vitansoz

Results 4 issues of vitansoz

## 🐛 Bug ## To Reproduce Steps to reproduce the behavior: 1. model = torchvision.models.detection.maskrcnn_resnet50_fpn(num_classes=24,pretrained=False).to(device) model.load_state_dict(checkpoint['model']) model.eval() 2. script_model = torch.jit.script(model) opt_model = optimize_for_mobile(script_model) opt_model._save_for_lite_interpreter("mask_rcnn_1.pt") 3. RuntimeError: __torch__ types other...

module: models
torchscript

use this demo code,can't display default layout picture,how to solve this problem? ![3F2AA873-2838-4AA7-9884-B5BC65EA3492](https://user-images.githubusercontent.com/45025677/128482761-41579d5c-d5d4-4292-a475-0469ae88836a.jpeg)

It's a long time no update,have a plan to continue update?

Can you provide download image or video from storage?like DJIMediaManager in MobileSDK。 gz#24242