Update README.md

README.md

@@ -27,7 +27,7 @@ class BLIPNet(torch.nn.Module):
             nn.Linear(self.ebd_dim, fc_dim),
             nn.ReLU(), 
         )
-        self.score = nn.Linear(fc_dim, 5)  # 5 classes
+        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)
@@ -35,13 +35,13 @@ class BLIPNet(torch.nn.Module):
         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.score(image_text_embeds)
+        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)
-
+```python
 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.