print(model.summary())
# Compile Model
model.compile(optimizer='Adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
'''
train model
'''
batch_size = 256
num_epochs = 20
# Train Model
history = model.fit(trainX, trainY, batch_size=batch_size,
epochs=num_epochs) #, callbacks=[checkpoint])
predY = model.predict(testX)
y_pred = np.argmax(predY, axis=1)
y_actual = np.argmax(testY, axis=1)
#y_label= [labels[k] for k in y_pred]
cm = confusion_matrix(y_actual, y_pred)
print(cm)
'''
confusion matrix
'''
import itertools
def plot_confusion_matrix(cm,
model.add(MaxPooling2D((2,2),strides=(2,2))) model.add(Conv2D(512,(3,3),activation='relu',padding='same')) model.add(Conv2D(512,(3,3),activation='relu',padding='same')) model.add(Conv2D(512,(3,3),activation='relu',padding='same')) model.add(MaxPooling2D((2,2),strides=(2,2))) model.add(Flatten()) model.add(Dense(600,activation='relu')) model.add(Dense(600,activation='relu')) model.add(Dense(2,activation='softmax')) model.compile(optimizer='adam',loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(train_record_fname,test_record_fname,epochs=2) """# Neuer Ansatz A) Eine andere Herangehensweise mit anderen Funktionen und Befehlen. Könnte sich rentieren das Netz in diese Richtung auszubauen bzw Betandteile zu übernehmen. ---wurde noch nicht auf das bestehende Netz angepasst--- """ ### A) Neuer Ansatz CNN_model https://androidkt.com/feeding-your-own-data-set-into-the-cnn-model-in-tensorflow/ labels=label_map_pbtxt_fname _DEFAULT_IMAGE_SIZE = 252 _NUM_CHANNELS = 3 _NUM_CLASSES = 4
model = Model(input_layer, output)
# Compiling model
optimizer = keras.optimizers.SGD(lr=learning_rate, momentum=momentum)
model.compile(
loss="sparse_categorical_crossentropy",
optimizer=optimizer,
metrics=["accuracy"]
)
model.summary()
# Train the model
history = model.fit(
train_data,
epochs=13,
validation_data = test_data
)
"""# Saving and Recreating the trained model"""
## Save the whole model
model.save('./trained_CNN/imagewoof/my_model_imagewoof.h5')
## Recreate whole model
new_model=keras.models.load_model('./trained_CNN/imagewoof/my_model_imagewoof.h5')
new_model.summary()
"""# DOWNLOAD created files
In this case downloading the previously created model.
(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()
x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))
x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
ip = Input(shape=(28, 28, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(ip)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dense(10, activation='softmax')(x)
x = Model(ip, x)
x.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
x.fit(x_train,
y_train,
epochs=10,
batch_size=128,
shuffle=True,
verbose=1,
validation_data=(x_test, y_test))
x.save("fashion_mnist2.h5")
model = Model(inputs=vgg.input, outputs=model)
for layer in vgg.layers:
layer.trainable = False
# compile
print("[INFO] compiling model...")
opt = Adam(lr=lr, decay=lr / epochs)
model.compile(loss="binary_crossentropy", optimizer=opt, metrics=["accuracy"])
# train
print("[INFO] training model...")
H = model.fit(x=X_train,
y=y_train,
batch_size=batch_size,
steps_per_epoch=len(X_train) // batch_size,
validation_data=(X_test, y_test),
validation_steps=len(X_test) // batch_size,
epochs=epochs)
# test
print("[INFO] evaluating model...")
predIdxs = model.predict(X_test, batch_size=batch_size)
predIdxs = np.argmax(predIdxs, axis=1)
print(
classification_report(y_test.argmax(axis=1),
predIdxs,
target_names=lb.classes_))
# confusion matrix
