поправил скрипт обучения

beerds_imagenet.py

@@ -8,25 +8,27 @@ import tensorflow as tf
 from tensorflow import keras
 from tensorflow.keras import layers
 from tensorflow.keras.utils import image_dataset_from_directory, split_dataset
-
+import keras_tuner
 
 img_size = (180, 180)
 
-conv_base = keras.applications.vgg16.VGG16(
+conv_base = keras.applications.resnet.ResNet152(
     weights="imagenet",
     include_top=False,
     input_shape=(180, 180, 3))
 conv_base.trainable = False
+# conv_base.trainable = True
+# for layer in conv_base.layers[:-4]:
+#     layer.trainable = False
 
 
 # обогащение выборки
 data_augmentation = keras.Sequential(
-[
-    layers.RandomFlip("horizontal"),
-    layers.RandomRotation(0.1),
-    layers.RandomZoom(0.2),
-])
-
+    [
+        layers.RandomFlip("horizontal"),
+        layers.RandomRotation(0.1),
+        layers.RandomZoom(0.2),
+    ])
 
 
 input_dir = "assets/dog"
@@ -37,7 +39,8 @@ for fname in os.listdir(input_dir):
         continue
     labels_dict[fname] = len(labels_dict)
 
-model_name = "beerd_imagenet_25_04_2023.keras"
+model_name = "beerd_imagenet_02_05_2023.keras"
+model_dir = "beerd_imagenet"
 train_dataset, val_ds = image_dataset_from_directory(
     input_dir,
     labels="inferred",
@@ -54,47 +57,72 @@ train_dataset, val_ds = image_dataset_from_directory(
     follow_links=False,
     crop_to_aspect_ratio=False
 )
-
 validation_dataset, test_dataset = split_dataset(val_ds, left_size=0.8)
 
-inputs = keras.Input(shape=(180, 180, 3))
-x = data_augmentation(inputs)
-x = keras.applications.vgg16.preprocess_input(x)
-x = conv_base(x)
-x = layers.Flatten()(x)
-x = layers.Dense(512)(x)
-x = layers.Dropout(0.5)(x)
-outputs = layers.Dense(len(labels_dict), activation="softmax")(x)
-model = keras.Model(inputs, outputs)
+def build_model(hp):
+    inputs = keras.Input(shape=(180, 180, 3))
+    x = data_augmentation(inputs)
+    x = keras.applications.resnet.preprocess_input(x)
+    x = conv_base(x)
+    x = layers.Flatten()(x)
+    units = hp.Int(name="units", min_value=1536, max_value=2048, step=512)
+    x = layers.Dense(units, activation="relu")(x)
+    x = layers.Dropout(0.5)(x)
+    outputs = layers.Dense(len(labels_dict), activation="softmax")(x)
+    model = keras.Model(inputs, outputs)
+    optimizer = hp.Choice(name="optimizer", values=["rmsprop", "adam"])
+    model.compile(optimizer=optimizer,
+                loss="categorical_crossentropy", metrics=['accuracy'])
+    return model
 
-model.compile(optimizer="rmsprop",
-              loss="categorical_crossentropy", metrics=['accuracy'])
+
+def build_model_new():
+    inputs = keras.Input(shape=(180, 180, 3))
+    x = data_augmentation(inputs)
+    x = keras.applications.resnet.preprocess_input(x)
+    x = conv_base(x)
+    x = layers.Flatten()(x)
+    x = layers.Dropout(0.5)(x)
+    outputs = layers.Dense(len(labels_dict), activation="softmax")(x)
+    model = keras.Model(inputs, outputs)
+    model.compile(optimizer="adam",
+                loss="categorical_crossentropy", metrics=['accuracy'])
+    return model
+
+
+
+# tuner = keras_tuner.BayesianOptimization(
+#     build_model,
+#     objective='val_accuracy',
+#     max_trials=100,
+#     executions_per_trial=2,
+#     directory=model_dir,
+#     overwrite=True,)
+
+# callbacks = [
+#     keras.callbacks.EarlyStopping(monitor="val_loss", patience=5)
+# ]
 callbacks = [
     keras.callbacks.ModelCheckpoint(model_name,
-                                    save_best_only=True)
+                                    save_best_only=True, monitor="val_accuracy"),
+    keras.callbacks.EarlyStopping(monitor="val_accuracy", patience=5)
 ]
-history = model.fit(train_dataset,
-                    epochs=100,
-                    callbacks=callbacks,
-                    validation_data=validation_dataset,)
 
-epochs = range(1, len(history.history["loss"]) + 1)
-loss = history.history["loss"]
-val_loss = history.history["val_loss"]
-acc = history.history["accuracy"]
-val_acc = history.history["val_accuracy"]
-plt.plot(epochs, acc, "bo", label="Точность на этапе обучения")
-plt.plot(epochs, val_acc, "b", label="Точность на этапе проверки")
-plt.title("Точность на этапах обучения и проверки")
-plt.legend()
-plt.figure()
-plt.plot(epochs, loss, "bo", label="Потери на этапе обучения")
-plt.plot(epochs, val_loss, "b", label="Потери на этапе проверки")
-plt.title("Потери на этапах обучения и проверки")
-plt.legend()
-plt.show()
+# tuner.search(train_dataset,
+#                     epochs=100,
+#                     callbacks=callbacks,
+#                     validation_data=validation_dataset,)
+
+# best_models = tuner.get_best_models(1)
+# best_models = keras.models.load_model(model_name)
+best_models = build_model_new()
+best_models.fit(train_dataset,
+                    epochs=30,
+                    callbacks=callbacks,
+                    validation_data=validation_dataset)
 
 
 test_model = keras.models.load_model(model_name)
 test_loss, test_acc = test_model.evaluate(test_dataset)
-print(f"Test accuracy: {test_acc:.3f}")
+print(f"Test accuracy: {test_acc:.3f}")
+