What do `loss` and `accuracy` values mean?

Question

I'm using this:

Python version: 3.7.7 (default, May  6 2020, 11:45:54) [MSC v.1916 64 bit (AMD64)]
TensorFlow version: 2.1.0
Eager execution: True

With this U-Net model:

inputs = Input(shape=img_shape)

    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_1')(inputs)
    conv1 = Conv2D(64, (5, 5), activation='relu', padding='same', data_format="channels_last", name='conv1_2')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool1')(conv1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_1')(pool1)
    conv2 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv2_2')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool2')(conv2)

    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_1')(pool2)
    conv3 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv3_2')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool3')(conv3)

    conv4 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv4_1')(pool3)
    conv4 = Conv2D(256, (4, 4), activation='relu', padding='same', data_format="channels_last", name='conv4_2')(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2), data_format="channels_last", name='pool4')(conv4)

    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_1')(pool4)
    conv5 = Conv2D(512, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv5_2')(conv5)

    up_conv5 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv5')(conv5)
    ch, cw = get_crop_shape(conv4, up_conv5)
    crop_conv4 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv4')(conv4)
    up6 = concatenate([up_conv5, crop_conv4])
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_1')(up6)
    conv6 = Conv2D(256, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv6_2')(conv6)

    up_conv6 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv6')(conv6)
    ch, cw = get_crop_shape(conv3, up_conv6)
    crop_conv3 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv3')(conv3)
    up7 = concatenate([up_conv6, crop_conv3])
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_1')(up7)
    conv7 = Conv2D(128, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv7_2')(conv7)

    up_conv7 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv7')(conv7)
    ch, cw = get_crop_shape(conv2, up_conv7)
    crop_conv2 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv2')(conv2)
    up8 = concatenate([up_conv7, crop_conv2])
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_1')(up8)
    conv8 = Conv2D(96, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv8_2')(conv8)

    up_conv8 = UpSampling2D(size=(2, 2), data_format="channels_last", name='up_conv8')(conv8)
    ch, cw = get_crop_shape(conv1, up_conv8)
    crop_conv1 = Cropping2D(cropping=(ch, cw), data_format="channels_last", name='crop_conv1')(conv1)
    up9 = concatenate([up_conv8, crop_conv1])
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_1')(up9)
    conv9 = Conv2D(64, (3, 3), activation='relu', padding='same', data_format="channels_last", name='conv9_2')(conv9)

    ch, cw = get_crop_shape(inputs, conv9)
    conv9 = ZeroPadding2D(padding=(ch, cw), data_format="channels_last", name='conv9_3')(conv9)
    conv10 = Conv2D(1, (1, 1), activation='sigmoid', data_format="channels_last", name='conv10_1')(conv9)
    model = Model(inputs=inputs, outputs=conv10)

To compile the model I do:

model.compile(tf.keras.optimizers.Adam(lr=(1e-4) * 2), loss=dice_coef_loss, metrics=['accuracy'])

And I get this output while training:

Epoch 1/2 5/5 [==============================] - 8s 2s/sample - loss: 0.9830 - accuracy: 0.1033 - val_loss: 1.0000 - val_accuracy: 0.9469 Epoch 2/2 5/5 [==============================] - 5s 1s/sample - loss: 1.0000 - accuracy: 0.9442 - val_loss: 0.9999 - val_accuracy: 0.9972 Train on 5 samples, validate on 5 samples

I don't understand what loss and accuracy values mean (if they are percentage, etc.).

For example, with the values:

loss: 0.9830 - accuracy: 0.1033

Mean that there is a 98.3% of error and there is a 10.33% of success.

And these values:

loss: 1.0000 - accuracy: 0.9442

There is a 100% of error and an 94.42% of success.

I think that the values for loss and accuracy could be [1.0, 0.0] (if I'm not wrong).

What do loss and accuracy values mean? I mean that I don't know when my model it is getting better.

Answer 1

I don't understand what loss and accuracy values mean (if they are percentage, etc.).

Loss is the difference between the feedforward output and the actual target. It is calculated using the function you passed for Loss in the compile method.
In your case it is - loss=dice_coef_loss. It is calculated after each batch.

Metrics is calculated on the metrics you pass to the metrics parm in the compile method.
In your case, it is "Accuracy".
It means the model is calculating the accuracy(correct prediction/total predictions) after every Batch and letting you know by printing.

An improving metrics means the model is learning with every Batch
If the model will learn the target, Loss will reduce.

Needless to say, too much learning of the train data creates another issue -Overfitting

loss: 0.9830 - accuracy: 0.1033

Loss value is 0.98 and Accuracy is 10.33% (Very poor)
Loss is not a percentage, it the value of the output of the Loss function using y_true and y_pred.