def store_prediction(self, sess, batch_x, batch_y, batch_z, name):
prediction, blurpredict = sess.run(
[self.net.predicter, self.net.blurpredict],
feed_dict={
self.net.x: batch_x,
self.net.y: batch_y,
self.net.z: batch_z,
self.net.keep_prob: 1.
})
pred_shape = prediction.shape
blurpred_shape = blurpredict.shape
loss = sess.run(self.net.cost,
feed_dict={
self.net.x: batch_x,
self.net.y:
util.crop_to_shape(batch_y, pred_shape),
self.net.z: batch_z,
self.net.keep_prob: 1.
})
logging.info("Verification error= {:.1f}%, loss= {:.4f}".format(
error_rate(prediction,
util.crop_to_shape(batch_y, prediction.shape)), loss))
img = util.combine_img_prediction(batch_x, batch_y, prediction)
util.save_image(img, "%s/%s.jpg" % (self.prediction_path, name))
return pred_shape, blurpred_shape
def store_prediction(self, sess, batch_x, batch_y, name):
y = crop_to_shape_v2(batch_y, self.in_shape)
#print(y.shape)
prediction = sess.run(self.predicter,
feed_dict={
self.x:
crop_to_shape_v2(batch_x, self.in_shape),
self.y: y,
self.Dropout_Rate: 0.,
self.IsTraining: False
})
loss = sess.run(self.loss,
feed_dict={
self.x: crop_to_shape_v2(batch_x, self.in_shape),
self.y: y,
self.IsTraining: False,
self.Dropout_Rate: 0
})
logging.info("Verification error= {:.1f}%, loss= {:.4f}".format(
error_rate(prediction, crop_to_shape_v2(batch_y, self.in_shape)),
loss))
img = util.combine_img_prediction(batch_x, batch_y, prediction)
util.save_image(img, "%s/%s.jpg" % (self.prediction_path, name))
def validate(self, sess, test_size, x_provider, y_provider, n_epoch):
self.net.is_training = False
mean_dice = 0
mean_iou = 0
for val_index in range(test_size):
val_x, val_y = sess.run([x_provider, y_provider])
prediction, loss = sess.run([self.net.predicter, self.net.loss],
feed_dict={
self.net.x: val_x,
self.net.y: val_y,
})
img_predict = prediction.reshape((self.nx, self.ny, 4))
img_predict = self.remove_minor_cc(img_predict, 0.3, 4)
img_y = val_y.reshape((self.nx * self.ny, 4))
img_predict = img_predict.reshape((self.nx * self.ny, 4))
dice, iou = sess.run([self.net.dice, self.net.iou],
feed_dict={
self.net.img_pred: img_predict,
self.net.img_y: img_y
})
dice1 = dice[0]
dice2 = dice[1]
dice3 = dice[2]
dice = (dice1 + dice2 + dice3) / 3
iou1 = iou[0]
iou2 = iou[1]
iou3 = iou[2]
iou = (iou1 + iou2 + iou3) / 3
mean_dice += dice
mean_iou += iou
if val_index == 0:
img = util.combine_img_prediction(val_x, img_y[:, 1],
img_predict[:, 1],
img_y[:, 2], img_predict[:,
2],
img_y[:, 3], img_predict[:,
3])
util.save_image(
img,
"%s/%s.jpg" % (self.prediction_path, "epoch_%s" % n_epoch +
'_%s' % val_index + '_%s' % dice))
mean_dice = mean_dice / test_size
mean_iou = mean_iou / test_size
logging.info(
"Validation Loss: {:.4f}, Dice: {:.4f}, IoU: {:.4f}".format(
loss, mean_dice, mean_iou))
return mean_dice, mean_iou
def store_prediction(self, sess, batch_x, batch_y, name):
prediction = sess.run(self.net.predicter, feed_dict={self.net.x: batch_x,
self.net.y: batch_y,
self.net.keep_prob: 1.})
pred_shape = prediction.shape
loss = sess.run(self.net.cost, feed_dict={self.net.x: batch_x,
self.net.y: batch_y,
self.net.keep_prob: 1.})
logging.info("Validation loss={:.4f}".format(loss))
img = util.combine_img_prediction(batch_x, batch_y, prediction)
util.save_image(img, "%s/%s.jpg" % (self.prediction_path, name))
return pred_shape
def store_prediction(self, sess, batch_x, batch_y, name):
prediction = sess.run(self.net.predicter,
feed_dict={
self.net.x: batch_x,
self.net.y: batch_y,
self.net.keep_prob: 1.
