File size: 9,559 Bytes
e3bb923 | 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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | # coding=utf-8
# Copyright 2025 The InternVideo 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.
"""Video processor class for InternVideo3."""
import math
from typing import Optional, Union
import numpy as np
import torch
from transformers.feature_extraction_utils import BatchFeature
from transformers.image_utils import ChannelDimension, PILImageResampling, SizeDict, get_image_size
from transformers.processing_utils import Unpack, VideosKwargs
from transformers.utils import TensorType, logging
from transformers.video_processing_utils import BaseVideoProcessor
from transformers.video_utils import VideoMetadata, group_videos_by_shape, reorder_videos
logger = logging.get_logger(__name__)
def smart_resize(
num_frames: int,
height: int,
width: int,
temporal_factor: int = 2,
factor: int = 32,
min_pixels: int = 128 * 128,
max_pixels: int = 16 * 16 * 2 * 2 * 2 * 6144,
):
if num_frames < temporal_factor:
raise ValueError(f"t:{num_frames} must be larger than temporal_factor:{temporal_factor}")
if height < factor or width < factor:
raise ValueError(f"height:{height} or width:{width} must be larger than factor:{factor}")
elif max(height, width) / min(height, width) > 200:
raise ValueError(
f"absolute aspect ratio must be smaller than 200, got {max(height, width) / min(height, width)}"
)
h_bar = round(height / factor) * factor
w_bar = round(width / factor) * factor
t_bar = round(num_frames / temporal_factor) * temporal_factor
if t_bar * h_bar * w_bar > max_pixels:
beta = math.sqrt((num_frames * height * width) / max_pixels)
h_bar = max(factor, math.floor(height / beta / factor) * factor)
w_bar = max(factor, math.floor(width / beta / factor) * factor)
elif t_bar * h_bar * w_bar < min_pixels:
beta = math.sqrt(min_pixels / (num_frames * height * width))
h_bar = math.ceil(height * beta / factor) * factor
w_bar = math.ceil(width * beta / factor) * factor
return h_bar, w_bar
class InternVideo3VideoProcessorInitKwargs(VideosKwargs):
patch_size: Optional[int]
temporal_patch_size: Optional[int]
merge_size: Optional[int]
min_frames: Optional[int]
max_frames: Optional[int]
class InternVideo3VideoProcessor(BaseVideoProcessor):
resample = PILImageResampling.BICUBIC
size = {"shortest_edge": 128 * 32 * 32, "longest_edge": 32 * 32 * 768}
image_mean = [0.5, 0.5, 0.5]
image_std = [0.5, 0.5, 0.5]
do_resize = True
do_rescale = True
do_normalize = True
do_convert_rgb = True
patch_size = 16
temporal_patch_size = 2
merge_size = 2
fps = 2
min_frames = 4
max_frames = 768
do_sample_frames = True
valid_kwargs = InternVideo3VideoProcessorInitKwargs
model_input_names = ["pixel_values_videos", "video_grid_thw"]
def __init__(self, **kwargs: Unpack[InternVideo3VideoProcessorInitKwargs]):
super().__init__(**kwargs)
if self.size is not None and (
self.size.get("shortest_edge", None) is None or self.size.get("longest_edge", None) is None
):
raise ValueError("size must contain 'shortest_edge' and 'longest_edge' keys.")
def _further_process_kwargs(
self,
size: Optional[SizeDict] = None,
**kwargs,
) -> dict:
if size is not None and ("shortest_edge" not in size or "longest_edge" not in size):
raise ValueError("size must contain 'shortest_edge' and 'longest_edge' keys.")
return super()._further_process_kwargs(size=size, **kwargs)
def sample_frames(
self,
metadata: VideoMetadata,
num_frames: Optional[int] = None,
fps: Optional[Union[int, float]] = None,
**kwargs,
):
if fps is not None and num_frames is not None:
raise ValueError("`num_frames` and `fps` are mutually exclusive arguments, please use only one!")
total_num_frames = metadata.total_num_frames
fps = fps if fps is not None else self.fps
if num_frames is None and fps is not None:
if metadata.fps is None:
metadata.fps = 24
logger.warning_once(
"Asked to sample `fps` frames per second but no video metadata was provided. "
"Defaulting to `fps=24`. Please provide `video_metadata` for more accurate results."
