Update App (#2)

- Summary (d5e9efc892e08de19347bb5a8522ec5e27809a26)

.flake8

@@ -0,0 +1,5 @@
+; https://www.flake8rules.com/
+
+[flake8]
+max-line-length = 120
+ignore = E203, E402, E741, W503

CODE_OF_CONDUCT.md

@@ -0,0 +1,80 @@
+# Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to make participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies within all project spaces, and it also applies when
+an individual is representing the project or its community in public spaces.
+Examples of representing a project or community include using an official
+project e-mail address, posting via an official social media account, or acting
+as an appointed representative at an online or offline event. Representation of
+a project may be further defined and clarified by project maintainers.
+
+This Code of Conduct also applies outside the project spaces when there is a
+reasonable belief that an individual's behavior may have a negative impact on
+the project or its community.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at <ryumina_ev@mail.ru>. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at <https://www.contributor-covenant.org/version/1/4/code-of-conduct.html>
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+<https://www.contributor-covenant.org/faq>

app.css

@@ -0,0 +1,68 @@
+div.app-flex-container {
+    display: flex;
+    align-items: left;
+}
+
+div.app-flex-container > img {
+    margin-right: 6px;
+}
+
+div.dl1 div.upload-container {
+    height: 350px;
+    max-height: 350px;
+}
+
+div.dl2 {
+    max-height: 200px;
+}
+
+div.dl2 img {
+    max-height: 200px;
+}
+
+.submit {
+    display: inline-block;
+    padding: 10px 20px;
+    font-size: 16px;
+    font-weight: bold;
+    text-align: center;
+    text-decoration: none;
+    cursor: pointer;
+    border: var(--button-border-width) solid var(--button-primary-border-color);
+    background: var(--button-primary-background-fill);
+    color: var(--button-primary-text-color);
+    border-radius: 8px;
+    transition: all 0.3s ease;
+}
+
+.submit[disabled] {
+    cursor: not-allowed;
+    opacity: 0.6;
+}
+
+.submit:hover:not([disabled]) {
+    border-color: var(--button-primary-border-color-hover);
+    background: var(--button-primary-background-fill-hover);
+    color: var(--button-primary-text-color-hover);
+}
+
+.clear {
+    display: inline-block;
+    padding: 10px 20px;
+    font-size: 16px;
+    font-weight: bold;
+    text-align: center;
+    text-decoration: none;
+    cursor: pointer;
+    border-radius: 8px;
+    transition: all 0.3s ease;
+}
+
+.clear[disabled] {
+    cursor: not-allowed;
+    opacity: 0.6;
+}
+
+.submit:active:not([disabled]), .clear:active:not([disabled]) {
+    transform: scale(0.98);
+}

app.py

@@ -1,110 +1,17 @@
-import torch
-from PIL import Image
-from torchvision import transforms
-import mediapipe as mp
-import numpy as np
-import math
-import requests
+"""
+File: app.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: Description: Main application file for Facial_Expression_Recognition.
+             The file defines the Gradio interface, sets up the main blocks,
+             and includes event handlers for various components.
+License: MIT License
+"""
 
