---
license: mit
---

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

  class BLIPNet(torch.nn.Module):
      def __init__(self, ):
          super().__init__()
          #Generation Model
          self.model = BlipForConditionalGeneration.from_pretrained(MODEL_NAME, cache_dir="model")
          #Same with https://huggingface.co/uf-aice-lab/BLIP-Math
          self.ebd_dim = 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.score = 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_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.score(image_embeds)
  
          #generated text, probabilities of classification
          return outputs, logits  
          
  model = BLIPNet()
  model.load_state_dict(torch.load(best_model_wts_path) ,strict=False)
  
You need to input the sample in the same way as: 
https://huggingface.co/uf-aice-lab/BLIP-Math
Then you can get the text and score at the same time.