def test_full_tokenizer(self):
        tokenizer = CLIPTokenizer(self.vocab_file, self.merges_file, **self.special_tokens_map)
        text = "lower newer"
        bpe_tokens = ["lo", "w", "er</w>", "n", "e", "w", "er</w>"]
        tokens = tokenizer.tokenize(text)
        self.assertListEqual(tokens, bpe_tokens)

        input_tokens = tokens + [tokenizer.unk_token]
        input_bpe_tokens = [10, 2, 16, 9, 3, 2, 16, 20]
        self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
Exemplo n.º 2
0
def convert_owlvit_checkpoint(pt_backbone, flax_params, attn_params, pytorch_dump_folder_path, config_path=None):
    """
    Copy/paste/tweak model's weights to transformers design.
    """
    repo = Repository(pytorch_dump_folder_path, clone_from=f"google/{pytorch_dump_folder_path}")
    repo.git_pull()

    if config_path is not None:
        config = OwlViTConfig.from_pretrained(config_path)
    else:
        config = OwlViTConfig()

    hf_backbone = OwlViTModel(config).eval()
    hf_model = OwlViTForObjectDetection(config).eval()

    copy_text_model_and_projection(hf_backbone, pt_backbone)
    copy_vision_model_and_projection(hf_backbone, pt_backbone)
    hf_backbone.logit_scale = pt_backbone.logit_scale
    copy_flax_attn_params(hf_backbone, attn_params)

    hf_model.owlvit = hf_backbone
    copy_class_merge_token(hf_model, flax_params)
    copy_class_box_heads(hf_model, flax_params)

    # Save HF model
    hf_model.save_pretrained(repo.local_dir)

    # Initialize feature extractor
    feature_extractor = OwlViTFeatureExtractor(
        size=config.vision_config.image_size, crop_size=config.vision_config.image_size
    )
    # Initialize tokenizer
    tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32", pad_token="!", model_max_length=16)

    # Initialize processor
    processor = OwlViTProcessor(feature_extractor=feature_extractor, tokenizer=tokenizer)
    feature_extractor.save_pretrained(repo.local_dir)
    processor.save_pretrained(repo.local_dir)

    repo.git_add()
    repo.git_commit("Upload model and processor")
    repo.git_push()
Exemplo n.º 3
0
 def get_tokenizer(self, **kwargs):
     kwargs.update(self.special_tokens_map)
     return CLIPTokenizer.from_pretrained(self.tmpdirname, **kwargs)
Exemplo n.º 4
0
 def get_tokenizer(self, **kwargs):
     return CLIPTokenizer.from_pretrained(self.tmpdirname, **kwargs)