train_err = 0 train_batches = 0 confusion_train = ConfusionMatrix(n_class) # Generate minibatches and train on each one of them for batch in iterate_minibatches(X_tr, y_tr, mask_tr, batch_size, shuffle=True): inputs, targets, in_masks = batch tr_err, predict = train_fn(inputs, targets, in_masks) train_err += tr_err train_batches += 1 preds = np.argmax(predict, axis=-1) confusion_train.batch_add(targets, preds) train_loss = train_err / train_batches train_accuracy = confusion_train.accuracy() cf_train = confusion_train.ret_mat() # Full pass validation set val_err = 0 val_batches = 0 confusion_valid = ConfusionMatrix(n_class) # Generate minibatches and train on each one of them for batch in iterate_minibatches(X_val, y_val, mask_val, batch_size): inputs, targets, in_masks = batch err, predict_val, alpha, context = val_fn(inputs, targets, in_masks) val_err += err val_batches += 1 preds = np.argmax(predict_val, axis=-1) confusion_valid.batch_add(targets, preds)
accuracy, predictions = dev_step(x_test, y_test)
#dev_step(x_dev, y_dev, writer=dev_summary_writer)
outputs = np.argmax(predictions, axis=-1)
print(outputs.shape)
confusion_test = ConfusionMatrix(num_classes)
y_test = np.argmax(y_test, axis=-1)
print(y_test.shape)
confusion_test.batch_add(y_test, outputs)
test_accuracy = confusion_test.accuracy()
a, positive_predictive_value = confusion_test.positive_predictive_value()
b, negative_predictive_value = confusion_test.negative_predictive_value()
e, F1 = confusion_test.F1()
f, MCC = confusion_test.matthews_correlation()
cf_val = confusion_test.ret_mat()
print("FINAL TEST RESULTS")
print(confusion_test)
print(cf_val)
print(" test accuracy:\t\t{:.2f} %".format(test_accuracy * 100))
print(a)
print(b)
print(e)
print(f)
print(" test positive_predictive_value:\t\t{:.2f} %".format(
positive_predictive_value * 100))
print(" test negative_predictive_value:\t\t{:.2f} %".format(
negative_predictive_value * 100))
print(" test F1:\t\t{:.2f} %".format(F1 * 100))
print(" test MCC:\t\t{:.2f} %".format(MCC * 100))
print("\nEvaluation:")
accuracy, predictions = dev_step(x_test,
y_test,
writer=dev_summary_writer)
if accuracy > max_acc:
max_acc = accuracy
path = saver.save(sess,
checkpoint_prefix,
global_step=current_step)
print("Saved model checkpoint to {}\n".format(path))
else:
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
saver.restore(sess, ckpt.model_checkpoint_path)
accuracy, predictions = dev_step(
x_test,
y_test) # dev_step(x_dev, y_dev, writer=dev_summary_writer)
outputs = np.argmax(predictions, axis=-1)
print(outputs.shape)
confusion_test = ConfusionMatrix(num_classes)
y_test = np.argmax(y_test, axis=-1)
print(y_test.shape)
confusion_test.batch_add(y_test, outputs)
test_accuracy = confusion_test.accuracy()
cf_test = confusion_test.ret_mat()
print("FINAL TEST RESULTS")
print(confusion_test)
print(" test accuracy:\t\t{:.2f} %".format(test_accuracy * 100))
print(" test Gorodkin:\t\t{:.2f}".format(gorodkin(cf_test)))
print(" test IC:\t\t{:.2f}".format(IC(cf_test)))