Syndria98/ith-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ok no

Browse Source
This commit is contained in:
BinarySandia04
2026-05-21 17:53:27 +02:00
parent 4b56e164a1
commit b2c0110d11
1 changed files with 17 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
skin_cancer_classification.py
View File

@@ -282,26 +282,22 @@ data_augmentation = tf.keras.Sequential([
tf.keras.layers.RandomContrast(0.1), tf.keras.layers.RandomContrast(0.1),
]) ])
with strategy.scope():
base_model = DenseNet121( base_model = DenseNet121(
weights='imagenet', weights='imagenet',
include_top=False, include_top=False,
input_shape=(224, 224, 3) input_shape=(224, 224, 3)
) )
with strategy.scope():
inputs = tf.keras.Input(shape=(224,224,3)) inputs = tf.keras.Input(shape=(224,224,3))
x = data_augmentation(inputs) x = data_augmentation(inputs)
with strategy.scope():
x = base_model.output x = base_model.output
x = GlobalAveragePooling2D()(x) x = GlobalAveragePooling2D()(x)
x = Dense(512, activation='relu')(x) # Added another Dense layer x = Dense(512, activation='relu')(x) # Added another Dense layer
x = Dense(256, activation='relu')(x) # Existing Dense layer x = Dense(256, activation='relu')(x) # Existing Dense layer
predictions = Dense(1, activation='sigmoid')(x) # Output layer for binary classification predictions = Dense(1, activation='sigmoid')(x) # Output layer for binary classification
with strategy.scope():
model = Model(inputs=base_model.input, outputs=predictions) model = Model(inputs=base_model.input, outputs=predictions)
model.compile(optimizer=Adam(learning_rate=0.0001), loss='binary_crossentropy', metrics=['accuracy']) model.compile(optimizer=Adam(learning_rate=0.0001), loss='binary_crossentropy', metrics=['accuracy'])