BLIPNet Model

This is the structure of the BLIPNet model. You can load the model with this structure, or you can create a bigger model for your specific task.
Model Structure

import torch
import torch.nn as nn
from transformers import BlipForConditionalGeneration

class BLIPNet(torch.nn.Module):
    def __init__(self):
        super().__init__()
        # Generation Model
        self.model = BlipForConditionalGeneration.from_pretrained("Salesforceblip-image-captioning-base", cache_dir="model")
        # Same with https://huggingface.co/uf-aice-lab/BLIP-Math
        self.ebd_dim = 443136
        
        # Classification Model
        fc_dim = 64  # You can choose a higher number for better performance, for example, 1024.
        self.head = nn.Sequential(
            nn.Linear(self.ebd_dim, fc_dim),
            nn.ReLU(), 
        )
        self.output1= nn.Linear(fc_dim, 5)  # 5 classes
        
    def forward(self, pixel_values, input_ids):
        outputs = self.model(input_ids=input_ids, pixel_values=pixel_values, labels=input_ids)
        image_text_embeds = self.model.vision_model(pixel_values, return_dict=True).last_hidden_state
        image_text_embeds = self.head(image_text_embeds.view(-1, self.ebd_dim))

        # A classification model is based on embeddings from a generative model to leverage BLIP's powerful image-text encoding capabilities.
        logits = self.output1(image_text_embeds)

        # generated text, probabilities of classification
        return outputs, logits  
        
model = BLIPNet()
model.load_state_dict(torch.load("BLILP_Generation_Classification.bin"), strict=False)

You need to input the sample in the same way as shown in the example provided at: https://huggingface.co/uf-aice-lab/BLIP-Math
Then you can get the generated text and classification score simultaneously.