CNN用于图像分类过度，显然不采取下一批

Question

I'm trying to create a CNN with TensorFlow that classifies images from google tutorials on CNNs . I created a function that loads the image dataset and one that extracts the batches for training. But even if I move to the next batch the network always trains on the same batch. The dataset have 10000 images. I think that the model doesn't take the next batch because I reach 100% accuracy in less than 10 iterations. Here the code:

#Training Parameters
learning_rate = 0.001
batch_size = 128
epochs = 10

MODE = 'TRAIN'

# Function that loads the entire dataset of images (X) with their respective labels (Y). X and Y are two np.array
len_X, X, Y = get_images(
    files_path=dataset_path,
    img_size_h=1000,
    img_size_w=48,
    mode='TRAIN',
    randomize=True
)

# Function that load the batch from X and Y
X_batch, Y_X_batch = next_batch(
    total=len_X,
    images=X,
    labels=Y,
    batch_size=batch_size,
    index=0
)

logits = cnn_model_fn(X_batch, MODE)
prediction = tf.nn.softmax(logits)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=Y_X_batch))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss)
correct_predict = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y_X_batch, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predict, tf.float32))

init = tf.global_variables_initializer()
best_acc=0

with tf.Session() as sess:

    sess.run(init)
    saver = tf.train.Saver()

    if MODE == 'TRAIN':
        print("TRAINING MODE")
        for step in range(1,epochs+1):
            for i in range(0, int(len_X/batch_size)+1):

                if i > 0:
                    X_batch, Y_X_batch = next_batch(
                        total=len_X,
                        images=X,
                        labels=Y,
                        batch_size=batch_size,
                        index=i
                    )


                sess.run(train_op)
                los, acc= sess.run([loss, accuracy])

                if acc >= best_acc:
                    best_acc = acc

        writer = tf.summary.FileWriter(TensorBoard_path, sess.graph)

    elif MODE=='TEST':
        # TEST MODE #

sess.close()

Here is the structure of the neural network model:

def cnn_model_fn(X, MODE):

    # INPUT LAYER
    input_layer = tf.reshape(X, [-1, 1000, 48, 1])

    # CONVOLUTIONAL LAYER #1
    conv1 = tf.layers.conv2d(
        inputs=input_layer,
        filters=4,
        kernel_size=[10, 10],
        strides=(2, 2),
        padding="valid",
    )
    conv1_relu = tf.nn.relu(conv1)

    # POOLING LAYER #1
    pool1 = tf.layers.max_pooling2d(
        inputs=conv1_relu,
        pool_size=[2, 2],
        strides=2
    )

    # CONVOLUTIONAL LAYER #2
    conv2 = tf.layers.conv2d(
        inputs=pool1,
        filters=64,
        kernel_size=[5, 5],
        padding="same",
    )
    conv2_relu = tf.nn.relu(conv2)

    # POOLING LAYER #2
    pool2 = tf.layers.max_pooling2d(
        inputs=conv2_relu,
        pool_size=[2, 2],
        strides=2
    )
    x = tf.TensorShape.as_list(pool2.shape)

    pool2_flat = tf.reshape(pool2, [-1, x[1] * x[2] * x[3]])


    # DENSE LAYER
    dense = tf.layers.dense(
        inputs=pool2_flat,
        units=1024,
    )

    dense_relu = tf.nn.relu(dense)

    # AGGIUNGO L'OPERAZIONE DI DROPOUT
    dropout = tf.layers.dropout(
        inputs=dense_relu,
        rate=0.4,
        training=MODE == tf.estimator.ModeKeys.TRAIN
    )

    # LOGIT LAYER
    logits = tf.layers.dense(
        inputs=dropout,
        units=2
    )

    return logits

Thank you so much for your time.

Answer 1

You were not using tensorflow placeholders. Make sure that X_batch_placeholder and Y_batch_placeholder are defined and used in your loss function like this:

Y_batch_placeholder = tf.placeholder(tf.float32 ,[None, 2] )
X_batch_placeholder = tf.placeholder(tf.float32 ,[None, 1000, 48])


logits = cnn_model_fn(X_batch_placeholder, MODE)
prediction = tf.nn.softmax(logits)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=Y_batch_placeholder))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss)
correct_predict = tf.equal(tf.argmax(prediction, 1), tf.argmax(Y_batch_placeholder, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predict, tf.float32))

Then run your session using feed_dict. Some tensorflow variables are placeholders, you need to use feed_dict to feed them relevant information while running a session:

_, los, acc = sess.run([train_op, loss, accuracy],
                                       feed_dict={X_batch_placeholder: X_batch, Y_batch_placeholder: Y_batch})

See here: Tensorflow: When should I use or not use `feed_dict`? and here: https://hanxiao.github.io/2017/07/07/Get-10x-Speedup-in-Tensorflow-Multi-Task-Learning-using-Python-Multiprocessing/