def build_model()

in trainers/catex.py [0:0]

• 20 lines of code
• 7 McCabe index (conditional complexity)

    def build_model(self):
        cfg = self.cfg
        classnames = self.dm.dataset.classnames

        print(f"Loading CLIP (backbone: {cfg.MODEL.BACKBONE.NAME})")
        clip_model = load_clip_to_cpu(cfg)
        
        if cfg.TRAINER.CATEX.PREC == "fp32" or cfg.TRAINER.CATEX.PREC == "amp":
            # CLIP's default precision is fp16
            clip_model.float()

        print("Building custom CLIP")
        self.model = CustomCLIP(cfg, classnames, clip_model)

        print("Turning off gradients in both the image and the text encoder")
        for name, param in self.model.named_parameters():
            if "prompt_learner" not in name:
                param.requires_grad_(False)

        if cfg.MODEL.INIT_WEIGHTS:
            load_pretrained_weights(self.model.prompt_learner, cfg.MODEL.INIT_WEIGHTS)

        self.model.to(self.device)
        # NOTE: only give prompt_learner/image_encoder to the optimizer
        self.optim = build_optimizer(self.model.prompt_learner, cfg.OPTIM)
        self.sched = build_lr_scheduler(self.optim, cfg.OPTIM)
        self.register_model("prompt_learner", self.model.prompt_learner, self.optim, self.sched)

        self.scaler = GradScaler() if cfg.TRAINER.CATEX.PREC == "amp" else None