updates

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

app.py

@@ -2,8 +2,10 @@ import gradio as gr
 import os
 import threading
 import random
-from datasets import load_dataset, Dataset, Features, Value
+from datasets import load_dataset, Dataset, Features, Value, concatenate_datasets
 from huggingface_hub import login
+
+# Authenticate with Hugging Face
 token = os.getenv("HUGGINGFACE_TOKEN")
 if token:
     login(token=token)
@@ -13,8 +15,8 @@ dataset_name = "GeorgeIbrahim/EGYCOCO"  # Replace with your dataset name
 
 # Load or create the dataset
 try:
-    dataset = load_dataset(dataset_name)
-    print(dataset)
+    dataset = load_dataset(dataset_name, split="train")
+    print("Loaded existing dataset:", dataset)
 except Exception as e:
     # Create an empty dataset if it doesn't exist
     features = Features({
@@ -32,7 +34,7 @@ current_image = None
 # Function to get a random image that hasn’t been annotated or skipped
 def get_next_image():
     with lock:
-        available_images = [img for img in image_files]
+        available_images = [img for img in image_files if img not in dataset["image_id"]]
         if available_images:
             return os.path.join(image_folder, random.choice(available_images))
     return None
@@ -50,13 +52,14 @@ def save_annotation(caption):
         if caption.strip().lower() == "skip":
             caption = "skipped"
 
-        # Add the new annotation to the dataset
-        new_data = {"image_id": image_id, "caption": caption}
-        dataset.add_item(new_data)  # Update the dataset variable
+        # Add the new annotation as a new row to the dataset
+        new_data = Dataset.from_dict({"image_id": [image_id], "caption": [caption]})
+        global dataset
+        dataset = concatenate_datasets([dataset, new_data])
 
         # Save updated dataset to Hugging Face
         dataset.push_to_hub(dataset_name)
-        print("Already pushed")
+        print("Pushed updated dataset")
 
     # Fetch the next image
     current_image = get_next_image()
@@ -67,25 +70,7 @@ def save_annotation(caption):
 
 # Function to skip the current image
 def skip_image():
-    global current_image
-    if current_image is None:
-        return gr.update(visible=False), gr.update(value="All images have been annotated!")
-
-    with lock:
-        image_id = os.path.basename(current_image)
-        # Record "skipped" caption directly here
-        new_data = {"image_id": image_id, "caption": "skipped"}
-        dataset.add_item(new_data)  # Update the dataset variable
-
-        # Save updated dataset to Hugging Face
-        dataset.push_to_hub(dataset_name)
-
-    # Fetch the next image
-    current_image = get_next_image()
-    if current_image:
-        return gr.update(value=current_image), gr.update(value="")
-    else:
-        return gr.update(visible=False), gr.update(value="All images have been annotated!")
+    return save_annotation("skip")
 
 # Function to initialize the interface
 def initialize_interface():