Is there any quick way to perform inference using the pretrained model on an input video or image file??

[XinyiYing]

For quick inference:

1. prepare test dataset download your datasets and prepare test data in code/data as below:

   data
   └── dataset_1
        └── scene_1
              └── hr    
                 ├── hr_01.png  
                 ├── hr_02.png  
                 ├── ...
                 └── hr_M.png    
              └── lr_x4
                 ├── lr_01.png  
                 ├── lr_02.png  
                 ├── ...
                 └── lr_M.png   
        ├── ...          
        └── scene_M
   ├── ...    
   └── dataset_N      

2. Compile deformable 3D convolution: Cd to code/dcn. For Windows users, run cmd make.bat. For Linux users, run bash make.sh. The scripts will build D3D automatically and create some folders. See code/dcn/test.py for example usage.

3. perform inference python --dataset [dataset_1] test.py

[rushi-the-neural-arch]

Thank you very much for the quick reply! :) However, I just wanted to know that if I have a low-resolution input video/image (basically I cannot create a test dataset with an LR- HR image pair as you explained), is there any way I can perform inference directly on the LR image and get an HR image as output?? I have already compiled deformable 3D convolution and also made a test run for training the network.

Thanks!

[XinyiYing]

Thank you for your comment. We have added inference.py and adjust the dataset.py in our code to offer a direct inference on D3Dnet.

[rushi-the-neural-arch]

Thank you very much for providing the inference file! I will check it out soon!