Create README.md

README.md

@@ -0,0 +1,44 @@
+Dataset stats: \
+lat_mean = 39.951564548022596 \
+lat_std = 0.0006361722351128644 \
+lon_mean = -75.19150880602636 \
+lon_std = 0.000611411894337979 
+
+The model can be loaded using:
+```
+from huggingface_hub import hf_hub_download
+import torch
+
+# Specify the repository and the filename of the model you want to load
+repo_id = "FinalProj5190/ImageToGPSproject-vit-base"  # Replace with your repo name
+filename = "resnet_gps_regressor_complete.pth"
+
+model_path = hf_hub_download(repo_id=repo_id, filename=filename)
+
+# Load the model using torch
+model_test = torch.load(model_path)
+model_test.eval()  # Set the model to evaluation mode
+```
+
+The model implementation is here:
+```
+class MultiModalModel(nn.Module):
+    def __init__(self, num_classes=2):
+        super(MultiModalModel, self).__init__()
+        self.vit = ViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
+        
+        # Replace for regression instead of classification
+        self.regression_head = nn.Sequential(
+            nn.Linear(self.vit.config.hidden_size, 512),
+            nn.ReLU(),
+            nn.Linear(512, num_classes)
+        )
+    
+    def forward(self, x):
+        outputs = self.vit(pixel_values=x)
+        # Take the last hidden state (CLS token embedding)
+        cls_output = outputs.last_hidden_state[:, 0, :]
+        # Pass through the regression head
+        gps_coordinates = self.regression_head(cls_output)
+        return gps_coordinates
+```