from open_clip import tokenize meta_path = osp.join(path_to_meta_data, "split", "lvis.json") with open(meta_path, "r") as file: meta = json.load(file) cats = sorted(np.unique([data['category'] for data in meta])) # load your extracted embeddings cat_embs_openshape_big_g_14 = np.load(osp.join(path_to_meta_data, "lvis_cat_name_pt_feat.npy"), allow_pickle=True) clip, _, _ = open_clip.create_model_and_transforms(model_name="ViT-bigG-14", pretrained='laion2b_s39b_b160k') clip.to("cuda").eval() with torch.no_grad(): gen_cat_embs = [] for name in tqdm.tqdm(cats): texts = [template.format(name) for template in _TEMPLATES] texts = tokenize(texts).to(device=device, non_blocking=True) if len(texts.shape) < 2: texts = texts[None, ...] class_emb = clip.encode_text(texts) class_emb = class_emb / class_emb.norm(dim=-1, keepdim=True) class_emb = class_emb.mean(dim=0) gen_cat_embs.append(class_emb) gen_cat_embs = torch.stack(gen_cat_embs, dim=0).cpu().numpy() # C x D assert np.allclose(gen_cat_embs, cat_embs_openshape_big_g_14)