def auto_like(self): while True: sleep(10) try: rawURL = self.get_image_path() image_url = self.get_url(rawURL) print(image_url) user['photos'].append(image_url) print(user['photos']) person1 = person.Person(user) detection_graph = person_detector.open_graph() with detection_graph.as_default(): with tf.Session() as sess: classifier = Classifier( graph="./tf/training_output/retrained_graph.pb", labels="./tf/training_output/retrained_labels.txt") score = person1.predict_likeliness(classifier, sess) print(score) if (score[0] <= 0.6): self.dislike() print("Nope") else: self.like() print("YES") user['photos'].pop() except Exception: try: self.close_pop_up() except Exception: try: self.match_pop_up() except Exception: try: self.window_pop_up() except Exception: # self.out_of_like_pop_up() break
import person_detector import tensorflow as tf command = """ python retrain.py --bottleneck_dir=tf/training_data/bottlenecks --model_dir=tf/training_data/inception --summaries_dir=tf/training_data/summaries/basic --output_graph=tf/training_output/retrained_graph.pb --output_labels=tf/training_output/retrained_labels.txt --image_dir=./images/classified --how_many_training_steps=50000 --testing_percentage=20 --learning_rate=0.001 """ IMAGE_FOLDER = "./images/unclassified" POS_FOLDER = "./images/classified/positive" NEG_FOLDER = "./images/classified/negative" LOVOO_FOLDER = "./images/lovoo" if __name__ == "__main__": detection_graph = person_detector.open_graph() images = [f for f in os.listdir(IMAGE_FOLDER) if os.path.isfile(os.path.join(IMAGE_FOLDER, f))] positive_images = filter(lambda image: (image.startswith("1_")), images) negative_images = filter(lambda image: (image.startswith("0_")), images) lovoo_images = [f for f in os.listdir(LOVOO_FOLDER) if os.path.isfile(os.path.join(LOVOO_FOLDER, f))] with detection_graph.as_default(): with tf.Session() as sess: for pos in lovoo_images: old_filename = LOVOO_FOLDER + "/" + pos new_filename = POS_FOLDER + "/" + pos[:-5] + ".jpg" if not os.path.isfile(new_filename): print(">> Moving positive image: " + pos)