120 lines
3.0 KiB
Python
120 lines
3.0 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
|
||
|
|
import keras
|
||
|
|
|
||
|
|
# %%
|
||
|
|
os.chdir(r"C:\Users\pittb\Documents\biedronkapp_2.0\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)
|
||
|
|
# %%
|
||
|
|
model = keras.models.load_model('saved_model/my_model')
|
||
|
|
|
||
|
|
# %%
|
||
|
|
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))
|
||
|
|
|
||
|
|
|
||
|
|
# %%
|
||
|
|
img_path = r"test\azjatyckie\Asian_lady_beetle-(Harmonia-axyridis).jpg"
|
||
|
|
|
||
|
|
img_nump = np.array(cv2.cvtColor(cv2.imread(img_path), cv2.COLOR_BGR2RGB))
|
||
|
|
|
||
|
|
plt.imshow(img_nump)
|
||
|
|
plt.show()
|
||
|
|
|
||
|
|
img_nump = cv2.resize(img_nump,(224,224))
|
||
|
|
img_nump = img_nump/255.0
|
||
|
|
img_nump = img_nump[np.newaxis,...]
|
||
|
|
|
||
|
|
pr = model.predict(img_nump)
|
||
|
|
print('azjatycka: '+str(pr[0][0])+' , siedmiokropka: '+str(pr[0][1]))
|
||
|
|
print(['azjatycka' if np.argmax(pr,axis=1)[0]==0 else 'siedmiokropka'][0])
|
||
|
|
# %%
|