Update app.py

app.py

@@ -16,7 +16,7 @@ RAW_PATH = os.path.join("images", "raw")
 EMBEDDINGS_PATH = os.path.join("images", "embeddings")
 
 # Specific values for percentage of data for training
-percentage_values = [10, 30, 50, 70, 100]
+percentage_values = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]
 
 # Custom class to capture print output
 class PrintCapture(io.StringIO):
@@ -47,6 +47,15 @@ def create_random_image(size=(300, 300)):
     random_image = np.random.rand(*size, 3) * 255
     return Image.fromarray(random_image.astype('uint8'))
 
+# Function to load the pre-trained model from your cloned repository
+def load_custom_model():
+    from lwm_model import LWM  # Assuming the model is defined in lwm_model.py
+    model = LWM()  # Modify this according to your model initialization
+    model.eval()
+    return model
+
+import importlib.util
+
 # Function to dynamically load a Python module from a given file path
 def load_module_from_path(module_name, file_path):
     spec = importlib.util.spec_from_file_location(module_name, file_path)
@@ -59,19 +68,42 @@ def split_dataset(channels, labels, percentage_idx):
     percentage = percentage_values[percentage_idx] / 100
     num_samples = channels.shape[0]
     train_size = int(num_samples * percentage)
+    print(f'Number of Training Samples: {train_size}')
+    
     indices = np.arange(num_samples)
     np.random.shuffle(indices)
     
     train_idx, test_idx = indices[:train_size], indices[train_size:]
+    
     train_data, test_data = channels[train_idx], channels[test_idx]
     train_labels, test_labels = labels[train_idx], labels[test_idx]
     
     return train_data, test_data, train_labels, test_labels
 
+# Function to calculate Euclidean distance between a point and a centroid
+def euclidean_distance(x, centroid):
+    return np.linalg.norm(x - centroid)
+
+import torch
+
+def classify_based_on_distance(train_data, train_labels, test_data):
+    # Compute the centroids for the two classes
+    centroid_0 = train_data[train_labels == 0].mean(dim=0)  # Use torch.mean
+    centroid_1 = train_data[train_labels == 1].mean(dim=0)  # Use torch.mean
+    
+    predictions = []
+    for test_point in test_data:
+        # Compute Euclidean distance between the test point and each centroid
+        dist_0 = euclidean_distance(test_point, centroid_0)
+        dist_1 = euclidean_distance(test_point, centroid_1)
+        predictions.append(0 if dist_0 < dist_1 else 1)
+    
+    return torch.tensor(predictions)  # Return predictions as a PyTorch tensor
+
 # Function to generate confusion matrix plot
 def plot_confusion_matrix(y_true, y_pred, title):
     cm = confusion_matrix(y_true, y_pred)
-    plt.figure(figsize=(4, 4))
+    plt.figure(figsize=(5, 5))
     plt.imshow(cm, cmap='Blues')
     plt.title(title)
     plt.xlabel('Predicted')
@@ -84,76 +116,101 @@ def plot_confusion_matrix(y_true, y_pred, title):
     return Image.open(f"{title}.png")
 
 def identical_train_test_split(output_emb, output_raw, labels, percentage):
-    N = output_emb.shape[0]  
-    indices = torch.randperm(N)  
+    N = output_emb.shape[0]  # Get the total number of samples
+    
+    # Generate the indices for shuffling and splitting
+    indices = torch.randperm(N)  # Randomly shuffle the indices
+    
+    # Calculate the split index
     split_index = int(N * percentage)
-    train_indices = indices[:split_index]
-    test_indices = indices[split_index:]
+    
+    # Split indices into train and test
+    train_indices = indices[:split_index]  # First 80% for training
+    test_indices = indices[split_index:]   # Remaining 20% for testing
+    
+    # Select the same indices from both output_emb and output_raw
     train_emb = output_emb[train_indices]
     test_emb = output_emb[test_indices]
+    
     train_raw = output_raw[train_indices]
     test_raw = output_raw[test_indices]
+
     train_labels = labels[train_indices]
     test_labels = labels[test_indices]
 