 import gradio as gr
 
-model_url = "https://huggingface.co/ElenaRyumina/face_emotion_recognition/resolve/main/FER_static_ResNet50_AffectNet.pth"
-model_path = "FER_static_ResNet50_AffectNet.pth"
-
-response = requests.get(model_url, stream=True)
-with open(model_path, "wb") as file:
-    for chunk in response.iter_content(chunk_size=8192):
-        file.write(chunk)
-
-pth_model = torch.jit.load(model_path)
-pth_model.eval()
-
-DICT_EMO = {
-    0: "Neutral",
-    1: "Happiness",
-    2: "Sadness",
-    3: "Surprise",
-    4: "Fear",
-    5: "Disgust",
-    6: "Anger",
-}
-
-mp_face_mesh = mp.solutions.face_mesh
-
-
-def pth_processing(fp):
-    class PreprocessInput(torch.nn.Module):
-        def init(self):
-            super(PreprocessInput, self).init()
-
-        def forward(self, x):
-            x = x.to(torch.float32)
-            x = torch.flip(x, dims=(0,))
-            x[0, :, :] -= 91.4953
-            x[1, :, :] -= 103.8827
-            x[2, :, :] -= 131.0912
-            return x
-
-    def get_img_torch(img):
-        ttransform = transforms.Compose([transforms.PILToTensor(), PreprocessInput()])
-        img = img.resize((224, 224), Image.Resampling.NEAREST)
-        img = ttransform(img)
-        img = torch.unsqueeze(img, 0)
-        return img
-
-    return get_img_torch(fp)
-
-
-def norm_coordinates(normalized_x, normalized_y, image_width, image_height):
-    x_px = min(math.floor(normalized_x * image_width), image_width - 1)
-    y_px = min(math.floor(normalized_y * image_height), image_height - 1)
-
-    return x_px, y_px
-
-
-def get_box(fl, w, h):
-    idx_to_coors = {}
-    for idx, landmark in enumerate(fl.landmark):
-        landmark_px = norm_coordinates(landmark.x, landmark.y, w, h)
-
-        if landmark_px:
-            idx_to_coors[idx] = landmark_px
-
-    x_min = np.min(np.asarray(list(idx_to_coors.values()))[:, 0])
-    y_min = np.min(np.asarray(list(idx_to_coors.values()))[:, 1])
-    endX = np.max(np.asarray(list(idx_to_coors.values()))[:, 0])
-    endY = np.max(np.asarray(list(idx_to_coors.values()))[:, 1])
-
-    (startX, startY) = (max(0, x_min), max(0, y_min))
-    (endX, endY) = (min(w - 1, endX), min(h - 1, endY))
-
-    return startX, startY, endX, endY
-
-
-def predict(inp):
-    inp = np.array(inp)
-    h, w = inp.shape[:2]
-
-    with mp_face_mesh.FaceMesh(
-        max_num_faces=1,
-        refine_landmarks=False,
-        min_detection_confidence=0.5,
-        min_tracking_confidence=0.5,
-    ) as face_mesh:
-        results = face_mesh.process(inp)
-        if results.multi_face_landmarks:
-            for fl in results.multi_face_landmarks:
-                startX, startY, endX, endY = get_box(fl, w, h)
-                cur_face = inp[startY:endY, startX:endX]
-                cur_face_n = pth_processing(Image.fromarray(cur_face))
-                prediction = (
-                    torch.nn.functional.softmax(pth_model(cur_face_n), dim=1)
-                    .detach()
-                    .numpy()[0]
-                )
-                confidences = {DICT_EMO[i]: float(prediction[i]) for i in range(7)}
-
-    return cur_face, confidences
+# Importing necessary components for the Gradio app
+from app.description import DESCRIPTION
+from app.app_utils import preprocess_and_predict
 
 
 def clear():
@@ -115,60 +22,19 @@ def clear():
     )
 
 
-style = """
-    div.dl1 div.upload-container {
-        height: 350px;
-        max-height: 350px;
-    }
-
-    div.dl2 {
-        max-height: 200px;
-    }
+with gr.Blocks(css="app.css") as demo:
+    gr.Markdown(value=DESCRIPTION)
 
-    div.dl2 img {
-        max-height: 200px;
-    }
-
-    .submit {
-        display: inline-block;
-        padding: 10px 20px;
-        font-size: 16px;
-        font-weight: bold;
-        text-align: center;
-        text-decoration: none;
-        cursor: pointer;
-        border: var(--button-border-width) solid var(--button-primary-border-color);
-        background: var(--button-primary-background-fill);
-        color: var(--button-primary-text-color);
-        border-radius: 8px;
-        transition: all 0.3s ease;
-    }
-    
-    .submit[disabled] {
-        cursor: not-allowed;
-        opacity: 0.6;
-    }
-    
-    .submit:hover:not([disabled]) {
-        border-color: var(--button-primary-border-color-hover);
-        background: var(--button-primary-background-fill-hover);
-        color: var(--button-primary-text-color-hover);
-    }
-    
-    .submit:active:not([disabled]) {
-        transform: scale(0.98);
-    }
-"""
-
-with gr.Blocks(css=style) as demo:
     with gr.Row():
         with gr.Column(scale=2, elem_classes="dl1"):
             input_image = gr.Image(type="pil")
             with gr.Row():
+                clear_btn = gr.Button(
+                    value="Clear", interactive=True, scale=1, elem_classes="clear"
+                )
                 submit = gr.Button(
                     value="Submit", interactive=True, scale=1, elem_classes="submit"
                 )
-                clear_btn = gr.Button(value="Clear", interactive=True, scale=1)
         with gr.Column(scale=1, elem_classes="dl4"):
             output_image = gr.Image(scale=1, elem_classes="dl2")
             output_label = gr.Label(num_top_classes=3, scale=1, elem_classes="dl3")
@@ -186,7 +52,7 @@ with gr.Blocks(css=style) as demo:
     )
 
