added license of mtlora and perception encoders code

app.py

@@ -10,8 +10,8 @@ import numpy as np
 from PIL import Image, ImageDraw, ImageFont
 import base64
 from io import BytesIO
-import traceback  # Import traceback at the top
-from huggingface_hub import snapshot_download # Use snapshot_download for startup
+import traceback  
+from huggingface_hub import snapshot_download 
 from utils.face_detector import FaceDetector
 
 # Class definitions
@@ -36,7 +36,7 @@ model = None
 transform = None
 detector = None
 device = None
-current_ckpt_dir = None # This will now store the full path to the loaded model
+current_ckpt_dir = None 
 CHECKPOINTS_DIR = './checkpoints/'
 MODEL_REPO_ID = "Antuke/FaR-FT-PE"
 
@@ -50,14 +50,13 @@ def scan_checkpoints(ckpt_dir):
         ckpt_files = [
             os.path.join(ckpt_dir, f)
             for f in sorted(os.listdir(ckpt_dir))
-            if f.endswith(('.pt', '.pth')) # Ensure we only scan for model files
+            if f.endswith(('.pt', '.pth')) 
         ]
     except Exception as e:
         print(f"Error scanning checkpoint directory {ckpt_dir}: {e}")
         return [], None
     
-    # Create a list of (label, value) tuples
-    # label = filename (e.g., "mtlora.pt"), value = full path
+
     choices_list = [(os.path.basename(f), f) for f in ckpt_files]
     
     default_ckpt_path = os.path.join(ckpt_dir, 'mtlora.pt')
@@ -65,7 +64,7 @@ def scan_checkpoints(ckpt_dir):
     if default_ckpt_path in ckpt_files:
         return choices_list, default_ckpt_path
     elif ckpt_files:
-        return choices_list, ckpt_files[0] # default_ckpt_value is the full path
+        return choices_list, ckpt_files[0] 
     else:
         print(f"No checkpoints found in {ckpt_dir}")
         return [], None
@@ -82,16 +81,13 @@ def load_model(device,ckpt_dir='./checkpoints/mtlora.pt', pe_vision_config="PE-C
     return model,transform
 
 def load_model_and_update_status(model_filepath):
-    """
-    Wrapper function to load a model *from a local file path* and return a status.
-    The file path is provided by the dropdown.
-    """
+    """Wrapper function to load a model """
     global model, current_ckpt_dir
     
     if model_filepath is None or model_filepath == "":
         return "No checkpoint selected."
 
-    # Check if this model *filepath* is already loaded
+    # Check if this model filepath is already loaded
     if model is not None and model_filepath == current_ckpt_dir:
         status = f"Model already loaded: {os.path.basename(model_filepath)}"
         print(status)
@@ -99,11 +95,8 @@ def load_model_and_update_status(model_filepath):
         
     gr.Info(f"Loading model: {os.path.basename(model_filepath)}...")
     try:
-        # --- This is the new logic ---
-        # The file is already local. Just initialize it.
-        # The 'model_filepath' *is* the ckpt_dir for init_model
+
         init_model(ckpt_dir=model_filepath, detection_confidence=0.5)
-        # --- End of new logic ---
         
         current_ckpt_dir = model_filepath  # Set global path on successful load
         status = f"Successfully loaded: {os.path.basename(model_filepath)}"
@@ -170,10 +163,14 @@ def predict(model, image):
         return results
 
 def get_centroid_weighted_age(probs):
+    """
+    Using centroids of age group we calculate an age regression number
+    using an average weight based on predicted probability distribution 
+    """
     probs = list(probs.values())
     centroids =  [1, 4.5, 14.5, 24.5, 34.5, 44.5, 54.5, 64.5, 80]
     age = 0
-    # print(probs) # DEBUG
+
     for i,p in enumerate(probs):
         age += p * centroids[i]
 
@@ -191,7 +188,6 @@ def init_model(ckpt_dir="./checkpoints/mtlora.pt", detection_confidence=0.5):
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     print(f"Using device: {device}")
 
-    # Verify model weights exist
     if not os.path.exists(ckpt_dir):
         error_msg = f"Model weights not found: {ckpt_dir}."
         print(f"ERROR: {error_msg}")
@@ -226,8 +222,6 @@ def process_image(image, selected_checkpoint_path):
         return None, "<p style='color: red;'>Please upload an image</p>"
 
     # Ensure model is initialized
-    # This check is crucial. If the user changes the dropdown, it triggers
-    # load_model_and_update_status. If they just hit "Classify",
     # this check ensures the selected model is loaded.
     if model is None or selected_checkpoint_path != current_ckpt_dir:
         print(f"Model mismatch or not loaded. Selected: {selected_checkpoint_path}, Current: {current_ckpt_dir}")
@@ -237,26 +231,24 @@ def process_image(image, selected_checkpoint_path):
 
 
     try:
-        # --- 1. Prepare images for detection and drawing ---
         
         # Convert PIL to OpenCV format (BGR) for the detector
         if isinstance(image, Image.Image):
             img_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
         else:
-            # Assuming it's a numpy array from Gradio webcam
             img_cv = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
 
