collaborative-experts/collaborative_experts.py

# 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.


from typing import Dict

from pathlib import Path
from towhee.operator.base import NNOperator
from towhee import register
from towhee.models import collaborative_experts

import warnings

warnings.filterwarnings('ignore')


@register(output_schema=['vec'])
class CollaborativeExperts(NNOperator):
    """
    CollaborativeExperts embedding operator
    """

    def __init__(self, config: Dict = None, weights_path: str = None, device: str = None):
        super().__init__()
        if weights_path is None:
            weights_path = str(Path(__file__).parent / 'model_state_dict.pth')
        self.ce_net_model = collaborative_experts.create_model(config, weights_path, device)

    def __call__(self, experts, ind, text):
        out = self.ce_net_model(experts, ind, text)
        text_embds = {k: v.squeeze(1).detach().cpu().numpy() for k, v in out['text_embds'].items()}
        vid_embds = {k: v.detach().cpu().numpy() for k, v in out['vid_embds'].items()}
        return text_embds, vid_embds

    def get_text_embds(self, experts, ind, text):
        out = self.ce_net_model(experts, ind, text)
        text_embds = {k: v.squeeze(1).detach().cpu().numpy() for k, v in out['text_embds'].items()}
        return text_embds

    def get_vid_embds(self, experts, ind, text):
        out = self.ce_net_model(experts, ind, text)
        vid_embds = {k: v.detach().cpu().numpy() for k, v in out['vid_embds'].items()}
        return vid_embds

    def get_cross_view_conf_matrix(self, experts, ind, text):
        out = self.ce_net_model(experts, ind, text)
        return out['cross_view_conf_matrix'].detach().cpu().numpy()