = "training_1/cp.ckpt"
-checkpoint_dir = os.path.dirname(checkpoint_path)
-
-cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
-                                                 save_weights_only=True,
-                                                 verbose=1)
-
-train_images_scaled = train_images/255
-model.compile(optimizer = 'adam', loss = tf.losses.sparse_categorical_crossentropy, metrics = ['accuracy'])
-
-history = model.fit(
-                        train_images_scaled.reshape(-1, 28, 28 ,1),
-                        train_labels,
-                        epochs = 8,
-                        validation_data=(test_images.reshape(-1, 28, 28 ,1), test_labels),
-                        callbacks=[cp_callback]
-                    )
-
-results = model.evaluate(test_images.reshape(-1, 28, 28 ,1), test_labels)
-
-testShow = test_labels[:100]
-
-pred = model.predict(test_images.reshape(-1, 28, 28 ,1))
-predict = []
-for item in pred:
-    predict.append(np.argmax(item))
-
-plt.figure()
-plt.title('Conv Predict')
-plt.ylabel('number')
-plt.plot( range( testShow.size ), predict[:100], label='predict')
-plt.plot( range( testShow.size ), testShow, label='result')
-plt.legend()
-plt.show()

predict.py

@@ -0,0 +1,41 @@
+import os
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from tensorflow.keras.models import load_model
+import numpy as np
+
+# 抑制tensorflow，以防显存占用过多报错
+config = tf.compat.v1.ConfigProto(gpu_options=tf.compat.v1.GPUOptions(allow_growth=True))
+sess = tf.compat.v1.Session(config=config)
+
+checkpoint_path = "./training_2/cp.ckpt"
+model_path = "./myModel/myModel.h5"
+
+# 读取手写数字数据集
+num_mnist = tf.keras.datasets.mnist
+(train_images, train_labels), (test_images, test_labels) = num_mnist.load_data()
+
+# 读取训练好点模型
+model = load_model(model_path)
+
+# 打印网络结构
+model.summary()
+
+# 评估
+model.evaluate(test_images.reshape(-1, 28, 28, 1), test_labels)
+
+# 可视化预测效果
+testShow = test_labels[:100]
+
+pred = model.predict(test_images.reshape(-1, 28, 28, 1))
+predict = []
+for item in pred:
+    predict.append(np.argmax(item))
+
+plt.figure()
+plt.title('Conv Predict')
+plt.ylabel('number')
+plt.plot(range(testShow.size), predict[:100], label='predict')
+plt.plot(range(testShow.size), testShow, label='result')
+plt.legend()
+plt.show()

train.py

@@ -0,0 +1,80 @@
+import os
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from tensorflow import keras
+import numpy as np
+
+# 抑制tensorflow，以防显存占用过多报错
+config = tf.compat.v1.ConfigProto(gpu_options=tf.compat.v1.GPUOptions(allow_growth=True))
+sess = tf.compat.v1.Session(config=config)
+# 读取手写数字数据集
+num_mnist = keras.datasets.mnist
+(train_images, train_labels), (test_images, test_labels) = num_mnist.load_data()
+# 打印shape
+print(train_images.shape)
+print(train_labels.shape)
+print(test_images.shape)
+print(test_labels.shape)
+
+# 构建网络 开始
+'''
+卷积 池化 卷积 池化  全连接 全连接
+'''
+model = keras.Sequential()
+model.add(keras.layers.Conv2D(8, (3, 3), activation='relu', input_shape=(28, 28, 1)))
+model.add(keras.layers.MaxPooling2D(2, 2))
+model.add(keras.layers.Conv2D(8, (3, 3), activation='relu'))
+model.add(keras.layers.MaxPooling2D(2, 2))
+
+model.add(keras.layers.Flatten())  # 扁平化处理，实现从卷积到全连接的过渡
+model.add(keras.layers.Dense(128, activation=tf.nn.relu))
+model.add(keras.layers.Dense(10, activation=tf.nn.softmax))
+
+model.compile(optimizer='adam', loss=tf.losses.sparse_categorical_crossentropy, metrics=['accuracy'])
+# 构建网络 结束
+
+# 打印网络结构
+model.summary()
+
+# 回调函数，用于训练中保存模型
+checkpoint_path = "./training_2/cp.ckpt"
+model_path = "./myModel/myModel.h5"
+checkpoint_dir = os.path.dirname(checkpoint_path)
+
+cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
+                                                 #save_weights_only=True,
+                                                 verbose=1)
+
+# 图片归一化处理
+train_images_scaled = train_images / 255
+
+# 训练
+history = model.fit(
+    train_images_scaled.reshape(-1, 28, 28, 1),
+    train_labels,
+    epochs=8,
+    validation_data=(test_images.reshape(-1, 28, 28, 1), test_labels),
+    callbacks=[cp_callback]
+)
+
+#保存模型
+model.save(model_path)
+
+# 评估
+results = model.evaluate(test_images.reshape(-1, 28, 28, 1), test_labels)
+
+# 可视化预测效果
+testShow = test_labels[:100]
+
+pred = model.predict(test_images.reshape(-1, 28, 28, 1))
+predict = []
+for item in pred:
+    predict.append(np.argmax(item))
+
+plt.figure()
+plt.title('Conv Predict')
+plt.ylabel('number')
+plt.plot(range(testShow.size), predict[:100], label='predict')
+plt.plot(range(testShow.size), testShow, label='result')
+plt.legend()
+plt.show()