136 lines
3.3 KiB
Python
136 lines
3.3 KiB
Python
#%%
|
|
|
|
from tensorflow.keras.layers import Input, Lambda, Dense, Flatten,Dropout
|
|
from tensorflow.keras.models import Model
|
|
from tensorflow.keras.applications.vgg19 import VGG19
|
|
from tensorflow.keras.applications.vgg19 import preprocess_input
|
|
from tensorflow.keras.preprocessing import image
|
|
from tensorflow.keras.preprocessing.image import ImageDataGenerator
|
|
from tensorflow.keras.models import Sequential
|
|
import numpy as np
|
|
import pandas as pd
|
|
import os
|
|
import cv2
|
|
import matplotlib.pyplot as plt
|
|
# %%
|
|
os.chdir(r"C:\Users\pittb\Documents\biedronkapp\BiedronkApp\biedronki_dataset")
|
|
train_path="train"
|
|
test_path="test"
|
|
# %%
|
|
x_train=[]
|
|
|
|
for folder in os.listdir(train_path):
|
|
|
|
sub_path=train_path+"/"+folder
|
|
|
|
for img in os.listdir(sub_path):
|
|
image_path=sub_path+"/"+img
|
|
|
|
img_arr=cv2.imread(image_path)
|
|
|
|
img_arr=cv2.resize(img_arr,(224,224))
|
|
|
|
x_train.append(img_arr)
|
|
|
|
x_test=[]
|
|
|
|
for folder in os.listdir(test_path):
|
|
|
|
sub_path=test_path+"/"+folder
|
|
|
|
for img in os.listdir(sub_path):
|
|
|
|
image_path=sub_path+"/"+img
|
|
|
|
img_arr=cv2.imread(image_path)
|
|
|
|
img_arr=cv2.resize(img_arr,(224,224))
|
|
|
|
x_test.append(img_arr)
|
|
# %%
|
|
train_x=np.array(x_train)
|
|
test_x=np.array(x_test)
|
|
|
|
train_x=train_x/255.0
|
|
test_x=test_x/255.0
|
|
# %%
|
|
train_datagen = ImageDataGenerator(rescale = 1./255)
|
|
test_datagen = ImageDataGenerator(rescale = 1./255)
|
|
# %%
|
|
training_set = train_datagen.flow_from_directory(train_path,
|
|
target_size = (224, 224),
|
|
batch_size = 32,
|
|
class_mode = 'sparse')
|
|
test_set = test_datagen.flow_from_directory(test_path,
|
|
target_size = (224, 224),
|
|
batch_size = 32,
|
|
class_mode = 'sparse')
|
|
# %%
|
|
train_y=training_set.classes
|
|
test_y=test_set.classes
|
|
|
|
training_set.class_indices
|
|
|
|
train_y.shape,test_y.shape
|
|
# %%
|
|
IMAGE_SIZE = [224, 224]
|
|
|
|
vgg = VGG19(input_shape=IMAGE_SIZE + [3], weights='imagenet', include_top=False)
|
|
|
|
for layer in vgg.layers:
|
|
layer.trainable = False
|
|
|
|
# %%
|
|
# our layers - you can add more if you want
|
|
x = Flatten()(vgg.output)
|
|
|
|
prediction = Dense(2, activation='softmax')(x)
|
|
# %%
|
|
# create a model object
|
|
model = Model(inputs=vgg.input, outputs=prediction)
|
|
|
|
# view the structure of the model
|
|
model.summary()
|
|
# %%
|
|
model.compile(
|
|
loss='sparse_categorical_crossentropy',
|
|
optimizer="adam",
|
|
metrics=['accuracy']
|
|
)
|
|
# %%
|
|
from tensorflow.keras.callbacks import EarlyStopping
|
|
early_stop=EarlyStopping(monitor='val_loss',mode='min',verbose=1,patience=5)
|
|
# %%
|
|
history = model.fit(
|
|
train_x,
|
|
train_y,
|
|
epochs=10,
|
|
callbacks=[early_stop],
|
|
batch_size=32,shuffle=True)
|
|
# %%
|
|
plt.plot(history.history['loss'], label='train loss')
|
|
plt.legend()
|
|
|
|
plt.savefig('vgg-loss-rps-1.png')
|
|
plt.show()
|
|
# %%
|
|
# accuracies
|
|
plt.plot(history.history['accuracy'], label='train acc')
|
|
plt.legend()
|
|
|
|
plt.savefig('vgg-acc-rps-1.png')
|
|
plt.show()
|
|
# %%
|
|
model.evaluate(test_x,test_y,batch_size=6)
|
|
# %%
|
|
from sklearn.metrics import accuracy_score,classification_report,confusion_matrix
|
|
import numpy as np
|
|
|
|
y_pred=model.predict(test_x)
|
|
y_pred=np.argmax(y_pred,axis=1)
|
|
|
|
accuracy_score(y_pred,test_y)
|
|
|
|
print(classification_report(y_pred,test_y))
|
|
# %%
|