Upload README.md

README.md

@@ -0,0 +1,136 @@
+# LAJ CNN Image-to-GPS Model Iteration 1
+
+This project features a convolutional neural network (CNN) for predicting GPS coordinates (latitude and longitude) from image inputs. Below, you'll find details on loading the model, performing inference, and the architecture of the network.
+
+---
+
+## 1. Loading the Model
+
+To load the model, look at the sampleRun_v3.ipynb and run the same commands.
+
+## 2. Running the Model
+
+To perform inference on our model, just normalize the latitudes and longitudes to our means and standard deviations below.
+Then run code similar to the code provided to test code provided below:
+
+```
+# Evaluate on Test Set
+model.eval()
+all_preds, all_actuals = [], []
+with torch.no_grad():
+    for images, gps_coords in val_loader:
+        images, gps_coords = images.to(device), gps_coords.to(device)
+        outputs = model(images)
+        all_preds.append(outputs.cpu())
+        all_actuals.append(gps_coords.cpu())
+all_preds = torch.cat(all_preds).numpy()
+all_actuals = torch.cat(all_actuals).numpy()
+
+# Denormalize Predictions
+all_preds_denorm = all_preds * np.array([lat_std, lon_std]) + np.array([lat_mean, lon_mean])
+all_actuals_denorm = all_actuals * np.array([lat_std, lon_std]) + np.array([lat_mean, lon_mean])
+
+# Compute Error Metrics
+mae = mean_absolute_error(all_actuals_denorm, all_preds_denorm)
+rmse = mean_squared_error(all_actuals_denorm, all_preds_denorm, squared=False)
+print(f"Test Set Mean Absolute Error: {mae:}")
+print(f"Test Set Root Mean Squared Error: {rmse:}")
+```
+
+## 3. Latitude and Longitude Means and Standard Deviations
+
+The following values represent the **means** and **standard deviations** of the latitude and longitude used in this model:
+
+- **Latitude Mean**: `39.95173729922173`
+- **Latitude Standard Deviation**: `0.0006877829213952256`
+- **Longitude Mean**: `-75.19138804851796`
+- **Longitude Standard Deviation**: `0.0006182574854250925`
+  These values are used to normalize and denormalize the latitude and longitude predictions during inference.
+
+## 4. CNN Architecture
+
+Finally here is the architecture of the CNN we used:
+
+```
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torchvision.models import efficientnet_v2_s
+from torch.optim.lr_scheduler import CosineAnnealingLR
+from torchvision import transforms
+from torch.utils.data import DataLoader, Dataset
+from torchvision.transforms import functional as F
+from PIL import Image
+import numpy as np
+from sklearn.metrics import mean_absolute_error, mean_squared_error
+from huggingface_hub import PyTorchModelHubMixin
+import os
+
+# Model Definition
+class CustomGPSModel(nn.Module):
+    def __init__(self):
+        super(CustomGPSModel, self).__init__()
+
+        # Load EfficientNetV2-S with pretrained weights
+        self.efficientnet = efficientnet_v2_s(pretrained=True)
+
+        # Modify the final layer for regression (predicting latitude and longitude)
+        num_features = self.efficientnet.classifier[1].in_features
+        self.efficientnet.classifier[1] = nn.Linear(num_features, 2)  # Output layer has 2 outputs for latitude & longitude
+
+        # Don't freeze earlier layers
+        for param in self.efficientnet.features.parameters():
+            param.requires_grad = True
+
+    def forward(self, x):
+        return self.efficientnet(x)  # Forward pass through EfficientNet
+
+```
+
+## 5. Sample Run Code (how to install and run everything)
+
+```
+!pip install datasets
+!pip install huggingface_hub
+!pip install requests
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torchvision.models import efficientnet_b0
+from torch.optim.lr_scheduler import CosineAnnealingLR
+from torchvision import transforms
+from torch.utils.data import DataLoader, Dataset
+from torchvision.transforms import functional as F
+from PIL import Image
+import numpy as np
+from sklearn.metrics import mean_absolute_error, mean_squared_error
+from huggingface_hub import PyTorchModelHubMixin
+import os
+# Model Definition
+class CustomGPSModel(nn.Module):
+    def __init__(self):
+        super(CustomGPSModel, self).__init__()
+        # Load EfficientNet-B0 with pretrained weights
+        self.efficientnet = efficientnet_b0(pretrained=True)
+        # Modify the final layer for regression (predicting latitude and longitude)
+        num_features = self.efficientnet.classifier[1].in_features
+        self.efficientnet.classifier[1] = nn.Linear(num_features, 2)  # Output layer has 2 outputs for latitude & longitude
+        # Freeze earlier layers except the last few
+        for param in self.efficientnet.features.parameters():
+            param.requires_grad = True
+    def forward(self, x):
+        return self.efficientnet(x)  # Forward pass through EfficientNet
+
+from huggingface_hub import hf_hub_download
+import torch
+path_name = "efficientnet_gps_regressor_complete.pth"
+repo_name = "CustomGPSModel_EfficientNetB0_Run2"
+organization_name = "LAJ-519-Image-Project"
+# Specify the repository and the filename of the model you want to load
+repo_id = f"{organization_name}/{repo_name}"
+filename = f"{path_name}"
+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()
+```