File size: 2,103 Bytes
1126ea7 |
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 |
"""Qwen2.5VL encoder with delayed normalization"""
import torch
from einops import rearrange
from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import (
Qwen2_5_VisionTransformerPretrainedModel,
)
def prepare_for_qwen_encoder(
x: torch.Tensor | list[torch.Tensor], mean: torch.Tensor, std: torch.Tensor
) -> tuple[torch.Tensor, torch.Tensor]:
"""
Preprocessing for Qwen encoder
Image mean and std come from processor.image_processor.image_mean and image_std
"""
grid_thw = torch.Tensor([[1, img.shape[0], img.shape[1]] for img in x]).to(x[0].device)
hws_flatten_shape = torch.prod(grid_thw, dim=-1)
x = torch.cat(
[img.reshape((int(hws_flatten_shape[idx].item()), -1)) for idx, img in enumerate(x)],
dim=0,
)
assert x.min() >= 0.0 and x.max() <= 1.0
og_shape = x.shape
x = rearrange(x, "L (c d) -> L c d", c=3)
x = (x - mean) / std
x = x.view(og_shape).to(torch.bfloat16)
return x, grid_thw
class Qwen25VLEncoder(torch.nn.Module):
"""Qwen2.5 VL encoder with pre/post processing to be compatible for
our CASA attention implementation"""
def __init__(
self,
visual: "Qwen2_5_VisionTransformerPretrainedModel",
):
super().__init__()
self.visual = visual
self.image_mean = torch.tensor(self.visual.config.image_mean).view(1, 3, 1)
self.image_std = torch.tensor(self.visual.config.image_std).view(1, 3, 1)
def forward(
self, x: torch.Tensor | list[torch.Tensor]
) -> dict[str, torch.Tensor | list[torch.Tensor]]:
x, grid_thw = prepare_for_qwen_encoder(
x, mean=self.image_mean.to(x[0].device), std=self.image_std.to(x[0].device)
)
grid_thw = grid_thw.type(torch.int)
assert len(x) == grid_thw.prod(dim=1).sum()
out = self.visual(x, grid_thw=grid_thw)
split_sizes = (grid_thw.prod(dim=-1) // self.visual.spatial_merge_size**2).tolist()
embeds = list(torch.split(out, split_sizes, dim=0)) # Ni * (seq, C)
return {"image_embeds": embeds, "grid_thw": grid_thw}
|