})
pred_shape = prediction.shape
loss = sess.run(self.net.cost,
feed_dict={
self.net.x: batch_x,
self.net.y: batch_y,
self.net.keep_prob: 1.
})
#logging.info("Verification error= {:.2f}%, loss= {:.6f}".format(error_rate(prediction, batch_y), loss))
img = util.combine_img_prediction(batch_x, batch_y, prediction)
util.save_image(img, "%s/%s.jpg" % (self.prediction_path, name))
return pred_shape
def test(self, model_path, data_provider, test_size):
mean_dice = 0
mean_dice1 = 0
mean_dice2 = 0
mean_dice3 = 0
mean_iou = 0
mean_iou1 = 0
mean_iou2 = 0
mean_iou3 = 0
self.net.is_training = False
test_init = data_provider.build_get_data()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(test_init)
x_provider = data_provider.images_test
y_provider = data_provider.gts_test
saver.restore(sess, tf.train.latest_checkpoint(model_path))
for test_index in range(test_size):
test_x, test_y = sess.run([x_provider, y_provider])
prediction, loss = sess.run(
[self.net.predicter, self.net.loss],
feed_dict={
self.net.x: test_x,
self.net.y: test_y,
self.net.keep_prob: 1.,
})
img_predict = prediction.reshape((256, 256, 4))
img_predict = self.remove_minor_cc(img_predict, 0.3, 4)
img_y = test_y.reshape((65536, 4))
img_predict = img_predict.reshape((65536, 4))
dice, iou = sess.run([self.net.dice, self.net.iou],
feed_dict={
self.net.img_pred: img_predict,
self.net.img_y: img_y
})
dice1 = dice[0]
dice2 = dice[1]
dice3 = dice[2]
dice = (dice1 + dice2 + dice3) / 3
iou1 = iou[0]
iou2 = iou[1]
iou3 = iou[2]
iou = (iou1 + iou2 + iou3) / 3
mean_dice += dice
mean_dice1 += dice1
mean_dice2 += dice2
mean_dice3 += dice3
mean_iou += iou
mean_iou1 += iou1
mean_iou2 += iou2
mean_iou3 += iou3
img = util.combine_img_prediction(test_x, img_y[:, 1],
img_predict[:, 1],
img_y[:, 2], img_predict[:,
2],
img_y[:, 3], img_predict[:,
3])
util.save_image(
img, "%s/%s.jpg" % (self.prediction_path,
"test_%s" % test_index + '_%s' % dice))
mean_dice = mean_dice / test_size
mean_iou = mean_iou / test_size
mean_dice1 = mean_dice1 / test_size
mean_dice2 = mean_dice2 / test_size
mean_dice3 = mean_dice3 / test_size
mean_iou1 = mean_iou1 / test_size
mean_iou2 = mean_iou2 / test_size
mean_iou3 = mean_iou3 / test_size
logging.info("Test Loss: {:.4f}, Dice: {:.4f}, IoU: {:.4f}".format(
loss, mean_dice, mean_iou))
logging.info(
"Dice1: {:.4f}, Dice2: {:.4f}, Dice3: {:.4f}, IoU1: {:.4f}, IoU2: {:.4f}, IoU3: {:.4f}"
.format(mean_dice1, mean_dice2, mean_dice3, mean_iou1,
mean_iou2, mean_iou3))
return mean_dice, mean_iou