def main(): model = futils.load_checkpoint(path) with open('cat_to_name.json', 'r') as json_file: cat_to_name = json.load(json_file) probabilities = futils.predict(path_image, model, number_of_outputs, device) labels = [ cat_to_name[str(index + 1)] for index in np.array(probabilities[1][0]) ] probability = np.array(probabilities[0][0]) i = 0 while i < number_of_outputs: print("{} with a probability of {}".format(labels[i], probability[i])) i += 1 print("All done!")
action="store", default='cat_to_name.json') ap.add_argument('--gpu', default="gpu", action="store", dest="gpu") pa = ap.parse_args() path_image = pa.input_img number_of_outputs = pa.top_k power = pa.gpu input_img = pa.input_img path = pa.checkpoint training_loader, testing_loader, validation_loader = futils.load_data() futils.load_checkpoint(path) with open('cat_to_name.json', 'r') as json_file: cat_to_name = json.load(json_file) probabilities = futils.predict(path_image, model, number_of_outputs, power) labels = [ cat_to_name[str(index + 1)] for index in np.array(probabilities[1][0]) ] probability = np.array(probabilities[0][0]) i = 0 while i < number_of_outputs: print("{} with a probability of {}".format(labels[i], probability[i])) i += 1 print("Prediction Mode: ON")
pa = ap.parse_args() path_image = pa.input_img number_of_outputs = pa.top_k power = pa.gpu input_img = pa.input_img checkpoint_path = pa.checkpoint model = futils.load_checkpoint(checkpoint_path) with open('cat_to_name.json', 'r') as json_file: cat_to_name = json.load(json_file) # Process image and predict label via model img = futils.process_image(input_img) probabilities = futils.predict(img, model, number_of_outputs, power) # Display probabilities and labels for each output specified labels = [ cat_to_name[str(index + 1)] for index in np.array(probabilities[1][0]) ] probability = np.array(probabilities[0][0]) print("\n\n**Results from image {} using pretrained model checkpoint {}**". format(path_image, checkpoint_path)) i = 0 while i < number_of_outputs: print("{} with a probability of {}".format(labels[i], probability[i])) i += 1 print("Finished")
action="store", type=str) ap.add_argument('--top_k', default=5, dest="top_k", action="store", type=int) ap.add_argument('--category_names', dest="category_names", action="store", default='cat_to_name.json') ap.add_argument('--gpu', default="gpu", action="store", dest="gpu") pa = ap.parse_args() path_image = pa.input_img number_of_outputs = pa.top_k power = pa.gpu path = pa.checkpoint cat_names = pa.category_names training_loader, testing_loader, validation_loader, train_data = futils.load_data( ) model = futils.load_checkpoint(path) if cat_names: with open(cat_names, 'r') as json_file: cat_to_name = json.load(json_file) prob, classes = futils.predict(path_image, model, number_of_outputs, power) print('File selected: ' + path_image) print(prob) print(classes) print([cat_to_name[x] for x in classes])