RuntimeError: result type Float can't be cast to the desired output type long int

[sayyidan-i]

I tried to training custom dataset but turns out I get this error, please enlighten me

---

RuntimeError Traceback (most recent call last)
/content/Yolo-FastestV2-Tooth/train.py in
108 preds = model(imgs)
109 # loss计算
--> 110 iou_loss, obj_loss, cls_loss, total_loss = utils.loss.compute_loss(preds, targets, cfg, device)
111
112 # 反向传播求解梯度

1 frames
/content/Yolo-FastestV2-Tooth/utils/loss.py in build_target(preds, targets, cfg, device)
117 # Append
118 a = t[:, 6].long() # anchor indices
--> 119 indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
120 tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
121 anch.append(anchors_cfg[a]) # anchors

RuntimeError: result type Float can't be cast to the desired output type long int

[sanimgh]

do you have a solution ?

[dinhln03]

at util/loss.py, you may need to change to this in build_target function, then it'll work

[flanremi]

indices.append((b, a, gj.clamp_(0, gain[3].long() - 1), gi.clamp_(0, gain[2].long() - 1)))
you need edit your code to this one, then will work