# Copyright 2021 Zilliz. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


import sys
from typing import NamedTuple
from pathlib import Path
from PIL import Image
import torch
from timm.data import resolve_data_config
from timm.data.transforms_factory import create_transform


from towhee.operator import Operator


class VisionTransformerEmbeddingOperator(Operator):
    """
    Embedding extractor using ViT.
    Args:
        model_name (`string`):
            Model name.
        weights_path (`string`):
            Path to local weights.
    """

    def __init__(self, model_name: str = 'vit_large_patch16_224',
                 framework: str = 'pytorch', weights_path: str = None) -> None:
        super().__init__()
        sys.path.append(str(Path(__file__).parent))
        if framework == 'pytorch':
            from vit_embedding.pytorch.model import Model
        self.model = Model(model_name, weights_path)
        config = resolve_data_config({}, model=self.model._model)
        self.tfms = create_transform(**config)

    def __call__(self, img_path: str) -> NamedTuple('Outputs', [('embedding', torch.Tensor)]):
        Outputs = NamedTuple('Outputs', [('embedding', torch.Tensor)])
        img = self.tfms(Image.open(img_path)).unsqueeze(0)
        features = self.model(img)
        return Outputs(features.flatten().detach().numpy())