Upload 6 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Examples/WhatsApp[[:space:]]Video[[:space:]]2025-06-03[[:space:]]at[[:space:]]21.40.27_ab5a54b6.mp4 filter=lfs diff=lfs merge=lfs -text
+Examples/WhatsApp[[:space:]]Video[[:space:]]2025-06-04[[:space:]]at[[:space:]]21.35.45_a5842999.mp4 filter=lfs diff=lfs merge=lfs -text

Examples/WhatsApp Video 2025-06-03 at 21.40.27_ab5a54b6.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b18a80d642e9a6ebdfe25cab81c7804301dd0a849b9f377cd287f5b47592d80
+size 1778559

Examples/WhatsApp Video 2025-06-04 at 21.35.45_a5842999.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a5ff02a2e8336c4b1cee2c31ab3063fc0557942245c03398083cdd3dcc9643
+size 1607622

app.py

@@ -0,0 +1,57 @@
+import torch
+import torchvision
+from torchvision import transforms
+import gradio as gr
+import os
+import cv2
+from PIL import Image
+from model import create_model
+model,transform=create_model(num_of classes=3)
+model.eval()
+def classify_video(video):
+    cap = cv2.VideoCapture(video)
+    predictions = []
+    Fire=[]
+    Smoke=[]
+    Default=[]
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+        img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        img_pil = Image.fromarray(img)
+        img_tensor = transform(img_pil).unsqueeze(0)
+        with torch.no_grad():
+            output = model(img_tensor)
+            pred = output.argmax().item()
+            predictions.append(pred)
+    cap.release()
+    class_names=['DEFAULT', 'FIRE', 'SMOKE']
+    for i in predictions:
+        if i == 1:
+            Fire.append(i)
+        elif i == 2:
+            Smoke.append(i)
+        else:
+            Default.append(i)
+    if Fire!=[] and Smoke!=[]:
+        return f"Spotted {class_names[1]} and {class_names[2]}"
+    elif Fire!=[]:
+        return f"Spotted {class_names[1]}"
+    elif Smoke!=[]:
+        return f"Spotted {class_names[2]}"
+    else:
+        return f"Spotted {class_names[0]}"
+Description="An MobileNET model trained to classify Fire and Smoke through Videos"
+Article="Created at jupyter NoteBook with GPU NVIDIA_GeForce_MX350"
+example_list=[["Examples/"+ example] for example in os.listdir("Examples")if example.endswith((".mp4", ".avi", ".mov"))]
+gr.Interface(
+    fn=classify_video,
+    inputs=gr.Video(streaming=True),
+    outputs="text",
+    title="Fire and Smoke Classifier",
+    examples=example_list,
+    description=description,
+    article=article,
+    live="True"
+).launch()

fire_smoke_weight.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7e9918c5dfaf3f7a790f0923c3cf59b42403571628641bad04b75f7fef8bde
+size 22153066

model.py

@@ -0,0 +1,16 @@
+import torchvision
+import torch
+from torchvision import transforms
+from torch import nn
+def create_model(num_of_classes:int=3):
+    weights=torchvision.models.MobileNet_V3_Large_Weights.DEFAULT
+    transform=weights.transforms()
+    model=torchvision.models.mobilenet_v3_large(weights=weights)
+    for parameter in model.parameters():
+        parameter.requires_grad=False
+    for parameter in model.classifier[-4:].parameters():
+        parameter.requires_grad=True
+    for parameter in model.features[-6:].parameters():
+        parameter.requires_grad=True
+    model.classifier[3]=nn.Sequential(nn.Linear(1280,1000),nn.ReLU(),nn.Dropout(p=0.3),nn.Linear(1000,num_of_classes))
+    return model,transform

requirements.txt

@@ -0,0 +1,5 @@
+torch==2.5.1
+torchvision==0.20.1
+gradio==5.29.1
+cv==4.11.0
+Pillow==10.2.0