When Inference,How do I set parameter of target with EfficientDet-Pytorch?

Question

Im studying objective detection code with efficientdet-pytorch at the first time.

I used pretrained Weight model as reference:

https://www.kaggle.com/shonenkov/inference-efficientdet

https://github.com/toandaominh1997/EfficientDet.Pytorch

I tried to check efficientdet model's output...


from effdet import get_efficientdet_config, EfficientDet, DetBenchTrain
from effdet.efficientdet import HeadNet

#load sample efficientdet code

config = get_efficientdet_config('tf_efficientdet_d0')
config.image_size = [512,512]
config.norm_kwargs=dict(eps=.001, momentum=.01)

net = EfficientDet(config, pretrained_backbone=False)
checkpoint = torch.load('efficientdet_d0-d92fd44f.pth')

net.load_state_dict(checkpoint)
#net.reset_head(num_classes=1)
#net.class_net = HeadNet(config, num_outputs=config.num_classes)

net=DetBenchTrain(net, config)
print("Loaded pretrained weights")
#>>>Loaded pretrained weights"

#img.shape:[3,512,512]

net.eval()
with torch.no_grad():
    detected=net(img.unsqueeze(0))

#error　of target is below.
TypeError: forward() missing 1 required positional argument: 'target'

And refering to https://www.kaggle.com/shonenkov/inference-efficientdet I tried below code.


def make_predictions(images, score_threshold=0.22):
    predictions = []
    with torch.no_grad():
        det = net(images, torch.tensor([1]*images.shape[0]).float())
        print(det.shape)
        for i in range(images.shape[0]):
            boxes = det[i].detach().cpu().numpy()[:,:4]    
            scores = det[i].detach().cpu().numpy()[:,4]
            indexes = np.where(scores > score_threshold)[0]
            boxes = boxes[indexes]
            boxes[:, 2] = boxes[:, 2] + boxes[:, 0]
            boxes[:, 3] = boxes[:, 3] + boxes[:, 1]
            predictions.append({
                'boxes': boxes[indexes],
                'scores': scores[indexes],
            })
    return [predictions]

output=make_predictions(img.unsqueeze(0))

#error is below...
---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
 in 
----> 1 output=make_predictions(img.unsqueeze(0))

 in make_predictions(images, score_threshold)
      3     predictions = []
      4     with torch.no_grad():
----> 5         det = net(images, torch.tensor([1]*images.shape[0]).float())
      6         print(det.shape)
      7         for i in range(images.shape[0]):

/opt/anaconda3/envs/yohenv/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    720             result = self._slow_forward(*input, **kwargs)
    721         else:
--> 722             result = self.forward(*input, **kwargs)
    723         for hook in itertools.chain(
    724                 _global_forward_hooks.values(),

/opt/anaconda3/envs/yohenv/lib/python3.7/site-packages/effdet/bench.py in forward(self, x, target)
    117         else:
    118             cls_targets, box_targets, num_positives = self.anchor_labeler.batch_label_anchors(
--> 119                 target['bbox'], target['cls'])
    120 
    121         loss, class_loss, box_loss = self.loss_fn(class_out, box_out, cls_targets, box_targets, num_positives)

IndexError: too many indices for tensor of dimension 1

When inference with TestData ,How do I set parameter of target?

Sorry for the inconvenience,Can you give me advice?

When Inference,How do I set parameter of target with EfficientDet-Pytorch?

0 Answers