         # Create a PIL copy to draw annotations on
         img_pil_annotated = image.copy()
         draw = ImageDraw.Draw(img_pil_annotated)
 
-        # --- 2. Detect faces ---
+        # ---  Detect faces ---
         faces = detector.detect(img_cv, pad_rect=True)
 
         if faces is None or len(faces) == 0:
             return image, "<p style='color: orange;'>No faces detected in the image</p>"
 
-        # --- 3. Process detected faces ---
+        # --- Process detected faces ---
         crops_pil = []
         face_data = []
 
@@ -265,33 +257,32 @@ def process_image(image, selected_checkpoint_path):
             crop_pil = Image.fromarray(crop_rgb)
             crops_pil.append(crop_pil)
 
-            # Resize crop to 336x336 for display
+            # Resize crop to 336x336 for display, to match model input size
             crop_resized = crop_pil.resize((336, 336), Image.Resampling.LANCZOS)
 
             face_data.append({
                 'bbox': bbox,
                 'detection_confidence': float(confidence),
-                'crop_image': crop_resized  # Store the resized crop
+                'crop_image': crop_resized  
             })
 
-        # --- 4. Batch transform and predict ---
+        # --- Batch transform and predict ---
         crop_tensors = [transform(crop_pil) for crop_pil in crops_pil]
         batch_tensor = torch.stack(crop_tensors).to(device)
 
-        # Get predictions
         predictions = predict(model, batch_tensor)
 
         # Combine face data with predictions
         for face, pred in zip(face_data, predictions):
             face['predictions'] = pred
 
-        # --- 5. Create annotated image (using PIL) ---
+        # ---  Create annotated image (using PIL) ---
         for idx, face in enumerate(face_data):
             bbox = face['bbox']
             pred = face['predictions']
             x, y, w, h = bbox
 
-            # --- Calculate Adaptive Font (from demo.py) ---
+            # --- Calculate Adaptive Font  ---
             font_size_ratio = 0.08
             min_font_size = 12
             max_font_size = 48
@@ -323,16 +314,15 @@ def process_image(image, selected_checkpoint_path):
             lines_to_draw.append(f"Emotion: {emo_label} ({emo_conf*100:.0f}%)")
 
 
-            # --- Calculate total height of the text block (from demo.py) ---
+            # --- Calculate total height of the text block  ---
             line_spacing = 10
             total_text_height = 0
             for line in lines_to_draw:
                 _left, top, _right, bottom = draw.textbbox((0, 0), line, font=font)
                 total_text_height += (bottom - top) + line_spacing
             
-            # --- Place text ABOVE or BELOW the box (from demo.py) ---
+            # --- Place text ABOVE or BELOW the box  ---
             if y - total_text_height > 0:
-                # PLACE TEXT ABOVE: There is enough space
                 text_y = y - line_spacing
                 for line in reversed(lines_to_draw):
                     left, top, right, bottom = draw.textbbox((x, text_y), line, font=font, anchor="ls") # anchor left-baseline
@@ -340,7 +330,6 @@ def process_image(image, selected_checkpoint_path):
                     draw.text((x, text_y), line, font=font, fill="white", anchor="ls")
                     text_y = top - line_spacing # Move y-position up for the next line
             else:
-                # PLACE TEXT BELOW: Not enough space above, so draw downwards
                 text_y = y + h + line_spacing
                 for line in lines_to_draw:
                     left, top, right, bottom = draw.textbbox((x, text_y), line, font=font, anchor="lt") 
@@ -348,7 +337,6 @@ def process_image(image, selected_checkpoint_path):
                     draw.text((x, text_y), line, font=font, fill="white", anchor="lt")
                     text_y = bottom + line_spacing 
 
-        # --- 6. Create HTML results ---
         
         # Helper function to convert PIL image to base64
         def pil_to_base64(img_pil):
@@ -357,7 +345,6 @@ def process_image(image, selected_checkpoint_path):
             img_str = base64.b64encode(buffered.getvalue()).decode()
             return f"data:image/jpeg;base64,{img_str}"
 
-        # (HTML Generation code remains the same as before)
         results_html = f"""
         <style>
             :root {{
@@ -609,7 +596,7 @@ def process_image(image, selected_checkpoint_path):
             """
         results_html += "</div>"
 
-        # --- 7. Return the annotated PIL image and HTML ---
+        # ---  Return the annotated PIL image and HTML ---
         return img_pil_annotated, results_html
 
     except Exception as e:
@@ -631,7 +618,6 @@ def create_interface(checkpoint_list, default_checkpoint, initial_status):
     """
 
