Skip to content

CNN_train.py 中,为什么要有 # 读测试集数据 的内容?Why should I read the test data set? #2

@miss-peret

Description

@miss-peret

包括以下内容:
Include the following :

def read_test_data()
x_test, y_test = read_test_data()x_batch_test, y_batch_test = tf.train.shuffle_batch([x_test, y_test], batch_size=batch_size, capacity=200,min_after_dequeue=100, num_threads=3)
images_test, label_test = sess.run([x_batch_test, y_batch_test])
_images_test = np.reshape(images_test, [batch_size, 49152])
accuracy_test = sess.run(getAccuracy, feed_dict={x: _images_test, y: label_test, drop_pro: 1})
print("test accuracy: %g" % accuracy_test)

我认为应该删除这些内容,在训练中为什么要出现测试集内容呢?
I think we should delete this content

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions