tensorflow - Creating confusion matrix after CNN model is completed

Question

I've been stuck here for a while. But how can i print a confusion-matrix from this code?

I've tried creating it through tensorboard, but that seems rather complicated.

I think i'm a little confused with keras.io setting train data as train_ds and not x_train and y_train.

I've also tried setting model.compile to report precision, recall etc. However that doesnt work.

Most of the code is rather new, and is from keras.io examples

# Pneumonia battle

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

import os

num_skipped = 0
for folder_name in ("Normal", "bacteria", "virus"):
    folder_path = os.path.join("data", folder_name)
    for fname in os.listdir(folder_path):
        fpath = os.path.join(folder_path, fname)

image_size = (256, 256)
batch_size = 32

train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    "data",
    validation_split=0.2,
    subset="training",
    seed=1337,
    image_size=image_size,
    batch_size=batch_size,
)
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    "data",
    validation_split=0.2,
    subset="validation",
    seed=1337,
    image_size=image_size,
    batch_size=batch_size,
)

data_augmentation = keras.Sequential(
    [
        layers.experimental.preprocessing.RandomFlip("horizontal"),
        layers.experimental.preprocessing.RandomRotation(0.1),
    ]
)

augmented_train_ds = train_ds.map(
  lambda x, y: (data_augmentation(x, training=True), y))

train_ds = train_ds.prefetch(buffer_size=32)
val_ds = val_ds.prefetch(buffer_size=32)

def make_model(input_shape, num_classes):
    inputs = keras.Input(shape=input_shape)
    # Image augmentation block
    x = data_augmentation(inputs)

    # Entry block
    x = layers.experimental.preprocessing.Rescaling(1.0 / 255)(x)
    x = layers.Conv2D(32, 3, strides=2, padding="same")(x)
    x = layers.BatchNormalization()(x)
    x = layers.Activation("relu")(x)

    x = layers.Conv2D(64, 3, padding="same")(x)
    x = layers.BatchNormalization()(x)
    x = layers.Activation("relu")(x)

    previous_block_activation = x  # Set aside residual

    for size in [128, 256, 512, 728]:
        x = layers.Activation("relu")(x)
        x = layers.SeparableConv2D(size, 3, padding="same")(x)
        x = layers.BatchNormalization()(x)

        x = layers.Activation("relu")(x)
        x = layers.SeparableConv2D(size, 3, padding="same")(x)
        x = layers.BatchNormalization()(x)

        x = layers.MaxPooling2D(3, strides=2, padding="same")(x)

        # Project residual
        residual = layers.Conv2D(size, 1, strides=2, padding="same")(
            previous_block_activation
        )
        x = layers.add([x, residual])  # Add back residual
        previous_block_activation = x  # Set aside next residual

    x = layers.SeparableConv2D(1024, 3, padding="same")(x)
    x = layers.BatchNormalization()(x)
    x = layers.Activation("relu")(x)

    x = layers.GlobalAveragePooling2D()(x)
    if num_classes == 2:
        activation = "sigmoid"
        units = 1
    else:
        activation = "softmax"
        units = num_classes

    x = layers.Dropout(0.4)(x)
    outputs = layers.Dense(units, activation=activation)(x)
    return keras.Model(inputs, outputs)

model = make_model(input_shape=image_size + (3,), num_classes=3)
keras.utils.plot_model(model, show_shapes=True)

model.summary()

epochs = 10

callbacks = [
    keras.callbacks.ModelCheckpoint("save_at_{epoch}.h5")
]

model.compile(
    optimizer=keras.optimizers.Adam(1e-4),
    loss="sparse_categorical_crossentropy",
    metrics=["accuracy"]
)

import datetime
log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)

history = model.fit(
    train_ds, epochs=epochs, callbacks=[tensorboard_callback], validation_data=val_ds,
)

question from:https://stackoverflow.com/questions/65937211/creating-confusion-matrix-after-cnn-model-is-completed

Answer 1

Waitting for answers