def run_inference(self, inference_id):
inference_obj = Inference.objects.get(id=inference_id)
inference_obj.task_id = self.request.id
inference_obj.save()
self.update_state(state='image preprocessing', meta={'progress': 0})
img = image.load_img(inference_obj.image.file.filename,
target_size=(150, 150))
img_array = image.image_to_array(img)
img_array.shape = (1, 150, 150, 3)
self.update_state(state='load the model', meta={'progress': 25})
with open('./model_architecture.json', 'r') as f:
model = model_from_json(f.read())
model.load_weights('./model_weights.h5')
self.update_state(state='predict the image', meta={'progress': 50})
prediction = model.predict(img_array, verbose=1)
result = 'unknown'
if prediction < 0.5:
result = 'Normal'
elif prediction > 0.5:
result = 'Pneumonia'
inference_obj.result = result
inference_obj.save()
self.update_state(state='Finished', meta={'progress': 100})
'haarcascade_frontalface_default.xml')
cap=cv2.VideoCapture(0)
while True:
test_image=cap.read()
coverted_image= cv2.cvtColor(test_image, cv2.COLOR_BGR2GRAY)
faces_detected = face_haar_cascade.detectMultiScale(converted_image)
for (x,y,w,h) in faces_detected:
cv2.rectangle(test_image,(x,y), (x+w,y+h), (255,0,0))
roi_gray=gray_image[y:y+w,x:x+h]
roi_gray=cv2.resize(roi_gray,(48,48))
image_pixels = image.image_to_array(roi_gray)
image_pixels = np.expand_dims(image_pixels, axis = 0)
image_pixels /= 255
predictions = model.predict(image_pixels)
max_index = np.argmax(predictions[0])
emotion_detection = ('angry', 'disgust', 'fear',
'happy', 'sad', 'surprise', 'neutral')
emotion_prediction = emotion_detection[max_index]
cv2.putText(test_image, emotion_prediction, (int(x), int(y)))
cv2.putText(frame,label,label_position,cv2.FONT_HERSHEY_SIMPLEX,2,(0,255,0),3)
target_size=(64, 64),
batch_size=batch,
class_mode='binary')
test_set = test_datagen.flow_from_directory('../dataset/test_set',
target_size=(64, 64),
batch_size=batch,
class_mode='binary')
classifier.fit_generator(training_set,
steps_per_epoch=(8000 / batch),
epochs=25,
validation_data=test_set,
validation_steps=(2000 / batch))
elapsed = time.time() - start
print("Elapsed: %f seconds", elapsed)
from keras.models import load_model
classifier.save('cat_or_dog_220batch.h5')
from keras.preprocessing import image
import numpy as np
prediction_image = image.load_img(
'./dataset/single_prediction/cat_or_dog_3.jpg')
prediction_image = image.image_to_array(prediction_image)
prediction_image = np.expand_dims(prediction_image, axis=0)
prediction_image = prediction_image.reshape(64, 64, 3)
print(new_prediction)
import os
import numpy as np
import matplotlib.pyplot as plt
import keras
from keras.layers import *
from keras.models import *
from keras.preprocessing import image
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
model = load_model(os.path.join(BASE_DIR, 'model.h5'))
img = image.load_image('image.jpeg', target_size=(224, 224))
img = image.image_to_array(img)
img = np.expand_dims(img, axis=0)
p = model.predict_classes(img)
print(p)