关于InternVL2的单卡、多卡推理

前言

本章节将介绍如何使用上一章节微调后的模型进行推理。推理又分为单卡和多卡，这里介绍的两种方式都是Hugging Face的transformers方法进行推理。模型的话可以使用上一章微调的任意一个非lora模型进行测试。

单卡推理

如果你可以完成前面模型的微调，那单卡推理的显存应该是足够的。这里使用的模式是上一章lora合并后最终模型internvl2_4b_phi3_3_8b_dynamic_res_2nd_finetune_mlpvit_llmlora，具体代码如下：

import time
import math
import os
import re
import cv2
import torch
import numpy as np
import torchvision.transforms as T
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer# 这里使用单卡，指定设备号；不指定默认使用0号卡；多GPU情况下不能指定
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)def build_transform(input_size):MEAN, STD = IMAGENET_MEAN, IMAGENET_STDtransform = T.Compose([T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),T.ToTensor(),T.Normalize(mean=MEAN, std=STD)])return transformdef find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):best_ratio_diff = float('inf')best_ratio = (1, 1)area = width * heightfor ratio in target_ratios:target_aspect_ratio = ratio[0] / ratio[1]ratio_diff = abs(aspect_ratio - target_aspect_ratio)if ratio_diff < best_ratio_diff:best_ratio_diff = ratio_diffbest_ratio = ratioelif ratio_diff == best_ratio_diff:if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:best_ratio = ratioreturn best_ratiodef dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):orig_width, orig_height = image.sizeaspect_ratio = orig_width / orig_heighttarget_ratios = set((i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) ifi * j <= max_num and i * j >= min_num)target_ratios = sorted(target_ratios, key=lambda x: x[0]