     # Create interface
-    # --- FIX: Added theme=gr.themes.Default() to enable light/dark mode switching ---
     with gr.Blocks(css=custom_css, title="Face Classification System", theme=gr.themes.Default()) as demo:
 
         with gr.Row():
@@ -642,8 +628,8 @@ def create_interface(checkpoint_list, default_checkpoint, initial_status):
             with gr.Column(scale=3):
                 checkpoint_dropdown = gr.Dropdown(
                     label="Select Model Checkpoint",
-                    choices=checkpoint_list, # This is now a list of (label, path) tuples
-                    value=default_checkpoint, # This is the full path to the default
+                    choices=checkpoint_list, 
+                    value=default_checkpoint, 
                 )
             with gr.Column(scale=2):
                 model_status_text = gr.Textbox(
@@ -698,7 +684,6 @@ def create_interface(checkpoint_list, default_checkpoint, initial_status):
                     size="lg"
                 )
 
-        # Examples - after button
         # Dynamically load example images from example directory
         example_dir = "example"
         example_images = []
@@ -720,7 +705,7 @@ def create_interface(checkpoint_list, default_checkpoint, initial_status):
                 cache_examples=False
             )
 
-        # Results section - full width below everything
+        # Results section
         with gr.Row():
             with gr.Column(scale=1):
                 output_html = gr.HTML(
@@ -731,13 +716,13 @@ def create_interface(checkpoint_list, default_checkpoint, initial_status):
         # Event handlers
         analyze_btn.click(
             fn=process_image,
-            inputs=[input_image, checkpoint_dropdown], # Pass dropdown value (which is the path)
+            inputs=[input_image, checkpoint_dropdown],
             outputs=[output_image, output_html]
         )
         
         checkpoint_dropdown.change(
             fn=load_model_and_update_status,
-            inputs=[checkpoint_dropdown], # Pass dropdown value (which is the path)
+            inputs=[checkpoint_dropdown],
             outputs=[model_status_text]
         )
 
@@ -764,10 +749,8 @@ try:
 except Exception as e:
     print(f"CRITICAL: Failed to download models from Hub. {e}")
     traceback.print_exc()
-# --- End of NEW code ---
 
 
-# --- 1. Scan for models first ---
 # This will now find the files you just downloaded
 checkpoint_list, default_checkpoint = scan_checkpoints(CHECKPOINTS_DIR)
 
@@ -777,7 +760,7 @@ else:
     print(f"Found checkpoints: {len(checkpoint_list)} file(s).")
     print(f"Default checkpoint: {default_checkpoint}")
 
-# --- 2. Try to initialize default model ---
+# --- Try to initialize default model ---
 initial_status_msg = "No default model found. Please select one."
 if default_checkpoint:
     print(f"\nInitializing default model: {default_checkpoint}")
@@ -789,7 +772,7 @@ else:
     print("⚠ Warning: No default model to load.")
 
 
-# --- 3. Create interface FIRST (so it shows even if model fails) ---
+# ---  Create interface FIRST (so it shows even if model fails) ---
 print("Creating Gradio interface...")
 demo = create_interface(checkpoint_list, default_checkpoint, initial_status_msg)
 print("✓ Interface created successfully!")
@@ -799,7 +782,6 @@ if __name__ == "__main__":
     import argparse
 
     parser = argparse.ArgumentParser(description="VLM Soft Biometrics - Gradio Interface")
-    # ckpt_dir is now managed by the startup download, so this arg is less relevant
     parser.add_argument("--ckpt_dir", type=str, default="./checkpoints/", 
                         help="Path to the checkpoint directory (will be populated from HF Hub)")
     parser.add_argument("--detection_confidence", type=float, default=0.5,
@@ -812,9 +794,7 @@ if __name__ == "__main__":
                         help="Server name/IP to bind to")
     args = parser.parse_args()
     
-    # Update global config if args are provided
     CHECKPOINTS_DIR = args.ckpt_dir
-    # Note: detection_confidence is passed to init_model during load, so it's handled.
 
     print(f"\nLaunching server on {args.server_name}:{args.port}")
     print(f"Monitoring checkpoint directory: {CHECKPOINTS_DIR}")

core/LICENSE_PE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

src/LICENSE_MTLORA

@@ -0,0 +1,21 @@
+MIT License
+
+    Copyright (c) SCALE Lab, Brown University.
+
+    Permission is hereby granted, free of charge, to any person obtaining a copy
+    of this software and associated documentation files (the "Software"), to deal
+    in the Software without restriction, including without limitation the rights
+    to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+    copies of the Software, and to permit persons to whom the Software is
+    furnished to do so, subject to the following conditions:
+
+    The above copyright notice and this permission notice shall be included in all
+    copies or substantial portions of the Software.
+
+    THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+    IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+    FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+    AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+    LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+    OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+    SOFTWARE