     return train_emb, test_emb, train_raw, test_raw, train_labels, test_labels
 
-# Function to classify test data based on distance to class centroids
-def classify_based_on_distance(train_data, train_labels, test_data):
-    centroid_0 = train_data[train_labels == 0].mean(dim=0)  
-    centroid_1 = train_data[train_labels == 1].mean(dim=0)  
-    
-    predictions = []
-    for test_point in test_data:
-        dist_0 = torch.norm(test_point - centroid_0)
-        dist_1 = torch.norm(test_point - centroid_1)
-        predictions.append(0 if dist_0 < dist_1 else 1)
-    
-    return torch.tensor(predictions)  
-
 # Store the original working directory when the app starts
 original_dir = os.getcwd()
 
 def process_hdf5_file(uploaded_file, percentage_idx):
     capture = PrintCapture()
-    sys.stdout = capture  
+    sys.stdout = capture  # Redirect print statements to capture
     
     try:
         model_repo_url = "https://huggingface.co/sadjadalikhani/LWM"
         model_repo_dir = "./LWM"
+
+        # Step 1: Clone the repository if not already done
         if not os.path.exists(model_repo_dir):
+            print(f"Cloning model repository from {model_repo_url}...")
             subprocess.run(["git", "clone", model_repo_url, model_repo_dir], check=True)
+
+        # Step 2: Verify the repository was cloned and change the working directory
         repo_work_dir = os.path.join(original_dir, model_repo_dir)
         if os.path.exists(repo_work_dir):
-            os.chdir(repo_work_dir)  
+            os.chdir(repo_work_dir)  # Change the working directory only once
+            print(f"Changed working directory to {os.getcwd()}")
+            print(f"Directory content: {os.listdir(os.getcwd())}")  # Debugging: Check repo content
+        else:
+            print(f"Directory {repo_work_dir} does not exist.")
+            return
+            
+        # Step 3: Dynamically load lwm_model.py, input_preprocess.py, and inference.py
         lwm_model_path = os.path.join(os.getcwd(), 'lwm_model.py')
         input_preprocess_path = os.path.join(os.getcwd(), 'input_preprocess.py')
         inference_path = os.path.join(os.getcwd(), 'inference.py')
 
+        # Load lwm_model
         lwm_model = load_module_from_path("lwm_model", lwm_model_path)
+
+        # Load input_preprocess
         input_preprocess = load_module_from_path("input_preprocess", input_preprocess_path)
+
+        # Load inference
         inference = load_module_from_path("inference", inference_path)
 
+        # Step 4: Load the model from lwm_model module
         device = 'cpu'
+        print(f"Loading the LWM model on {device}...")
         model = lwm_model.LWM.from_pretrained(device=device)
 
+        # Step 5: Load the HDF5 file and extract the channels and labels
         with h5py.File(uploaded_file.name, 'r') as f:
-            channels = np.array(f['channels'])
-            labels = np.array(f['labels'])
+            channels = np.array(f['channels'])  # Assuming 'channels' dataset in the HDF5 file
+            labels = np.array(f['labels'])  # Assuming 'labels' dataset in the HDF5 file
+        print(f"Loaded dataset with {channels.shape[0]} samples.")
 
+        # Step 7: Tokenize the data using the tokenizer from input_preprocess
         preprocessed_chs = input_preprocess.tokenizer(manual_data=channels)
+
+        # Step 7: Perform inference using the functions from inference.py
         output_emb = inference.lwm_inference(preprocessed_chs, 'channel_emb', model)
         output_raw = inference.create_raw_dataset(preprocessed_chs, device)
 
-        train_data_emb, test_data_emb, train_data_raw, test_data_raw, train_labels, test_labels = identical_train_test_split(
-            output_emb.view(len(output_emb),-1),
-            output_raw.view(len(output_raw),-1),
-            labels,
-            percentage_idx)
+        print(f"Output Embeddings Shape: {output_emb.shape}")
+        print(f"Output Raw Shape: {output_raw.shape}")
+
+        train_data_emb, test_data_emb, train_data_raw, test_data_raw, train_labels, test_labels = identical_train_test_split(output_emb.view(len(output_emb),-1),
+                                                                                                                             output_raw.view(len(output_raw),-1),
+                                                                                                                             labels,
+                                                                                                                             percentage_idx)
         
+        # Step 8: Perform classification using the Euclidean distance for both raw and embeddings
         pred_raw = classify_based_on_distance(train_data_raw, train_labels, test_data_raw)
         pred_emb = classify_based_on_distance(train_data_emb, train_labels, test_data_emb)
 
