Create README.md

README.md

@@ -0,0 +1,87 @@
+---
+datasets:
+- cis519-Image2GPS/gps_images_dataset
+base_model:
+- cis519-Image2GPS/ImageToGPSproject_resnet18
+---
+- lat mean = 39.95169318421053
+- lat std = 0.0007139636196696079
+- lon mean = -75.19131129824562
+- lon std = 0.0006948352800088026
+
+---
+To load & evaluate our model:
+``` python
+!pip install geopy > delete.txt
+!pip install datasets > delete.txt
+!pip install torch torchvision datasets > delete.txt
+!pip install huggingface_hub > delete.txt
+!rm delete.txt
+!pip install transformers
+!pip install geopy
+
+import getpass
+from huggingface_hub import notebook_login
+# Securely input the Hugging Face token
+token = getpass.getpass("Enter your Hugging Face token: ")
+# Log in to Hugging Face Hub
+notebook_login(token)
+
+from huggingface_hub import hf_hub_download
+import torch
+from huggingface_hub import HfApi, HfFolder, Repository
+# Specify the repository and the filename of the model you want to load
+repo_id = "cis519-Image2GPS/ImageToGPSproject_resnet18_layer"  # 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
+
+from datasets import load_dataset, Image
+dataset_test = load_dataset("gydou/released_img", split="train")
+
+import torchvision.transforms as transforms
+import numpy as np
+from geopy.distance import geodesic
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+transform = transforms.Compose([
+    transforms.RandomResizedCrop(224),  # Random crop and resize to 224x224
+    transforms.RandomHorizontalFlip(),  # Random horizontal flip
+    # transforms.RandomRotation(degrees=15),  # Random rotation between -15 and 15 degrees
+    transforms.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.1),  # Random color jitter
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                         std=[0.229, 0.224, 0.225])
+])
+inference_transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                         std=[0.229, 0.224, 0.225])
+])
+with torch.no_grad():
+    for data in dataset_test:
+        image = inference_transform(data["image"]).unsqueeze(0).to(device)
+        outputs = model_test(image)
+        # print("Predicted latitude & longitude:", outputs.cpu().numpy())
+lat_mean = 39.95169318421053
+lat_std = 0.0007139636196696079
+lon_mean = -75.19131129824562
+lon_std = 0.0006948352800088026
+all_distances = []
+model_test.eval()
+with torch.no_grad():
+    for data in dataset_test:
+        image = transform(data["image"]).unsqueeze(0).to(device)
+        outputs = model_test(image).cpu().numpy()
+        preds_denorm = outputs * np.array([lat_std, lon_std]) + np.array([lat_mean, lon_mean])
+        actual = [data["Latitude"], data["Longitude"]]
+        distance = geodesic(actual, preds_denorm[0]).meters
+        all_distances.append(distance)
+mean_error = np.mean(all_distances)
+rmse_error = np.sqrt(np.mean(np.square(all_distances)))
+print('mean_error: ', mean_error)
+print('rmse_error: ', rmse_error)
+
+```