Question

我已经编写了一个vgg模型并对其进行了训练。现在，我将测试一个新的图像。当我使用code1时，它运行良好，但在code2中是错误的。 vgg（）是我定义它的模型。并且ckpt文件已保存在“D：\ Demo \ ckpt”中。

code1：打印预测为[[1.77901700e-01 8.22093844e-01 4.42284863e-06]]

def evaluate_one_image(path):
    with tf.Graph().as_default():
        image_plt = Image.open(path)
        image = image_plt.resize([224, 224])
        image_array = np.array(image)
        image = np.reshape(image_array, (1,224,224,3))
        x = tf.placeholder(tf.float32, shape=[1, 224, 224, 3])
        logit = vgg(x)
        logit = tf.nn.softmax(logit)
        logs_train_dir = 'D:\\Demo\\ckpt'
        saver = tf.train.Saver(tf.global_variables())
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            saver.restore(sess, ckpt.model_checkpoint_path)               
            prediction = sess.run(logit, feed_dict={x: image})
            print(prediction)

----------------------------------------------- -Dividing Line --------------------------------------

code2：我在tensorflow中使用了一些函数。它打印的预测为[[0.33333334 0.33333334 0.33333334]]。

def test_one_image(path):
    with tf.Graph().as_default():
        image_plt = Image.open(path)
        image_tensor = tf.image.decode_jpeg(tf.read_file(path), channels=3)
        image_tensor = tf.image.resize_image_with_crop_or_pad(image_tensor, 224, 224)
        # image_tensor = tf.image.per_image_standardization(image_tensor)
        image_tensor = tf.reshape(image_tensor, [1, 224, 224, 3])
        x = tf.placeholder(tf.float32, shape=[1, 224, 224, 3])
        logit = vgg(x)
        logit = tf.nn.softmax(logit)
        logs_train_dir = 'D:\\Demo\\ckpt'
        saver = tf.train.Saver(tf.global_variables())
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            saver.restore(sess, ckpt.model_checkpoint_path)              
            prediction = sess.run(logit, feed_dict={x: image_tensor.eval()})
            print(prediction)

我认为这两个代码的步骤几乎相同。但我不知道为什么这是错的，以及如何处理它。帮助我，非常感谢你！

Answer 1

第一个代码调整大小图片。第二个代码裁剪图片。这是两个不同的动作，第一个动作将完整图像缩放到新尺寸，第二个动作切割部分图像以使其大小等于224 x 224

<强>更新

试试这段代码：

def test_one_image(path):
    with tf.Graph().as_default():
        image_plt = Image.open(path)
        image_tensor = tf.image.decode_jpeg(tf.read_file(path), channels=3)
        image_tensor = tf.expand_dims(image_tensor, [0])
        image_tensor = tf.image.resize_images(image_tensor, [224, 224])
        logit = vgg(image_tensor)
        logit = tf.nn.softmax(logit)
        logs_train_dir = 'D:\\Demo\\ckpt'
        saver = tf.train.Saver(tf.global_variables())
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            saver.restore(sess, ckpt.model_checkpoint_path)              
            prediction = sess.run(logit)
            print(prediction)

Answer 2

当我使用此代码时，发生错误。结果再次为[[0.33333334 0.33333334 0.33333334]。

def test_one_image(path):
    with tf.Graph().as_default():
        image_plt = Image.open(path)
        image_tensor = tf.image.decode_jpeg(tf.read_file(path), channels=3)
        image_tensor = tf.image.per_image_standardization(image_tensor)
        image_tensor = tf.reshape(image_tensor, [1, 224, 224, 3])
        x = tf.placeholder(tf.float32, shape=[1, 224, 224, 3])
        logit = vgg(x)
        logit = tf.nn.softmax(logit)
        logs_train_dir = 'D:\\Demo\\ckpt'
        saver = tf.train.Saver(tf.global_variables())
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            saver.restore(sess, ckpt.model_checkpoint_path)              
            prediction = sess.run(logit, feed_dict={x: image_tensor.eval()})
            print(prediction)

当我使用tf.nn.read_file（）来测试vgg中的图像时，这是错误的。但是当我使用PIL打开它时，它是正确的。这么奇怪

2 个答案: