torch.jit.frontend.NotSupportedError: Compiled functions can't take variable number of arguments or use keyword-only arguments with defaults:

Hi,
I am trying to save a model using torch.jit.script in the following code:

    with torch.jit.optimized_execution(True):
    	traced_script_module = torch.jit.script(model)# save the converted model
    	traced_script_module.save("yolov3.pt")

But I got this error :

torch.jit.frontend.NotSupportedError: Compiled functions can't take variable number of arguments or use keyword-only arguments with defaults:
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 87
    def forward(self, *input):
                      ~~~~~~ <--- HERE
        r"""Defines the computation performed at every call.

The code of building the model can be found here:

How can I solve this issue?

1 Like

Is the DarkNet the thing you want to script for? Can you provide a smaller example for easier navigation?

Yes, I am trying to script YOLOv3 based on Darknet
The main two classes are YOLOLayer and Darknet

class YOLOLayer(nn.Module):
    """Detection layer"""

    def __init__(self, anchors, num_classes, img_dim=416):
        super(YOLOLayer, self).__init__()
        self.anchors = anchors
        self.num_anchors = len(anchors)
        self.num_classes = num_classes
        self.ignore_thres = 0.5
        self.mse_loss = nn.MSELoss()
        self.bce_loss = nn.BCELoss()
        self.obj_scale = 1
        self.noobj_scale = 100
        self.metrics = {}
        self.img_dim = img_dim
        self.grid_size = 0  # grid size


    def forward(self, x, targets=None, img_dim=None):

        # Tensors for cuda support
        FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
        LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
        ByteTensor = torch.cuda.ByteTensor if x.is_cuda else torch.ByteTensor

        self.img_dim = img_dim
        num_samples = x.size(0)
        grid_size = x.size(2)

        prediction = (
            x.view(num_samples, self.num_anchors, self.num_classes + 5, grid_size, grid_size)
            .permute(0, 1, 3, 4, 2)
            .contiguous()
        )

        # Get outputs
        x = torch.sigmoid(prediction[..., 0])  # Center x
        y = torch.sigmoid(prediction[..., 1])  # Center y
        w = prediction[..., 2]  # Width
        h = prediction[..., 3]  # Height
        pred_conf = torch.sigmoid(prediction[..., 4])  # Conf
        pred_cls = torch.sigmoid(prediction[..., 5:])  # Cls pred.

        # If grid size does not match current we compute new offsets
        if grid_size != self.grid_size:
            self.compute_grid_offsets(grid_size, cuda=x.is_cuda)

        # Add offset and scale with anchors
        pred_boxes = FloatTensor(prediction[..., :4].shape)
        pred_boxes[..., 0] = x.data + self.grid_x
        pred_boxes[..., 1] = y.data + self.grid_y
        pred_boxes[..., 2] = torch.exp(w.data) * self.anchor_w
        pred_boxes[..., 3] = torch.exp(h.data) * self.anchor_h

        output = torch.cat(
            (
                pred_boxes.view(num_samples, -1, 4) * self.stride,
                pred_conf.view(num_samples, -1, 1),
                pred_cls.view(num_samples, -1, self.num_classes),
            ),
            -1,
        )

        if targets is None:
            return output, 0
        else:
            iou_scores, class_mask, obj_mask, noobj_mask, tx, ty, tw, th, tcls, tconf = build_targets(
                pred_boxes=pred_boxes,
                pred_cls=pred_cls,
                target=targets,
                anchors=self.scaled_anchors,
                ignore_thres=self.ignore_thres,
            )

