Nrthugu

This is my CNN model. I run the program with two labels. The labels are cat and dog. But:

1. Training accuracy is strange. The accuracy of the first label is
   reduced. and the second label is increased.




2. Loss function value is reduced. but test accuracy is The accuracy
   does not increase.

what's wrong??

`def cnn_model_fn(features, labels, mode):

    """Model function for CNN."""

    # Input Layer

    input_layer = tf.reshape(features["image"], [-1, _DEFAULT_IMAGE_SIZE, _DEFAULT_IMAGE_SIZE, 3])`





# Convolutional Layer #1

conv1 = tf.layers.conv2d(

    inputs=input_layer,

    filters=32,

    kernel_size=[3, 3],

    padding="SAME",

    activation=tf.nn.relu)



# Pooling Layer #1

pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)



# Convolutional Layer #2 and Pooling Layer #2

conv2 = tf.layers.conv2d(

    inputs=pool1,

    filters=64,

    kernel_size=[3, 3],

    padding="SAME",

    activation=tf.nn.relu)

pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)



# Dense Layer full connection layer

pool2_flat = tf.reshape(pool2, [-1, 50 * 50 * 64])

dense = tf.layers.dense(inputs=pool2_flat, units=512, activation=tf.nn.relu)

dropout = tf.layers.dropout(

    inputs=dense, rate=0.2, training=mode == tf.estimator.ModeKeys.TRAIN)



# Logits Layer

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



predictions = {

    # Generate predictions (for PREDICT and EVAL mode)

    "classes": tf.argmax(input=logits, axis=1),

    # Add `softmax_tensor` to the graph. It is used for PREDICT and by the

    # `logging_hook`.

    "probabilities": tf.nn.softmax(logits, name="softmax_tensor")

}



if mode == tf.estimator.ModeKeys.PREDICT:

    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)



onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=2)

loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits)



# Configure the Training Op (for TRAIN mode)

if mode == tf.estimator.ModeKeys.TRAIN:

    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)

    train_op = optimizer.minimize(

        loss=loss,

        global_step=tf.train.get_global_step())

    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)



# Add evaluation metrics (for EVAL mode)

eval_metric_ops = {

    "accuracy": tf.metrics.accuracy(

        labels=labels, predictions=predictions["classes"])}

return tf.estimator.EstimatorSpec(

    mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)