how to train a pretrained complete multimodal model

[wupeng1989]

May I know how to train a pretrained complete multimodal model? Does setting arg.mr=0 in the code means set to train complete multimodal model. But when I set arg.mr=0, miss_2[-1]=1.0， the code goes to lose two multimodal @mdswyz

miss_2 = [0.1, 0.2, 0.3, 0.5, 0.7, 0.9, 1.0] miss_1 = [0.1, 0.2, 0.3, 0.2, 0.1, 0.0, 0.0] if miss_two / (np.round(len(dataloader) / 10) * 10) < miss_2[int(self.args.mr * 10 - 1)]: # missing two modal outputs = model(text, audio, vision, num_modal=1) miss_two += 1 elif miss_one / (np.round(len(dataloader) / 10) * 10) < miss_1[int(self.args.mr * 10 - 1)]: # missing one modal outputs = model(text, audio, vision, num_modal=2) miss_one += 1 else: # no missing outputs = model(text, audio, vision, num_modal=3)