towhee
/
vit-image-embedding
copied
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions
42 lines
1.5 KiB
42 lines
1.5 KiB
# 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 torch
|
|
from torch.nn import Linear
|
|
from torch import nn
|
|
import timm
|
|
|
|
|
|
class Model():
|
|
"""
|
|
PyTorch model class
|
|
"""
|
|
def __init__(self, model_name: str, weights_path: str, num_classes=1000):
|
|
super().__init__()
|
|
if weights_path:
|
|
self._model = timm.create_model(model_name, checkpoint_path=weights_path, num_classes=num_classes)
|
|
else:
|
|
self._model = timm.create_model(model_name, pretrained=True, num_classes=num_classes)
|
|
self._model.eval()
|
|
|
|
def __call__(self, img_tensor: torch.Tensor):
|
|
self._model.eval()
|
|
features = self._model.forward_features(img_tensor)
|
|
if features.dim() == 4: # if the shape of feature map is [N, C, H, W], where H > 1 and W > 1
|
|
global_pool = nn.AdaptiveAvgPool2d(1)
|
|
features = global_pool(features)
|
|
return features.flatten().detach().numpy()
|
|
|
|
|