calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]

Checks the validity of commandline arguments. Parameters ---------- None Returns ------- error : string

Check resume states and pretrain_model paths

dict to string for logger

Converts the `video` to images. Parameters ---------- video : string full path to the video file. outDir : st

Warp an image or feature map with optical flow Args: x (Tensor): size (N, C, H, W) flow (Tensor): size (N, H, W, 2), normal value

Parameters ---------- input_tensor: todo 5-D Tensor either of shape (t, b, c, h, w) or (b, t, c, h, w)

xforward, xreverse = B T C H W tensors.

align other neighboring frames to the reference frame in the feature level fea1, fea2: [L1, L2, L3], each with [B,C,H,W] features esti

Parameters ---------- input_tensor: 5-D Tensor either of shape (t, b, c, h, w) or (b, t, c, h, w)

input: input features for deformable conv fea: other features used for generating offsets and mask

get image path list support lmdb or image files

read image by cv2 or from lmdb return: Numpy float32, HWC, BGR, [0,1]

read a sequence of images

worker for reading images

same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

set up logger

Converts a torch Tensor into an image Numpy array Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order Output: 3D(

params: skip: if skip even number; N_out: number of frames of the network; len_in: length of input frames example: len_in |

same as matlab ycbcr2rgb Input: uint8, [0, 255] float, [0, 1]