     submit.click(
-        fn=predict,
+        fn=preprocess_and_predict,
         inputs=[input_image],
         outputs=[output_image, output_label],
         queue=True,
@@ -194,11 +60,7 @@ with gr.Blocks(css=style) as demo:
     clear_btn.click(
         fn=clear,
         inputs=[],
-        outputs=[
-            input_image,
-            output_image,
-            output_label,
-        ],
+        outputs=[input_image, output_image, output_label],
         queue=True,
     )
 

app/app_utils.py

@@ -0,0 +1,52 @@
+"""
+File: app_utils.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: This module contains utility functions for facial expression recognition application.
+License: MIT License
+"""
+
+import torch
+import numpy as np
+import mediapipe as mp
+from PIL import Image
+
+# Importing necessary components for the Gradio app
+from app.model import pth_model, pth_processing
+from app.face_utils import get_box
+from app.config import DICT_EMO
+
+
+mp_face_mesh = mp.solutions.face_mesh
+
+
+def preprocess_and_predict(inp):
+    inp = np.array(inp)
+
+    if inp is None:
+        return None, None
+
+    try:
+        h, w = inp.shape[:2]
+    except Exception:
+        return None, None
+
+    with mp_face_mesh.FaceMesh(
+        max_num_faces=1,
+        refine_landmarks=False,
+        min_detection_confidence=0.5,
+        min_tracking_confidence=0.5,
+    ) as face_mesh:
+        results = face_mesh.process(inp)
+        if results.multi_face_landmarks:
+            for fl in results.multi_face_landmarks:
+                startX, startY, endX, endY = get_box(fl, w, h)
+                cur_face = inp[startY:endY, startX:endX]
+                cur_face_n = pth_processing(Image.fromarray(cur_face))
+                prediction = (
+                    torch.nn.functional.softmax(pth_model(cur_face_n), dim=1)
+                    .detach()
+                    .numpy()[0]
+                )
+                confidences = {DICT_EMO[i]: float(prediction[i]) for i in range(7)}
+
+    return cur_face, confidences

app/config.py

@@ -0,0 +1,39 @@
+"""
+File: config.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: Configuration file.
+License: MIT License
+"""
+
+import toml
+from typing import Dict
+from types import SimpleNamespace
+
+
+def flatten_dict(prefix: str, d: Dict) -> Dict:
+    result = {}
+
+    for k, v in d.items():
+        if isinstance(v, dict):
+            result.update(flatten_dict(f"{prefix}{k}_", v))
+        else:
+            result[f"{prefix}{k}"] = v
+
+    return result
+
+
+config = toml.load("config.toml")
+
+config_data = flatten_dict("", config)
+
+config_data = SimpleNamespace(**config_data)
+
+DICT_EMO = {
+    0: "Neutral",
+    1: "Happiness",
+    2: "Sadness",
+    3: "Surprise",
+    4: "Fear",
+    5: "Disgust",
+    6: "Anger",
+}

