MCPcopy Create free account
hub / github.com/argman/EAST / loss

Function loss

model.py:103–136  ·  view source on GitHub ↗

define the loss used for training, contraning two part, the first part we use dice loss instead of weighted logloss, the second part is the iou loss defined in the paper :param y_true_cls: ground truth of text :param y_pred_cls: prediction os text :param y_true_geo: ground t

(y_true_cls, y_pred_cls,
         y_true_geo, y_pred_geo,
         training_mask)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

dice_coefficientFunction · 0.85

Tested by

no test coverage detected