updates

app.py

@@ -1,3 +1,4 @@
+#Latest working version
 import gradio as gr
 import os
 import threading
@@ -13,22 +14,18 @@ else:
     print("HUGGINGFACE_TOKEN environment variable not set.")
 dataset_name = "GeorgeIbrahim/EGYCOCO"  # Replace with your dataset name
 
-# Load or create the datasets
+# Load or create the dataset
 try:
-    train_dataset = load_dataset(dataset_name, split="train")
-    val_dataset = load_dataset(dataset_name, split="validation")
-    print("Loaded existing datasets:", train_dataset, val_dataset)
+    dataset = load_dataset(dataset_name, split="train")
+    print("Loaded existing dataset:", dataset)
 except Exception as e:
-    # Create empty datasets if they don't exist
+    # Create an empty dataset if it doesn't exist
     features = Features({
         'image_id': Value(dtype='string'),
         'caption': Value(dtype='string'),
     })
-    train_dataset = Dataset.from_dict({'image_id': [], 'caption': []}, features=features)
-    val_dataset = Dataset.from_dict({'image_id': [], 'caption': []}, features=features)
-    dataset_dict = {"train": train_dataset, "validation": val_dataset}
-    for split_name, split_dataset in dataset_dict.items():
-        split_dataset.push_to_hub(dataset_name, split=split_name)
+    dataset = Dataset.from_dict({'image_id': [], 'caption': []}, features=features)
+    dataset.push_to_hub(dataset_name)  # Push the empty dataset to Hugging Face
 
 image_folder = "images"
 image_files = [f for f in os.listdir(image_folder) if f.endswith(('.png', '.jpg', '.jpeg'))]
@@ -37,14 +34,15 @@ lock = threading.Lock()
 # Function to get a random image that hasn’t been annotated or skipped
 def get_next_image(session_data):
     with lock:
-        annotated_images = set(train_dataset["image_id"]) | set(val_dataset["image_id"])  # Set of annotated images
+        annotated_images = set(dataset["image_id"])  # Set of annotated images
         available_images = [img for img in image_files if img not in annotated_images]
+        # Check if the user already has an image
         if session_data["current_image"] is None and available_images:
             # Assign a new random image to the user
             session_data["current_image"] = random.choice(available_images)
     return os.path.join(image_folder, session_data["current_image"]) if session_data["current_image"] else None
 
-# Function to save the annotation to the correct split in Hugging Face datasets and fetch the next image
+# Function to save the annotation to Hugging Face dataset and fetch the next image
 def save_annotation(caption, session_data):
     if session_data["current_image"] is None:
         return gr.update(visible=False), gr.update(value="All images have been annotated!")
@@ -56,23 +54,14 @@ def save_annotation(caption, session_data):
         if caption.strip().lower() == "skip":
             caption = "skipped"
 
-        # Determine the dataset split based on the image name
-        if "train" in image_id:
-            target_dataset = train_dataset
-            split_name = "train"
-        elif "val" in image_id:
-            target_dataset = val_dataset
-            split_name = "validation"
-        else:
-            return gr.update(visible=False), gr.update(value="Unknown dataset split for image!")
-
-        # Add the new annotation to the correct dataset without overwriting
+        # Add the new annotation as a new row to the dataset
         new_data = Dataset.from_dict({"image_id": [image_id], "caption": [caption]})
-        target_dataset = concatenate_datasets([target_dataset, new_data])
+        global dataset
+        dataset = concatenate_datasets([dataset, new_data])
 
-        # Save the updated split to Hugging Face without overwriting
-        target_dataset.push_to_hub(dataset_name, split=split_name)
-        print(f"Pushed updated {split_name} dataset")
+        # Save updated dataset to Hugging Face
+        dataset.push_to_hub(dataset_name)
+        print("Pushed updated dataset")
 
         # Clear user's current image so they get a new one next time
         session_data["current_image"] = None
@@ -116,4 +105,4 @@ with gr.Blocks() as demo:
     # Load initial image
     demo.load(fn=initialize_interface, inputs=session_data, outputs=[image, caption])
 
-demo.launch(share=True)
+demo.launch(share=True)