app/description.py

@@ -0,0 +1,17 @@
+"""
+File: description.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: Project description for the Gradio app.
+License: MIT License
+"""
+
+# Importing necessary components for the Gradio app
+from app.config import config_data
+
+DESCRIPTION = f"""\
+# Facial_Expression_Recognition
+<div class="app-flex-container">
+    <img src="https://img.shields.io/badge/version-v{config_data.APP_VERSION}-rc0" alt="Version">
+    <a href="https://visitorbadge.io/status?path=https%3A%2F%2Fhuggingface.co%2Fspaces%2FElenaRyumina%2FFacial_Expression_Recognition"><img src="https://api.visitorbadge.io/api/combined?path=https%3A%2F%2Fhuggingface.co%2Fspaces%2FElenaRyumina%2FFacial_Expression_Recognition&countColor=%23263759&style=flat" /></a>
+</div>
+"""

app/face_utils.py

@@ -0,0 +1,33 @@
+"""
+File: face_utils.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: This module contains utility functions related to facial landmarks and image processing.
+License: MIT License
+"""
+
+import numpy as np
+import math
+
+
+def norm_coordinates(normalized_x, normalized_y, image_width, image_height):
+    x_px = min(math.floor(normalized_x * image_width), image_width - 1)
+    y_px = min(math.floor(normalized_y * image_height), image_height - 1)
+    return x_px, y_px
+
+
+def get_box(fl, w, h):
+    idx_to_coors = {}
+    for idx, landmark in enumerate(fl.landmark):
+        landmark_px = norm_coordinates(landmark.x, landmark.y, w, h)
+        if landmark_px:
+            idx_to_coors[idx] = landmark_px
+
+    x_min = np.min(np.asarray(list(idx_to_coors.values()))[:, 0])
+    y_min = np.min(np.asarray(list(idx_to_coors.values()))[:, 1])
+    endX = np.max(np.asarray(list(idx_to_coors.values()))[:, 0])
+    endY = np.max(np.asarray(list(idx_to_coors.values()))[:, 1])
+
+    (startX, startY) = (max(0, x_min), max(0, y_min))
+    (endX, endY) = (min(w - 1, endX), min(h - 1, endY))
+
+    return startX, startY, endX, endY

app/model.py

@@ -0,0 +1,55 @@
+"""
+File: model.py
+Author: Elena Ryumina and Dmitry Ryumin
+Description: This module provides functions for loading and processing a pre-trained deep learning model
+             for facial expression recognition.
+License: MIT License
+"""
+
+import torch
+import requests
+from PIL import Image
+from torchvision import transforms
+
+# Importing necessary components for the Gradio app
+from app.config import config_data
+
+
+def load_model(model_url, model_path):
+    try:
+        # Загрузка модели
+        with requests.get(model_url, stream=True) as response:
+            with open(model_path, "wb") as file:
+                for chunk in response.iter_content(chunk_size=8192):
+                    file.write(chunk)
+        return torch.jit.load(model_path).eval()
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        return None
+
+
+# Загрузите модель
+pth_model = load_model(config_data.model_url, config_data.model_path)
+
+
+def pth_processing(fp):
+    class PreprocessInput(torch.nn.Module):
+        def init(self):
+            super(PreprocessInput, self).init()
+
+        def forward(self, x):
+            x = x.to(torch.float32)
+            x = torch.flip(x, dims=(0,))
+            x[0, :, :] -= 91.4953
+            x[1, :, :] -= 103.8827
+            x[2, :, :] -= 131.0912
+            return x
+
+    def get_img_torch(img, target_size=(224, 224)):
+        transform = transforms.Compose([transforms.PILToTensor(), PreprocessInput()])
+        img = img.resize(target_size, Image.Resampling.NEAREST)
+        img = transform(img)
+        img = torch.unsqueeze(img, 0)
+        return img
+
+    return get_img_torch(fp)

config.toml

@@ -0,0 +1,5 @@
+APP_VERSION = "0.1.0"
+
+[model]
+url = "https://huggingface.co/ElenaRyumina/face_emotion_recognition/resolve/main/FER_static_ResNet50_AffectNet.pth"
+path = "FER_static_ResNet50_AffectNet.pth"

requirements.txt

@@ -3,5 +3,5 @@ requests==2.31.0
 torch==2.1.2
 torchaudio==2.1.2
 torchvision==0.16.2
-mediapipe==0.9.0.1
+mediapipe==0.10.9
 pillow==10.2.0