location: "models/yolo_layer.py", line 438,error: obj_mask[b, a, j, i] = 1 IndexError: index 40 is out of bounds for dimension 0 with size 40 about pytorch_yolov3

[BucolicWind]

        for ti in range(best_n.shape[0]):
            if best_n_mask[ti] == 1:
                i, j = truth_i[ti], truth_j[ti]
                a = best_n[ti]
                obj_mask[b, a, j, i] = 1
                tgt_mask[b, a, j, i, :] = 1
                target[b, a, j, i, 0] = truth_x_all[b, ti] - \
                    truth_x_all[b, ti].to(torch.int16).to(torch.float)
                target[b, a, j, i, 1] = truth_y_all[b, ti] - \
                    truth_y_all[b, ti].to(torch.int16).to(torch.float)
                target[b, a, j, i, 2] = torch.log(
                    truth_w_all[b, ti] / torch.Tensor(self.masked_anchors)[best_n[ti], 0] + 1e-16)
                target[b, a, j, i, 3] = torch.log(
                    truth_h_all[b, ti] / torch.Tensor(self.masked_anchors)[best_n[ti], 1] + 1e-16)
                target[b, a, j, i, 4] = 1
                target[b, a, j, i, 5 + labels[b, ti,
                                              0].to(torch.int16).numpy()] = 1
                tgt_scale[b, a, j, i, :] = torch.sqrt(
                    2 - truth_w_all[b, ti] * truth_h_all[b, ti] / fsize / fsize)

I try to change this code to train my data, error occurred during the code above.

[hirotomusiker]

Hi,
The dimension 0 of obj_mask should be batchsize and 'b' stands for the current batch number in the for loop.

        obj_mask = torch.ones(batchsize, self.n_anchors,
                              fsize, fsize).type(dtype)

        for b in range(batchsize):
...
                obj_mask[b, a, j, i] = 1

So b changes from 0 to 39 if your batchsize is 40.

Which part of yolo_layer.py have you changed?

[hirotomusiker]

@BucolicWind
Please put your reply on this thread.

Hi, I simply copy your code and run,but i will also meet this problem.i changed the bctchsize to 8 >when training in the visdrone dataset,

If you train on visdrone, you should have changed something - dataloader, config,.. and so on.

And

location: "models/yolo_layer.py", line 438

The original yolo_layer.py does not have 438th line. Please let us know if you customized the code.

Thank you.