Spaces:
Sleeping
Sleeping
File size: 2,570 Bytes
e84842d |
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 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
"""
Copyright (c) 2022, salesforce.com, inc.
All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
from lavis.common.registry import registry
from lavis.processors.blip_processors import BlipImageBaseProcessor
from omegaconf import OmegaConf
from torchvision import transforms
from torchvision.transforms.functional import InterpolationMode
def _convert_to_rgb(image):
return image.convert("RGB")
@registry.register_processor("clip_image_train")
class ClipImageTrainProcessor(BlipImageBaseProcessor):
def __init__(
self, image_size=224, mean=None, std=None, min_scale=0.9, max_scale=1.0
):
super().__init__(mean=mean, std=std)
self.transform = transforms.Compose(
[
transforms.RandomResizedCrop(
image_size,
scale=(min_scale, max_scale),
interpolation=InterpolationMode.BICUBIC,
),
_convert_to_rgb,
transforms.ToTensor(),
self.normalize,
]
)
@classmethod
def from_config(cls, cfg=None):
if cfg is None:
cfg = OmegaConf.create()
image_size = cfg.get("image_size", 224)
mean = cfg.get("mean", None)
std = cfg.get("std", None)
min_scale = cfg.get("min_scale", 0.9)
max_scale = cfg.get("max_scale", 1.0)
return cls(
image_size=image_size,
mean=mean,
std=std,
min_scale=min_scale,
max_scale=max_scale,
)
@registry.register_processor("clip_image_eval")
class ClipImageEvalProcessor(BlipImageBaseProcessor):
def __init__(self, image_size=224, mean=None, std=None):
super().__init__(mean=mean, std=std)
self.transform = transforms.Compose(
[
transforms.Resize(image_size, interpolation=InterpolationMode.BICUBIC),
transforms.CenterCrop(image_size),
_convert_to_rgb,
transforms.ToTensor(),
self.normalize,
]
)
@classmethod
def from_config(cls, cfg=None):
if cfg is None:
cfg = OmegaConf.create()
image_size = cfg.get("image_size", 224)
mean = cfg.get("mean", None)
std = cfg.get("std", None)
return cls(
image_size=image_size,
mean=mean,
std=std,
)
|