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)
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()
def get_tokenizer(self, **kwargs):
kwargs.update(self.special_tokens_map)
return CLIPTokenizer.from_pretrained(self.tmpdirname, **kwargs)
def get_tokenizer(self, **kwargs):
return CLIPTokenizer.from_pretrained(self.tmpdirname, **kwargs)