)
num_frames = int(total_num_frames / metadata.fps * fps)
num_frames = min(min(max(num_frames, self.min_frames), self.max_frames), total_num_frames)
if num_frames is None:
num_frames = min(max(total_num_frames, self.min_frames), self.max_frames)
indices = np.linspace(0, total_num_frames - 1, num_frames).round().astype(int)
return indices
def _preprocess(
self,
videos: list[torch.Tensor],
do_convert_rgb: bool = True,
do_resize: bool = True,
size: Optional[SizeDict] = None,
interpolation: PILImageResampling = PILImageResampling.BICUBIC,
do_rescale: bool = True,
rescale_factor: float = 1 / 255.0,
do_normalize: bool = True,
image_mean: Optional[Union[float, list[float]]] = None,
image_std: Optional[Union[float, list[float]]] = None,
patch_size: Optional[int] = None,
temporal_patch_size: Optional[int] = None,
merge_size: Optional[int] = None,
return_tensors: Optional[Union[str, TensorType]] = None,
**kwargs,
):
grouped_videos, grouped_videos_index = group_videos_by_shape(videos)
resized_videos_grouped = {}
for shape, stacked_videos in grouped_videos.items():
B, T, C, H, W = stacked_videos.shape
num_frames, height, width = T, H, W
if do_resize:
resized_height, resized_width = smart_resize(
num_frames=num_frames,
height=height,
width=width,
temporal_factor=temporal_patch_size,
factor=patch_size * merge_size,
min_pixels=size.shortest_edge,
max_pixels=size.longest_edge,
)
stacked_videos = stacked_videos.view(B * T, C, H, W)
stacked_videos = self.resize(
stacked_videos,
size=SizeDict(height=resized_height, width=resized_width),
interpolation=interpolation,
)
stacked_videos = stacked_videos.view(B, T, C, resized_height, resized_width)
resized_videos_grouped[shape] = stacked_videos
resized_videos = reorder_videos(resized_videos_grouped, grouped_videos_index)
grouped_videos, grouped_videos_index = group_videos_by_shape(resized_videos)
processed_videos_grouped = {}
processed_grids = {}
for shape, stacked_videos in grouped_videos.items():
resized_height, resized_width = get_image_size(stacked_videos[0], channel_dim=ChannelDimension.FIRST)
stacked_videos = self.rescale_and_normalize(
stacked_videos, do_rescale, rescale_factor, do_normalize, image_mean, image_std
)
patches = stacked_videos
if patches.shape[1] % temporal_patch_size != 0:
repeats = patches[:, -1:].repeat(1, temporal_patch_size - 1, 1, 1, 1)
patches = torch.cat([patches, repeats], dim=1)
batch_size, grid_t, channel = patches.shape[:3]
grid_t = grid_t // temporal_patch_size
grid_h, grid_w = resized_height // patch_size, resized_width // patch_size
patches = patches.view(
batch_size,
grid_t,
temporal_patch_size,
channel,
grid_h // merge_size,
merge_size,
patch_size,
grid_w // merge_size,
merge_size,
patch_size,
)
patches = patches.permute(0, 1, 4, 7, 5, 8, 3, 2, 6, 9)
flatten_patches = patches.reshape(
batch_size,
grid_t * grid_h * grid_w,
channel * temporal_patch_size * patch_size * patch_size,
)
processed_videos_grouped[shape] = flatten_patches
processed_grids[shape] = [[grid_t, grid_h, grid_w]] * batch_size
processed_videos = reorder_videos(processed_videos_grouped, grouped_videos_index)
processed_grids = reorder_videos(processed_grids, grouped_videos_index)
pixel_values_videos = torch.cat(processed_videos, dim=0)
video_grid_thw = torch.tensor(processed_grids)
data = {
"pixel_values_videos": pixel_values_videos,
"video_grid_thw": video_grid_thw,
}
return BatchFeature(data=data, tensor_type=return_tensors)
__all__ = ["InternVideo3VideoProcessor"]
|