Preparing submission

tasks/image.py

@@ -12,6 +12,13 @@ from .utils.emissions import tracker, clean_emissions_data, get_space_info
 from dotenv import load_dotenv
 load_dotenv()
 
+# Dependencies for inference
+import logging
+from pathlib import Path
+from ultralytics import YOLO
+from torch import device
+from torch.cuda import is_available
+
 router = APIRouter()
 
 DESCRIPTION = "Frugal Object Detector for forest fires"
@@ -97,18 +104,13 @@ async def evaluate_image(request: ImageEvaluationRequest):
     # YOUR MODEL INFERENCE CODE HERE
     # Update the code below to replace the random baseline with your model inference
     #--------------------------------------------------------------------------------------------  
-    # Import strict minimum
-    from pathlib import Path
-    from ultralytics import YOLO
-    from torch import device
-    from torch.cuda import is_available
 
     THRESHOLD = 0.18
 
     # Load model
     model_path = Path("tasks", "models")
-    model_name = "pruned_fp16.pt"
-    print(f"Loading model {model_name}")
+    model_name = "best_gpu_fp16.pt"
+    logging.info(f"Loading model {model_name}")
     model = YOLO(Path(model_path, model_name), task="detect")
     device_name = device("cuda" if is_available() else "cpu")
     IMGSIZE = 1280
@@ -118,7 +120,7 @@ async def evaluate_image(request: ImageEvaluationRequest):
     pred_boxes = []
     true_boxes_list = []  # List of lists, each inner list contains boxes for one image
     
-    print(f"Inference start on device: {device_name}")
+    logging.info(f"Inference start on device: {device_name}")
     for example in test_dataset:
         # Parse true annotation (YOLO format: class_id x_center y_center width height)
         annotation = example.get("annotations", "").strip()

tasks/models/cpu_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df234f73cd50dcb745021703a067a350e7b1ff192cf5d9a1f67af3527fa9f0d3
+size 5322682