I tried to basically copy this tutorial: https://keras.io/examples/vision/image_classification_from_scratch/
But I can't seem to improve on my val_accuracy score. I also have 2 kinds of images dogs (Hunde) and cats (Katzen) but only 95 samples each. I have an "upper" folder "Hunde und Katzen" where the folders of these samples are. I probably have to tune some parameters, because my sample size is so low but I already tried at some code parts.
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import os
num_skipped = 0
for folder_name in ("Hund", "Katze"):
folder_path = os.path.join("Hund und Katze", folder_name)
for fname in os.listdir(folder_path):
fpath = os.path.join(folder_path, fname)
try:
fobj = open(fpath, "rb")
is_jfif = tf.compat.as_bytes("JFIF") in fobj.peek(10)
finally:
fobj.close()
if not is_jfif:
num_skipped = 1
# Delete corrupted image
os.remove(fpath)
print("Deleted %d images" % num_skipped)
image_size = (180, 180)
batch_size = 16
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
"Hund und Katze",
validation_split=0.5,
subset="training",
seed=9,
image_size=image_size,
batch_size=batch_size,
)
val_ds = tf.keras.preprocessing.image_dataset_from_directory(
"Hund und Katze",
validation_split=0.5,
subset="validation",
seed=9,
image_size=image_size,
batch_size=batch_size,
)
#Found 190 files belonging to 2 classes.
#Using 95 files for training.
#Found 190 files belonging to 2 classes.
#Using 95 files for validation.
data_augmentation = keras.Sequential(
[
layers.RandomFlip("horizontal"),
layers.RandomRotation(0.1),
]
)
train_ds = train_ds.prefetch(buffer_size=8)
val_ds = val_ds.prefetch(buffer_size=8)
def make_model(input_shape, num_classes):
inputs = keras.Input(shape=input_shape)
# Image augmentation block
x = data_augmentation(inputs)
# Entry block
x = layers.Rescaling(1.0 / 255)(x)
x = layers.Conv2D(16, 3, strides=2, padding="same")(x)
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
x = layers.Conv2D(32, 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(0.5)(x)
outputs = layers.Dense(units, activation=activation)(x)
return keras.Model(inputs, outputs)
model = make_model(input_shape=image_size (3,), num_classes=2)
keras.utils.plot_model(model, show_shapes=True)
#('You must install pydot (`pip install pydot`) and install graphviz (see instructions at
#https://graphviz.gitlab.io/download/) ', 'for plot_model/model_to_dot to work.')
epochs = 10
callbacks = [
keras.callbacks.ModelCheckpoint("save_at_{epoch}.h5"),
]
model.compile(
optimizer=keras.optimizers.Adam(0.001),
loss="binary_crossentropy",
metrics=["accuracy"],
)
model.fit(
train_ds, epochs=epochs, callbacks=callbacks, validation_data=val_ds,
)
Output: Epoch 1/10
6/6 [==============================] - 8s 1s/step - loss: 0.7691 - accuracy: 0.6421 - val_loss: 0.6935 - val_accuracy: 0.4632
E:\anacondaBI\lib\site-packages\keras\engine\functional.py:1410: CustomMaskWarning: Custom mask layers require a config and must override get_config. When loading, the custom mask layer must be passed to the custom_objects argument.
layer_config = serialize_layer_fn(layer)
Epoch 2/10
6/6 [==============================] - 6s 995ms/step - loss: 0.7747 - accuracy: 0.6526 - val_loss: 0.6917 - val_accuracy: 0.5368
Epoch 3/10
6/6 [==============================] - 6s 1s/step - loss: 0.6991 - accuracy: 0.7053 - val_loss: 0.6905 - val_accuracy: 0.5368
Epoch 4/10
6/6 [==============================] - 6s 1s/step - loss: 0.5411 - accuracy: 0.7368 - val_loss: 0.6935 - val_accuracy: 0.5368
Epoch 5/10
6/6 [==============================] - 6s 1s/step - loss: 0.3949 - accuracy: 0.8316 - val_loss: 0.7023 - val_accuracy: 0.5368
Epoch 6/10
6/6 [==============================] - 6s 1s/step - loss: 0.4440 - accuracy: 0.8526 - val_loss: 0.7199 - val_accuracy: 0.5368
Epoch 7/10
6/6 [==============================] - 6s 1s/step - loss: 0.3515 - accuracy: 0.8842 - val_loss: 0.7470 - val_accuracy: 0.5368
Epoch 8/10
6/6 [==============================] - 6s 1s/step - loss: 0.3249 - accuracy: 0.8526 - val_loss: 0.7955 - val_accuracy: 0.5368
Epoch 9/10
6/6 [==============================] - 6s 994ms/step - loss: 0.3953 - accuracy: 0.8421 - val_loss: 0.8570 - val_accuracy: 0.5368
Epoch 10/10
6/6 [==============================] - 6s 989ms/step - loss: 0.4363 - accuracy: 0.7789 - val_loss: 0.9189 - val_accuracy: 0.5368
<keras.callbacks.History at 0x2176ec764c0>
CodePudding user response：
95 samples for each class is less to achieve a decent accuracy
decrease your validation_split to 0.05 (5% for validation ), as you have very less number of data points
If the first step does not help you then you can use transfer learning i.e using architectures that have a good accuracy on imagenet for e.g: MobileNets, ResNets and efficientnets
If the above 2 steps are not giving you a good accuracy then try increasing your data size and tune your hyperparameters.