# plt.savefig('../results/wrong_kitchen.png') # plt.show() # util.save_wordmap(wordmap, filename) # visual_recog.build_recognition_system(num_workers=6) # conf, accuracy = visual_recog.evaluate_recognition_system(num_workers=6) # print(conf) # print(accuracy) # wrong = np.load("../results/wrong_prediction.npy") # for item in wrong: # file_path, actual, predict = item # print(file_path, actual, predict) # if actual == 1 and predict == 7: # print(file_path) # vgg16 = torchvision.models.vgg16(pretrained=True).double() # vgg16.eval() # print(list(vgg16.children())) vgg16_weights = util.get_VGG16_weights() # deep_recog.build_recognition_system(vgg16_weights, num_workers=6) # deep = np.load("../results/trained_system_deep.npz", allow_pickle=True) # print(deep['features'].shape) # print(deep['labels'].shape) conf, accuracy = deep_recog.evaluate_recognition_system(vgg16_weights, num_workers=4) # conf = np.load("../results/conf_deep.npy") print(conf) print(accuracy) # print(np.trace(conf)/conf.sum())
if __name__ == '__main__': num_cores = util.get_num_CPU() path_img = "../data/kitchen/sun_aasmevtpkslccptd.jpg" image = skimage.io.imread(path_img) image = image.astype('float') / 255 filter_responses = visual_words.extract_filter_responses(image) util.display_filter_responses(filter_responses) visual_words.compute_dictionary(num_workers=num_cores) dictionary = np.load('dictionary.npy') img = visual_words.get_visual_words(image, dictionary) #util.save_wordmap(wordmap, filename) visual_recog.build_recognition_system(num_workers=num_cores) conf, accuracy = visual_recog.evaluate_recognition_system( num_workers=num_cores) print(conf) print(np.diag(conf).sum() / conf.sum()) vgg16 = torchvision.models.vgg16(pretrained=True).double() vgg16.eval() deep_recog.build_recognition_system(vgg16, num_workers=num_cores // 2) conf = deep_recog.evaluate_recognition_system(vgg16, num_workers=num_cores // 2) print(conf) print(np.diag(conf).sum() / conf.sum()) #
if __name__ == '__main__': num_cores = util.get_num_CPU() path_img = "../data/kitchen/sun_aasmevtpkslccptd.jpg" image = skimage.io.imread(path_img) image = image.astype('float') / 255 filter_responses = visual_words.extract_filter_responses(image) util.display_filter_responses(filter_responses) visual_words.compute_dictionary(num_workers=num_cores) dictionary = np.load('dictionary.npy') filename = "test.jpg" img = visual_words.get_visual_words(image, dictionary) util.save_wordmap(img, filename) visual_recog.build_recognition_system(num_workers=num_cores) conf, accuracy = visual_recog.evaluate_recognition_system( num_workers=num_cores) print(conf) print(np.diag(conf).sum() / conf.sum()) vgg16 = torchvision.models.vgg16(pretrained=True).double() vgg16.eval() deep_recog.build_recognition_system(vgg16, num_workers=num_cores) conf, accuracy = deep_recog.evaluate_recognition_system( vgg16, num_workers=num_cores) print(conf) print(np.diag(conf).sum() / conf.sum())