File size: 1,549 Bytes
df4a4de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
# Copyright 2024 Black Forest Labs and The HuggingFace Team. 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 dataclasses import dataclass
from typing import Optional
import torch
import torch.nn as nn
from ...configuration_utils import ConfigMixin, register_to_config
from ...models.modeling_utils import ModelMixin
from ...utils import BaseOutput
@dataclass
class ReduxImageEncoderOutput(BaseOutput):
image_embeds: Optional[torch.Tensor] = None
class ReduxImageEncoder(ModelMixin, ConfigMixin):
@register_to_config
def __init__(
self,
redux_dim: int = 1152,
txt_in_features: int = 4096,
) -> None:
super().__init__()
self.redux_up = nn.Linear(redux_dim, txt_in_features * 3)
self.redux_down = nn.Linear(txt_in_features * 3, txt_in_features)
def forward(self, x: torch.Tensor) -> ReduxImageEncoderOutput:
projected_x = self.redux_down(nn.functional.silu(self.redux_up(x)))
return ReduxImageEncoderOutput(image_embeds=projected_x)
|