code/model/blip2.py

"""
Adapted from salesforce@LAVIS. Below is the original copyright:
 Copyright (c) 2023, salesforce.com, inc.
 All rights reserved.
 SPDX-License-Identifier: BSD-3-Clause
 For full license text, see the LICENSE_Lavis file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
import contextlib
import logging
import os
import time
import datetime

import torch
import torch.nn as nn
import torch.distributed as dist
import torch.nn.functional as F

from .common import dist_utils
# from video_llama.common.dist_utils import download_cached_file
# from .common.utils import is_url
from .common.logger import MetricLogger
# from video_llama.models.base_model import BaseModel
# from video_llama.models.Qformer import BertConfig, BertLMHeadModel
# from video_llama.models.eva_vit import create_eva_vit_g
# from transformers import BertTokenizer


def disabled_train(self, mode=True):
    """Overwrite model.train with this function to make sure train/eval mode
    does not change anymore."""
    return self


class LayerNorm(nn.LayerNorm):
    """Subclass torch's LayerNorm to handle fp16."""

    def forward(self, x: torch.Tensor):
        orig_type = x.dtype
        ret = super().forward(x.type(torch.float32))
        return ret.type(orig_type)


def compute_sim_matrix(model, data_loader, **kwargs):
    k_test = kwargs.pop("k_test")

    metric_logger = MetricLogger(delimiter="  ")
    header = "Evaluation:"

    logging.info("Computing features for evaluation...")
    start_time = time.time()

    texts = data_loader.dataset.text
    num_text = len(texts)
    text_bs = 256
    text_ids = []
    text_embeds = []
    text_atts = []
    for i in range(0, num_text, text_bs):
        text = texts[i : min(num_text, i + text_bs)]
        text_input = model.tokenizer(
            text,
            padding="max_length",
            truncation=True,
            max_length=35,
            return_tensors="pt",
        ).to(model.device)
        text_feat = model.forward_text(text_input)
        text_embed = F.normalize(model.text_proj(text_feat))
        text_embeds.append(text_embed)
        text_ids.append(text_input.input_ids)
        text_atts.append(text_input.attention_mask)

    text_embeds = torch.cat(text_embeds, dim=0)
    text_ids = torch.cat(text_ids, dim=0)
    text_atts = torch.cat(text_atts, dim=0)

    vit_feats = []
    image_embeds = []
    for samples in data_loader:
        image = samples["image"]

        image = image.to(model.device)
        image_feat, vit_feat = model.forward_image(image)
        image_embed = model.vision_proj(image_feat)
        image_embed = F.normalize(image_embed, dim=-1)

        vit_feats.append(vit_feat.cpu())
        image_embeds.append(image_embed)

    vit_feats = torch.cat(vit_feats, dim=0)
    image_embeds = torch.cat(image_embeds, dim=0)

    sims_matrix = []
    for image_embed in image_embeds:
        sim_q2t = image_embed @ text_embeds.t()
        sim_i2t, _ = sim_q2t.max(0)
        sims_matrix.append(sim_i2t)
    sims_matrix = torch.stack(sims_matrix, dim=0)

    score_matrix_i2t = torch.full(
        (len(data_loader.dataset.image), len(texts)), -100.0
    ).to(model.device)

    num_tasks = dist_utils.get_world_size()
    rank = dist_utils.get_rank()
    step = sims_matrix.size(0) // num_tasks + 1
    start = rank * step
    end = min(sims_matrix.size(0), start + step)

    for i, sims in enumerate(
        metric_logger.log_every(sims_matrix[start:end], 50, header)
    ):
        topk_sim, topk_idx = sims.topk(k=k_test, dim=0)
        image_inputs = vit_feats[start + i].repeat(k_test, 1, 1).to(model.device)
        score = model.compute_itm(
            image_inputs=image_inputs,
            text_ids=text_ids[topk_idx],
            text_atts=text_atts[topk_idx],
        ).float()
        score_matrix_i2t[start + i, topk_idx] = score + topk_sim

    sims_matrix = sims_matrix.t()
    score_matrix_t2i = torch.full(
        (len(texts), len(data_loader.dataset.image)), -100.0
    ).to(model.device)

    step = sims_matrix.size(0) // num_tasks + 1
    start = rank * step
    end = min(sims_matrix.size(0), start + step)

    for i, sims in enumerate(
        metric_logger.log_every(sims_matrix[start:end], 50, header)
    ):
        topk_sim, topk_idx = sims.topk(k=k_test, dim=0)
        image_inputs = vit_feats[topk_idx.cpu()].to(model.device)
        score = model.compute_itm(
            image_inputs=image_inputs,
            text_ids=text_ids[start + i].repeat(k_test, 1),
            text_atts=text_atts[start + i].repeat(k_test, 1),
        ).float()
        score_matrix_t2i[start + i, topk_idx] = score + topk_sim

    if dist_utils.is_dist_avail_and_initialized():
        dist.barrier()
        torch.distributed.all_reduce(
            score_matrix_i2t, op=torch.distributed.ReduceOp.SUM
        )
        torch.distributed.all_reduce(
            score_matrix_t2i, op=torch.distributed.ReduceOp.SUM
        )

    total_time = time.time() - start_time
    total_time_str = str(datetime.timedelta(seconds=int(total_time)))
    logging.info("Evaluation time {}".format(total_time_str))

    return score_matrix_i2t.cpu().numpy(), score_matrix_t2i.cpu().numpy()