+        # Step 9: Generate confusion matrices for both raw and embeddings
         raw_cm_image = plot_confusion_matrix(test_labels, pred_raw, title="Confusion Matrix (Raw Channels)")
         emb_cm_image = plot_confusion_matrix(test_labels, pred_emb, title="Confusion Matrix (Embeddings)")
 
@@ -163,28 +220,29 @@ def process_hdf5_file(uploaded_file, percentage_idx):
         return str(e), str(e), capture.get_output()
 
     finally:
+        # Always return to the original working directory after processing
         os.chdir(original_dir)
-        sys.stdout = sys.__stdout__  
+        sys.stdout = sys.__stdout__  # Reset print statements
 
+# Function to handle logic based on whether a file is uploaded or not
 def los_nlos_classification(file, percentage_idx):
     if file is not None:
         return process_hdf5_file(file, percentage_idx)
     else:
         return display_predefined_images(percentage_idx), None
 
-# Define the Gradio interface with a compact, minimal layout
+# Define the Gradio interface
 with gr.Blocks(css="""
+    .vertical-slider input[type=range] {
+        writing-mode: bt-lr; /* IE */
+        -webkit-appearance: slider-vertical; /* WebKit */
+        width: 8px;
+        height: 200px;
+    }
     .slider-container {
+        display: inline-block;
+        margin-right: 50px;
         text-align: center;
-        margin-bottom: 20px;
-    }
-    .image-row {
-        justify-content: center;
-        margin-top: 10px;
-    }
-    .output-box {
-        max-width: 600px;
-        margin: 0 auto;
     }
 """) as demo:
     
@@ -203,24 +261,33 @@ with gr.Blocks(css="""
     # Tabs for Beam Prediction and LoS/NLoS Classification
     with gr.Tab("Beam Prediction Task"):
         gr.Markdown("### Beam Prediction Task")
+        
         with gr.Row():
             with gr.Column(elem_id="slider-container"):
-                percentage_slider_bp = gr.Slider(minimum=0, maximum=4, step=1, value=0, label="Training Data (%)")
-        with gr.Row(elem_id="image-row"):
-            raw_img_bp = gr.Image(label="Raw Channels", type="pil", width=300, height=300)
-            embeddings_img_bp = gr.Image(label="Embeddings", type="pil", width=300, height=300)
+                gr.Markdown("Percentage of Data for Training")
+                percentage_slider_bp = gr.Slider(minimum=0, maximum=4, step=1, value=0, interactive=True, elem_id="vertical-slider")
+
+        with gr.Row():
+            raw_img_bp = gr.Image(label="Raw Channels", type="pil", width=300, height=300, interactive=False)
+            embeddings_img_bp = gr.Image(label="Embeddings", type="pil", width=300, height=300, interactive=False)
+
         percentage_slider_bp.change(fn=display_predefined_images, inputs=[percentage_slider_bp], outputs=[raw_img_bp, embeddings_img_bp])
 
     with gr.Tab("LoS/NLoS Classification Task"):
         gr.Markdown("### LoS/NLoS Classification Task")
+        
         file_input = gr.File(label="Upload HDF5 Dataset", file_types=[".h5"])
+
         with gr.Row():
             with gr.Column(elem_id="slider-container"):
-                percentage_slider_los = gr.Slider(minimum=0, maximum=4, step=1, value=0, label="Training Data (%)")
-        with gr.Row(elem_id="image-row"):
-            raw_img_los = gr.Image(label="Raw Channels", type="pil", width=300, height=300)
-            embeddings_img_los = gr.Image(label="Embeddings", type="pil", width=300, height=300)
-            output_textbox = gr.Textbox(label="Console Output", lines=8, elem_classes="output-box")
+                gr.Markdown("Percentage of Data for Training")
+                percentage_slider_los = gr.Slider(minimum=0, maximum=4, step=1, value=0, interactive=True, elem_id="vertical-slider")
+
+        with gr.Row():
+            raw_img_los = gr.Image(label="Raw Channels", type="pil", width=300, height=300, interactive=False)
+            embeddings_img_los = gr.Image(label="Embeddings", type="pil", width=300, height=300, interactive=False)
+            output_textbox = gr.Textbox(label="Console Output", lines=10)
+
         file_input.change(fn=los_nlos_classification, inputs=[file_input, percentage_slider_los], outputs=[raw_img_los, embeddings_img_los, output_textbox])
         percentage_slider_los.change(fn=los_nlos_classification, inputs=[file_input, percentage_slider_los], outputs=[raw_img_los, embeddings_img_los, output_textbox])