关于后处理

1 图像语义分割Iou阈值

def iou_metric_batch(y_true_in, y_pred_in):
    batch_size = y_true_in.shape[0]
    metric = []
    for batch in range(batch_size):
        value = iou_metric(y_true_in[batch], y_pred_in[batch])
        metric.append(value)
    return np.mean(metric)
    
thresholds = np.linspace(0, 1, 50)
ious = np.array([iou_metric_batch(y_valid_ori, np.int32(preds_valid > threshold)) for threshold in tqdm_notebook(thresholds)])

2 其他

skimage去除小连通域；

---

参考：
1 kaggle 后处理；