ESRGAN video scaling script

import sys
import os.path
import glob
import cv2
import numpy as np
import torch
import architecture as arch

model_path = sys.argv[1]  # models/RRDB_ESRGAN_x4.pth OR models/RRDB_PSNR_x4.pth
device = torch.device('cuda')  # if you want to run on CPU, change 'cuda' -> cpu
# device = torch.device('cpu')

test_img_folder = 'LR_V/*'

model = arch.RRDB_Net(3, 3, 64, 23, gc=32, upscale=4, norm_type=None, act_type='leakyrelu', \
                            mode='CNA', res_scale=1, upsample_mode='upconv')
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for k, v in model.named_parameters():
    v.requires_grad = False
model = model.to(device)

print('Model path {:s}. \nTesting...'.format(model_path))

idx = 0
for path in glob.glob(test_img_folder):
    idx += 1
    base = os.path.splitext(os.path.basename(path))[0]
    print(idx, base)
    cap = cv2.VideoCapture(path)
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) * 4
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) * 4
    fps = int(cap.get(cv2.CAP_PROP_FPS))
    out = cv2.VideoWriter('results/{:s}.avi'.format(base), cv2.VideoWriter_fourcc('M','J','P','G'), fps, (width,height))
    while True:
        ret, img = cap.read();
        if img is None:
            break
        img = img * 1.0 / 255
        img = torch.from_numpy(np.transpose(img[:, :, [2, 1, 0]], (2, 0, 1))).float()
        img_LR = img.unsqueeze(0)
        img_LR = img_LR.to(device)

        output = model(img_LR).data.squeeze().float().cpu().clamp_(0, 1).numpy()
        output = np.transpose(output[[2, 1, 0], :, :], (1, 2, 0))
        output = (output * 255.0).round()
        output = np.uint8(output)
        out.write(output)
    cap.release()
    out.release()