def main(_):
sess = tf.compat.v1.Session()
model = MyModel(sess,model_configs)
if args.mode == "train":
x_train, y_train, _,_ = load_data(args.data_dir)
model.train(x_train, y_train,200)
elif args.mode == "test":
# Testing on public testing dataset
_, _, x_test, y_test = load_data(args.data_dir)
model.evaluate(x_test, y_test)
elif args.mode == "predict":
# Predicting and storing results on private testing dataset
x_test = load_testing_images(args.data_dir)
predictions = model.predict_prob(x_test)
np.save("../predictions.npy", predictions)
if __name__ == '__main__':
model = MyModel(model_configs)
if args.mode == 'train':
print('----- training mode ----')
train,test,orig_trainset = load_data(args.data_dir,train_aug=training_configs['train_augmentation']) # augment the train data with config
train,valid = train_valid_split(train,orig_trainset,train_ratio=1)
if args.resume_checkpoint is not None:
checkpoint = torch.load('../saved_models/' + args.resume_checkpoint)
epoch,accuracy_type,prev_accuracy = (checkpoint[k] for k in ['epoch','accuracy_type','accuracy'])
print('RESUME---> Loading model from Epoch %d with %s Accuracy %f' %(epoch,accuracy_type,prev_accuracy))
else:
checkpoint = None
model.train(train, training_configs,valid=None,test=test,checkpoint=checkpoint) # note test data is used only to evaluate model performance during training
model.evaluate(test)
elif args.mode == 'test':
# Testing on public testing dataset
_, test, _ = load_data(args.data_dir,None)
if args.checkpoint is not None:
checkpoint = torch.load('../saved_models/' + args.checkpoint)
print('Loading Model--->')
else:
raise('No Checkpoint file specified! Specify one with --checkpoint')
model.network.load_state_dict(checkpoint['net'])
test_accuracy, correct, total = model.evaluate(test)
print("[%s%s test results] Model Accuracy %f, Total Correctt %d, Total Test Samples %d" %(args.checkpoint,utils.get_time(),test_accuracy,correct,total))
elif args.mode == 'predict':
parser.add_argument("--test_file", help="path to the test file")
parser.add_argument("--save_dir", help="path to save the results")
args = parser.parse_args()
if __name__ == '__main__':
model = MyModel(model_configs, training_configs)
if args.mode == 'train':
x_train, y_train, x_test, y_test = load_data(args.data_dir)
x_train, y_train, x_valid, y_valid = train_valid_split(
x_train, y_train)
model.train(x_train, y_train, x_valid, y_valid)
model.save_weights(
os.path.join(args.save_dir, model_configs["version"], ""))
model.evaluate(x_test, y_test)
elif args.mode == 'test':
# Testing on public testing dataset
model.load_weights(
os.path.join(args.save_dir, model_configs["version"], ""))
_, _, x_test, y_test = load_data(args.data_dir)
model.evaluate(x_test, y_test)
elif args.mode == 'predict':
# Predicting and storing results on private testing dataset
model.load_weights(
os.path.join(args.save_dir, model_configs["version"], ""))
x_test = load_testing_images(args.test_file)
predictions = model.predict_prob(x_test)
np.save("final_pred_" + model_configs["version"] + ".npy", predictions)
model = MyModel(model_configs)
# model.load()
if args.mode == 'train':
x_train, y_train, x_test, y_test = load_data(args.data_dir)
x_train, y_train, x_valid, y_valid = train_valid_split(
x_train, y_train)
train_stats = model.train(x_train, y_train, training_configs, x_valid,
y_valid)
w = csv.writer(
open(
os.path.join(model_configs["save_dir"], model_configs['name'])
+ ".csv", "w"))
for key, val in train_stats.items():
w.writerow([key, val])
score, loss = model.evaluate(x_test, y_test)
print("The test score is: {:.3f}% ({:.4f})".format(score * 100, loss))
elif args.mode == 'test':
model.load()
# Testing on public testing dataset
_, _, x_test, y_test = load_data(args.data_dir)
score, loss = model.evaluate(x_test, y_test)
print("The test score is: {:.3f}% ({:.4f})".format(score * 100, loss))
elif args.mode == 'predict':
model.load()
# Predicting and storing results on private testing dataset
x_test = load_testing_images(args.data_dir)
predictions = model.predict_prob(x_test)
np.save(args.result_dir, predictions)