Inference using load_state_dict

[Karthik-U-94]

I have created Model using torch.save(retinanet.state_dict(), 'model_final.pt') Now I have changed

from retinanet import model

    ##########################

    retinanetModel = model.resnet101(num_classes=3,)
    retinanetModel.load_state_dict(torch.load(model_path), strict=False)

    if torch.cuda.is_available():
        retinanetModel = retinanetModel.cuda()

    retinanetModel.training = False
    retinanetModel.eval()

    ##########################
    
    scores, classification, transformed_anchors = retinanetModel(image.cuda().float())

No objects are Detecting. Please help me out

[ajithvcoder]

@Karthik-U-94 you can use this https://github.com/yhenon/pytorch-retinanet/issues/200#issuecomment-748992020