Last active
March 18, 2020 02:33
-
-
Save krishnak/a869ca18e5b14564bc01dbf37cba8d28 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from keras import backend as K | |
def custom_loss(args, anchors, num_classes, ignore_thresh=.5, print_loss=False): | |
num_layers = len(anchors)//3 # default setting | |
yolo_outputs = args[:num_layers] | |
y_true = args[num_layers:] | |
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]] | |
input_shape = K.cast(K.shape(yolo_outputs[0])[1:3] * 32, K.dtype(y_true[0])) | |
grid_shapes = [K.cast(K.shape(yolo_outputs[l])[1:3], K.dtype(y_true[0])) for l in range(num_layers)] | |
loss = 0 | |
m = K.shape(yolo_outputs[0])[0] # batch size, tensor | |
mf = K.cast(m, K.dtype(yolo_outputs[0])) | |
for l in range(num_layers): | |
object_mask = y_true[l][..., 4:5] | |
true_class_probs = y_true[l][..., 5:] | |
grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l], | |
anchors[anchor_mask[l]], num_classes, input_shape, calc_loss=True) | |
pred_box = K.concatenate([pred_xy, pred_wh]) | |
# Darknet raw box to calculate loss. | |
raw_true_xy = y_true[l][..., :2]*grid_shapes[l][::-1] - grid | |
raw_true_wh = K.log(y_true[l][..., 2:4] / anchors[anchor_mask[l]] * input_shape[::-1]) | |
raw_true_wh = K.switch(object_mask, raw_true_wh, K.zeros_like(raw_true_wh)) # avoid log(0)=-inf | |
box_loss_scale = 2 - y_true[l][...,2:3]*y_true[l][...,3:4] | |
# Find ignore mask, iterate over each of batch. | |
ignore_mask = tf.TensorArray(K.dtype(y_true[0]), size=1, dynamic_size=True) | |
object_mask_bool = K.cast(object_mask, 'bool') | |
def loop_body(b, ignore_mask): | |
true_box = tf.boolean_mask(y_true[l][b,...,0:4], object_mask_bool[b,...,0]) | |
iou = box_iou(pred_box[b], true_box) | |
best_iou = K.max(iou, axis=-1) | |
ignore_mask = ignore_mask.write(b, K.cast(best_iou<ignore_thresh, K.dtype(true_box))) | |
return b+1, ignore_mask | |
_, ignore_mask = tf.while_loop(lambda b,*args: b<m, loop_body, [0, ignore_mask]) | |
ignore_mask = ignore_mask.stack() | |
ignore_mask = K.expand_dims(ignore_mask, -1) | |
# K.binary_crossentropy is helpful to avoid exp overflow. | |
xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[...,0:2], from_logits=True) | |
wh_loss = object_mask * box_loss_scale * 0.5 * K.square(raw_true_wh-raw_pred[...,2:4]) | |
confidence_loss = object_mask * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True)+ \ | |
(1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask | |
class_loss = object_mask * K.binary_crossentropy(true_class_probs, raw_pred[...,5:], from_logits=True) | |
xy_loss = K.sum(xy_loss) / mf | |
wh_loss = K.sum(wh_loss) / mf | |
confidence_loss = K.sum(confidence_loss) / mf | |
class_loss = K.sum(class_loss) / mf | |
loss += xy_loss + wh_loss + confidence_loss + class_loss | |
if print_loss: | |
loss = tf.Print(loss, [loss, xy_loss, wh_loss, confidence_loss, class_loss, K.sum(ignore_mask)], message='loss: ') | |
return loss |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment