Added Audio and Pre-trained Large model

wanghaoddd · Oct 24, 2022 · 1789c77 · 1789c77
1 parent dacf535
commit 1789c77
Show file tree

Hide file tree

Showing 75 changed files with 79 additions and 22 deletions.
diff --git a/FYP/__pycache__/__init__.cpython-37.pyc b/FYP/__pycache__/__init__.cpython-37.pyc
diff --git a/FYP/__pycache__/__init__.cpython-39.pyc b/FYP/__pycache__/__init__.cpython-39.pyc
diff --git a/FYP/__pycache__/settings.cpython-37.pyc b/FYP/__pycache__/settings.cpython-37.pyc
diff --git a/FYP/__pycache__/settings.cpython-39.pyc b/FYP/__pycache__/settings.cpython-39.pyc
diff --git a/FYP/__pycache__/urls.cpython-37.pyc b/FYP/__pycache__/urls.cpython-37.pyc
diff --git a/FYP/__pycache__/urls.cpython-39.pyc b/FYP/__pycache__/urls.cpython-39.pyc
diff --git a/FYP/__pycache__/wsgi.cpython-37.pyc b/FYP/__pycache__/wsgi.cpython-37.pyc
diff --git a/FYP/__pycache__/wsgi.cpython-39.pyc b/FYP/__pycache__/wsgi.cpython-39.pyc
diff --git a/OFA/OFA b/OFA/OFA
diff --git a/OFA/__pycache__/__init__.cpython-37.pyc b/OFA/__pycache__/__init__.cpython-37.pyc
diff --git a/OFA/__pycache__/__init__.cpython-39.pyc b/OFA/__pycache__/__init__.cpython-39.pyc
diff --git a/OFA/__pycache__/admin.cpython-37.pyc b/OFA/__pycache__/admin.cpython-37.pyc
diff --git a/OFA/__pycache__/admin.cpython-39.pyc b/OFA/__pycache__/admin.cpython-39.pyc
diff --git a/OFA/__pycache__/apps.cpython-37.pyc b/OFA/__pycache__/apps.cpython-37.pyc
diff --git a/OFA/__pycache__/apps.cpython-39.pyc b/OFA/__pycache__/apps.cpython-39.pyc
diff --git a/OFA/__pycache__/forms.cpython-37.pyc b/OFA/__pycache__/forms.cpython-37.pyc
diff --git a/OFA/__pycache__/forms.cpython-39.pyc b/OFA/__pycache__/forms.cpython-39.pyc
diff --git a/OFA/__pycache__/models.cpython-37.pyc b/OFA/__pycache__/models.cpython-37.pyc
diff --git a/OFA/__pycache__/models.cpython-39.pyc b/OFA/__pycache__/models.cpython-39.pyc
diff --git a/OFA/__pycache__/urls.cpython-37.pyc b/OFA/__pycache__/urls.cpython-37.pyc
diff --git a/OFA/__pycache__/urls.cpython-39.pyc b/OFA/__pycache__/urls.cpython-39.pyc
diff --git a/OFA/__pycache__/views.cpython-37.pyc b/OFA/__pycache__/views.cpython-37.pyc
diff --git a/OFA/__pycache__/views.cpython-39.pyc b/OFA/__pycache__/views.cpython-39.pyc
diff --git a/OFA/audio.mp3 b/OFA/audio.mp3
diff --git a/OFA/About.css → OFA/backup/About.css b/OFA/About.css → OFA/backup/About.css
diff --git a/OFA/About.html → OFA/backup/About.html b/OFA/About.html → OFA/backup/About.html
diff --git a/OFA/Home.css → OFA/backup/Home.css b/OFA/Home.css → OFA/backup/Home.css
diff --git a/OFA/Home.html → OFA/backup/Home.html b/OFA/Home.html → OFA/backup/Home.html
diff --git a/OFA/nicepage.css → OFA/backup/nicepage.css b/OFA/nicepage.css → OFA/backup/nicepage.css
diff --git a/OFA/nicepage.js → OFA/backup/nicepage.js b/OFA/nicepage.js → OFA/backup/nicepage.js
diff --git a/OFA/fairseq b/OFA/fairseq
diff --git a/OFA/media/Empty_Image.png b/OFA/media/Empty_Image.png
diff --git a/OFA/media/Screenshot 2022-10-17 162715.png b/OFA/media/Screenshot 2022-10-17 162715.png
diff --git a/OFA/migrations/0004_alter_ofaimage_image.py b/OFA/migrations/0004_alter_ofaimage_image.py
@@ -0,0 +1,18 @@
+# Generated by Django 3.2.16 on 2022-10-24 03:07
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('OFA', '0003_alter_ofaimage_image'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='ofaimage',
+            name='image',
+            field=models.ImageField(upload_to='OFA\\static'),
+        ),
+    ]
diff --git a/OFA/migrations/__pycache__/0001_initial.cpython-37.pyc b/OFA/migrations/__pycache__/0001_initial.cpython-37.pyc
diff --git a/OFA/migrations/__pycache__/0001_initial.cpython-39.pyc b/OFA/migrations/__pycache__/0001_initial.cpython-39.pyc
diff --git a/OFA/migrations/__pycache__/0002_remove_ofaimage_name.cpython-37.pyc b/OFA/migrations/__pycache__/0002_remove_ofaimage_name.cpython-37.pyc
diff --git a/OFA/migrations/__pycache__/0002_remove_ofaimage_name.cpython-39.pyc b/OFA/migrations/__pycache__/0002_remove_ofaimage_name.cpython-39.pyc
diff --git a/OFA/migrations/__pycache__/0003_alter_ofaimage_image.cpython-37.pyc b/OFA/migrations/__pycache__/0003_alter_ofaimage_image.cpython-37.pyc
diff --git a/OFA/migrations/__pycache__/0003_alter_ofaimage_image.cpython-39.pyc b/OFA/migrations/__pycache__/0003_alter_ofaimage_image.cpython-39.pyc
diff --git a/OFA/migrations/__pycache__/0004_alter_ofaimage_image.cpython-37.pyc b/OFA/migrations/__pycache__/0004_alter_ofaimage_image.cpython-37.pyc
diff --git a/OFA/migrations/__pycache__/__init__.cpython-37.pyc b/OFA/migrations/__pycache__/__init__.cpython-37.pyc
diff --git a/OFA/migrations/__pycache__/__init__.cpython-39.pyc b/OFA/migrations/__pycache__/__init__.cpython-39.pyc
diff --git a/OFA/models.py b/OFA/models.py
@@ -1,3 +1,3 @@
 from django.db import models  
 class OFAImage(models.Model):
-    image = models.ImageField(upload_to='') 
+    image = models.ImageField(upload_to='OFA\static') 
diff --git a/OFA/ofa_image-caption_coco_large_en b/OFA/ofa_image-caption_coco_large_en
diff --git a/OFA/static/Screenshot 2022-10-14 195905.png b/OFA/static/Screenshot 2022-10-14 195905.png
diff --git a/OFA/static/Screenshot 2022-10-14 195905_OcCkF3W.png b/OFA/static/Screenshot 2022-10-14 195905_OcCkF3W.png
diff --git a/OFA/static/face.jpg b/OFA/static/face.jpg
diff --git a/OFA/urls.py b/OFA/urls.py
@@ -4,6 +4,6 @@
 urlpatterns = [
     path('', views.index, name='index'),
     path('About', views.about, name='about'),
-    path('Model', views.model, name='model'),
+    path('Model', views.model, name='model')
 ]
 
diff --git a/OFA/views.py b/OFA/views.py
@@ -14,13 +14,16 @@
 import os
 from datetime import datetime
 
-
+# better accuracy but slower 
 # img_captioning = pipeline(
 #   Tasks.image_captioning, 
-#   model='ofa_image-caption_coco_large_en')
+#   model='OFA/ofa_image-caption_coco_large_en')
+
+# lower accuracy but very fast
 img_captioning = pipeline(
     Tasks.image_captioning, 
     model='damo/ofa_image-caption_coco_distilled_en')
+
 # result = img_captioning({'image': 'https://farm9.staticflickr.com/8044/8145592155_4a3e2e1747_z.jpg'})
 # print(result[OutputKeys.CAPTION]) # 'a bunch of donuts on a wooden board with popsicle sticks'
 
@@ -32,14 +35,20 @@ def index(request):
 def about(request):
     return render(request, 'about.html')
 
-# @csrf_exempt
-# def model(request):
-#     return render(request, 'OFA.html')
 
+caption = "No Caption!"
 @csrf_exempt
 def model(request):
     start_time = datetime.now()
-    if request.method == 'POST':            
+    if request.method == 'POST': 
+
+        # Remove all old images
+        directory = "OFA/static"
+        files_in_directory = os.listdir(directory)
+        for file in files_in_directory:
+            path_to_file = os.path.join(directory, file)
+            os.remove(path_to_file)
+
         # Image Display
         form = OFAImageForm(request.POST, request.FILES)
         if form.is_valid():
@@ -48,10 +57,21 @@ def model(request):
 
             # OFA Image Caption from pre-trained
             result = img_captioning({'image': img_object.image.name})
+            global caption
+            caption = result[OutputKeys.CAPTION][0]
+
+            # Save audio file
+            engine = pyttsx3.init()
+            engine.save_to_file(caption, 'OFA/audio.mp3')
+            engine.runAndWait()
+
+            # timer
             end_time = datetime.now()
             time_lapsed =  end_time - start_time
+
             # format time
             t = str(round(time_lapsed.total_seconds(),1))+'s'
+
             # data will send to frontend
             context = {
                 'form': form, 
@@ -62,10 +82,14 @@ def model(request):
             return render(request, 'OFA.html', context)  
     else:
         form = OFAImageForm()
+
+    # timer
     end_time = datetime.now()
     time_lapsed = end_time - start_time
+
     # format time
     t = str(round(time_lapsed.total_seconds(),1))+'s'
+
     # data will send to frontend
     context = {
         'form' : form,  
@@ -87,4 +111,5 @@ def caption1(request):
         'caption': result[OutputKeys.CAPTION]
     }
     return render(request, 'OFA.html', context)
- """
+ """
+
diff --git a/ReadMe.txt b/ReadMe.txt
@@ -1,6 +1,7 @@
 python -m venv venv
 .\venv\Scripts\activate
 pip install "modelscope[nlp]==0.4.7" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
+pip install git+https://github.com/nateshmbhat/pyttsx3
 pip install -r requirements.txt
 python manage.py makemigrations
 python manage.py migrate

diff --git a/child-in-car-scaled_Soac6UM.jpg b/child-in-car-scaled_Soac6UM.jpg
diff --git a/db.sqlite3 b/db.sqlite3
diff --git a/templates/OFA.html b/templates/OFA.html
@@ -201,7 +201,7 @@
       </nav>
     </div></header>
     <center><h4>OFA (pre-trained)</h4>
-    <div style="width: 100%; overflow: hidden;">
+    <div style="width: 70%; overflow: hidden;">
 
         <form method="POST" action ="Model" enctype="multipart/form-data">
             {% comment %} <p>Please select your OFA model: </p>
@@ -211,7 +211,7 @@
             <label for="OFALarge">Large</label>
             <input type="radio" id="OFATiny" name="OFA" value="OFA_Tiny">
             <label for="OFATiny">Tiny</label><br> {% endcomment %}
-            <div style="width: 50%; float: left;">                  
+            <div style="width: 40%; float: left;">                  
                 {% block content %}       
                 {% csrf_token %}  
                 <br>            
@@ -227,7 +227,7 @@
                         <br>
                         <img id="output" src = " " />  
                         <span>&times;</span>  
-                        <input type="file" name="image" onchange="loadFile(event)" > 
+                        <input type="file" accept="image/*" name="image" onchange="loadFile(event)" > 
                         <br><br>         
                     </div>
                     <br>
@@ -237,13 +237,22 @@
                     </div>                
             </div> 
 
-            <div style="width: 50%; float: right;">              
+            <div style="width: 50%; float: right;">
                 {% if img_obj %}          
                     <img src="{{ img_obj.image.url}}" alt="connect" style="max-height:300px">  
                 {% endif %}  
-                {% endblock content %} 
-                <p><strong>Caption: </strong> {{result}}</p>                    
-                <p><strong>Timing: </strong> {{time_lapsed}}</p>
+                {% endblock content %}  
+                <br>                   
+                <small>processing: {{time_lapsed}}</small> 
+                <br>   
+                <br> 
+                <div>
+                    <audio controls preload="none"> 
+                        <source src="audio.mp3" type="audio/mpeg">
+                        Your browser does not support the audio element.
+                    </audio>
+                    <p><strong>Caption: </strong> {{result}}</p>
+                </div>  
             </div>  
         </form>    
     </div>

diff --git a/templates/about.html b/templates/about.html
@@ -37,10 +37,10 @@
 <body class="u-body u-xl-mode" data-lang="en">
     <header class="u-clearfix u-header u-header" id="sec-164b">
         <div class="u-clearfix u-sheet u-sheet-1">
-            <a href="Home.html" class="u-image u-logo u-image-1" data-image-width="870" data-image-height="870">
+            <a href="{% load static %}" class="u-image u-logo u-image-1" data-image-width="870" data-image-height="870">
                 <img src="images/UOW.png" class="u-logo-image u-logo-image-1">
             </a>
-            <a href="Home.html" class="u-image u-logo u-image-2" data-image-width="200" data-image-height="200">
+            <a href="{% load static %}" class="u-image u-logo u-image-2" data-image-width="200" data-image-height="200">
                 <img src="images/1663124232782.jpg" class="u-logo-image u-logo-image-2">
             </a>
             <nav class="u-menu u-menu-dropdown u-offcanvas u-menu-1">
@@ -63,7 +63,7 @@
                 <div class="u-nav-container">
                     <ul class="u-nav u-unstyled u-nav-1"><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'index' %}" style="padding: 10px 14px;">Home</a>
                     </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'about' %}" style="padding: 10px 14px;">About</a>
-                    </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'model' %}" target="_blank" style="padding: 10px 14px;">Model</a>
+                    </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'model' %}" style="padding: 10px 14px;">Model</a>
                     </li></ul>
                 </div>
                 <div class="u-nav-container-collapse">

diff --git a/templates/index.html b/templates/index.html
@@ -6,7 +6,7 @@
     <meta name="description" content="">
     <title>Home</title>
     <link rel="stylesheet" href="nicepage.css" media="screen">
-<link rel="stylesheet" href="Home.css" media="screen">
+    <link rel="stylesheet" href="Home.css" media="screen">
     <script class="u-script" type="text/javascript" src="jquery.js" defer=""></script>
     <script class="u-script" type="text/javascript" src="nicepage.js" defer=""></script>
     <meta name="generator" content="Nicepage 4.19.3, nicepage.com">
@@ -47,7 +47,7 @@
           <div class="u-nav-container">
             <ul class="u-nav u-unstyled u-nav-1"><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'index' %}" style="padding: 10px 14px;">Home</a>
             </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'about' %}" style="padding: 10px 14px;">About</a>
-            </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'model' %}" target="_blank" style="padding: 10px 14px;">Model</a>
+            </li><li class="u-nav-item"><a class="u-button-style u-nav-link u-text-active-palette-1-base u-text-hover-palette-2-base" href="{% url 'model' %}" style="padding: 10px 14px;">Model</a>
             </li></ul>
           </div>
           <div class="u-nav-container-collapse">
@@ -107,7 +107,7 @@ <h2 class="u-custom-font u-font-montserrat u-text u-text-1">The Majoriy of the p
               <div class="u-align-center u-container-style u-layout-cell u-size-30 u-layout-cell-2">
                 <div class="u-container-layout u-container-layout-2">
                   <h2 class="u-text u-text-default u-text-2"> Our AI-Powered model is capbe to generate comprehensive sentence from image</h2>
-                  <a href="{% url 'model' %}" class="u-btn u-button-style u-hover-black u-palette-1-base u-btn-1" target="_blank">try it now</a>
+                  <a href="{% url 'model' %}" class="u-btn u-button-style u-hover-black u-palette-1-base u-btn-1" >try it now</a>
                 </div>
               </div>
             </div>

diff --git a/templates/test.html b/templates/test.html
@@ -0,0 +1 @@
+{{result}}
diff --git a/text2audio/__pycache__/__init__.cpython-37.pyc b/text2audio/__pycache__/__init__.cpython-37.pyc
diff --git a/text2audio/__pycache__/__init__.cpython-39.pyc b/text2audio/__pycache__/__init__.cpython-39.pyc
diff --git a/text2audio/__pycache__/admin.cpython-37.pyc b/text2audio/__pycache__/admin.cpython-37.pyc
diff --git a/text2audio/__pycache__/admin.cpython-39.pyc b/text2audio/__pycache__/admin.cpython-39.pyc
diff --git a/text2audio/__pycache__/apps.cpython-37.pyc b/text2audio/__pycache__/apps.cpython-37.pyc
diff --git a/text2audio/__pycache__/apps.cpython-39.pyc b/text2audio/__pycache__/apps.cpython-39.pyc
diff --git a/text2audio/__pycache__/forms.cpython-37.pyc b/text2audio/__pycache__/forms.cpython-37.pyc
diff --git a/text2audio/__pycache__/forms.cpython-39.pyc b/text2audio/__pycache__/forms.cpython-39.pyc
diff --git a/text2audio/__pycache__/models.cpython-37.pyc b/text2audio/__pycache__/models.cpython-37.pyc
diff --git a/text2audio/__pycache__/models.cpython-39.pyc b/text2audio/__pycache__/models.cpython-39.pyc
diff --git a/text2audio/__pycache__/urls.cpython-37.pyc b/text2audio/__pycache__/urls.cpython-37.pyc
diff --git a/text2audio/__pycache__/urls.cpython-39.pyc b/text2audio/__pycache__/urls.cpython-39.pyc
diff --git a/text2audio/__pycache__/views.cpython-37.pyc b/text2audio/__pycache__/views.cpython-37.pyc
diff --git a/text2audio/__pycache__/views.cpython-39.pyc b/text2audio/__pycache__/views.cpython-39.pyc
diff --git a/text2audio/migrations/__pycache__/0001_initial.cpython-37.pyc b/text2audio/migrations/__pycache__/0001_initial.cpython-37.pyc
diff --git a/text2audio/migrations/__pycache__/0001_initial.cpython-39.pyc b/text2audio/migrations/__pycache__/0001_initial.cpython-39.pyc
diff --git a/text2audio/migrations/__pycache__/__init__.cpython-37.pyc b/text2audio/migrations/__pycache__/__init__.cpython-37.pyc
diff --git a/text2audio/migrations/__pycache__/__init__.cpython-39.pyc b/text2audio/migrations/__pycache__/__init__.cpython-39.pyc