如何保存，运行或测试经过Tensorflow卷积神经网络（CNN）训练的python文件？
我希望能够将此模型导出/保存为.tf和.tflite文件以及输入图像进行测试。
这是我的模型的代码：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
DATA_DIR = 'data'
NUM_STEPS = 1000
MINIBATCH_SIZE = 100
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev = 0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
def conv_later(input, shape):
W = weight_variable(shape)
b = bias_variable([shape[3]])
return tf.nn.relu(conv2d(input, W) + b)
def full_layer(input, size):
in_size = int(input.get_shape()[1])
W = weight_variable([in_size, size])
b = bias_variable([size])
return tf.matmul(input, W) + b
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])
conv1 = conv_later(x_image, shape=[5,5,1,32])
conv1_pool = max_pool_2x2(conv1)
conv2 = conv_later(conv1_pool, shape=[5,5,32,64])
conv2_pool = max_pool_2x2(conv2)
conv2_flat = tf.reshape(conv2_pool, [-1, 7*7*64])
full_1 = tf.nn.relu(full_layer(conv2_flat, 1024))
keep_prob = tf.placeholder(tf.float32)
full1_drop = tf.nn.dropout(full_1, keep_prob=keep_prob)
y_conv = full_layer(full1_drop, 10)
mnist = input_data.read_data_sets(DATA_DIR, one_hot=True)
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(NUM_STEPS):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = sess.run(accuracy, feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print("step {}, training accuracy {}".format(i, train_accuracy))
sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
X = mnist.test.images.reshape(10, 1000, 784)
Y = mnist.test.labels.reshape(10, 1000, 10)
test_accuracy = np.mean([sess.run(accuracy, feed_dict={x:X[i], y_:Y[i], keep_prob:1.0}) for i in range(10)])
print("test accuracy: {}".format(test_accuracy))
有人可以告诉我如何将该模型保存为.tf或.tflite并进行测试吗？
答案 0 :(得分：1)
目前，使用Tensorflow 2非常可行。因此，我正在发布有关它，并尽可能地复制您的模型。
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images,
test_labels) = fashion_mnist.load_data()
train_images = train_images / 255.0
test_images = test_images / 255.0
inputs = keras.Input(shape=(28, 28, 1), name="img")
x = layers.Conv2D(32, 5, activation="relu")(inputs)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(64, 5, activation="relu")(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Flatten()(x)
x = layers.Dense(1024, activation='relu')(x)
x = layers.Dropout(rate=0.5)(x)
outputs = layers.Dense(10, activation='relu')(x)
model = keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")
print(model.summary())
keras.utils.plot_model(
model, "model.png", show_shapes=True)
model.compile(
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer=keras.optimizers.Adam(learning_rate=1e-4),
metrics=["accuracy"],
)
history = model.fit(train_images, train_labels, batch_size=64,
epochs=2, validation_split=0.2)
# Saving Model
model.save("model.tf")
model = keras.models.load_model("model.tf")
test_scores = model.evaluate(test_images, test_labels, verbose=2)
print("Test loss:", test_scores[0])
print("Test accuracy:", test_scores[1])
# Convert the model.
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
# Save the TF Lite model.
with tf.io.gfile.GFile('model.tflite', 'wb') as f:
f.write(tflite_model)
输出：
Model: "mnist_model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
img (InputLayer) [(None, 28, 28, 1)] 0
_________________________________________________________________
conv2d (Conv2D) (None, 24, 24, 32) 832
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 12, 12, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 8, 8, 64) 51264
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 4, 4, 64) 0
_________________________________________________________________
flatten (Flatten) (None, 1024) 0
_________________________________________________________________
dense (Dense) (None, 1024) 1049600
_________________________________________________________________
dropout (Dropout) (None, 1024) 0
_________________________________________________________________
dense_1 (Dense) (None, 10) 10250
=================================================================
Total params: 1,111,946
Trainable params: 1,111,946
Non-trainable params: 0
_________________________________________________________________
Epoch 1/2
750/750 [==============================] - 82s 109ms/step - loss: 0.8672 - accuracy: 0.6908 - val_loss: 0.5704 - val_accuracy: 0.7868
Epoch 2/2
750/750 [==============================] - 109s 145ms/step - loss: 0.5553 - accuracy: 0.7936 - val_loss: 0.4854 - val_accuracy: 0.8205
313/313 - 14s - loss: 0.4997 - accuracy: 0.8206
Test loss: 0.4996977150440216
Test accuracy: 0.8205999732017517
型号详细信息：LINK。