            # Loss : Mask outputs to ignore non-existing objects (except with conf. loss)
            loss_x = self.mse_loss(x[obj_mask], tx[obj_mask])
            loss_y = self.mse_loss(y[obj_mask], ty[obj_mask])
            loss_w = self.mse_loss(w[obj_mask], tw[obj_mask])
            loss_h = self.mse_loss(h[obj_mask], th[obj_mask])
            loss_conf_obj = self.bce_loss(pred_conf[obj_mask], tconf[obj_mask])
            loss_conf_noobj = self.bce_loss(pred_conf[noobj_mask], tconf[noobj_mask])
            loss_conf = self.obj_scale * loss_conf_obj + self.noobj_scale * loss_conf_noobj
            loss_cls = self.bce_loss(pred_cls[obj_mask], tcls[obj_mask])
            total_loss = loss_x + loss_y + loss_w + loss_h + loss_conf + loss_cls

            # Metrics
            cls_acc = 100 * class_mask[obj_mask].mean()
            conf_obj = pred_conf[obj_mask].mean()
            conf_noobj = pred_conf[noobj_mask].mean()
            conf50 = (pred_conf > 0.5).float()
            iou50 = (iou_scores > 0.5).float()
            iou75 = (iou_scores > 0.75).float()
            detected_mask = conf50 * class_mask * tconf
            precision = torch.sum(iou50 * detected_mask) / (conf50.sum() + 1e-16)
            recall50 = torch.sum(iou50 * detected_mask) / (obj_mask.sum() + 1e-16)
            recall75 = torch.sum(iou75 * detected_mask) / (obj_mask.sum() + 1e-16)

            self.metrics = {
                "loss": to_cpu(total_loss).item(),
                "x": to_cpu(loss_x).item(),
                "y": to_cpu(loss_y).item(),
                "w": to_cpu(loss_w).item(),
                "h": to_cpu(loss_h).item(),
                "conf": to_cpu(loss_conf).item(),
                "cls": to_cpu(loss_cls).item(),
                "cls_acc": to_cpu(cls_acc).item(),
                "recall50": to_cpu(recall50).item(),
                "recall75": to_cpu(recall75).item(),
                "precision": to_cpu(precision).item(),
                "conf_obj": to_cpu(conf_obj).item(),
                "conf_noobj": to_cpu(conf_noobj).item(),
                "grid_size": grid_size,
            }

            return output, total_loss


class Darknet(nn.Module):
    """YOLOv3 object detection model"""

    def __init__(self, config_path, img_size=416):
        super(Darknet, self).__init__()
        self.module_defs = parse_model_config(config_path)
        self.hyperparams, self.module_list = create_modules(self.module_defs)
        self.yolo_layers = [layer[0] for layer in self.module_list if hasattr(layer[0], "metrics")]
        self.img_size = img_size
        self.seen = 0
        self.header_info = np.array([0, 0, 0, self.seen, 0], dtype=np.int32)

    def forward(self, x, targets=None):
        img_dim = x.shape[2]
        loss = 0
        layer_outputs, yolo_outputs = [], []
        for i, (module_def, module) in enumerate(zip(self.module_defs, self.module_list)):
            if module_def["type"] in ["convolutional", "upsample", "maxpool"]:
                x = module(x)
            elif module_def["type"] == "route":
                x = torch.cat([layer_outputs[int(layer_i)] for layer_i in module_def["layers"].split(",")], 1)
            elif module_def["type"] == "shortcut":
                layer_i = int(module_def["from"])
                x = layer_outputs[-1] + layer_outputs[layer_i]
            elif module_def["type"] == "yolo":
                x, layer_loss = module[0](x, targets, img_dim)
                loss += layer_loss
                yolo_outputs.append(x)
            layer_outputs.append(x)
        yolo_outputs = to_cpu(torch.cat(yolo_outputs, 1))
        return yolo_outputs if targets is None else (loss, yolo_outputs)

Hi @wanchaol,
Is there anything that I can do from my side to help you navigate through the code and realize my problem?

HI @baheytharwat, sorry I haven’t got time to debug the issue out as the model is a big large, I will continue do it next week. It would be nice if you could provide a minimal repro, that could help on debug and fix :slight_smile:

Hi everyone,
@baheytharwat Did you manage to solve this?
Does anyone have some ideas on how to debug it?
Thanks!