AbdullahImran commited on
Commit
7c23455
·
verified ·
1 Parent(s): e7178fc

Add fire detection model card

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras
3
+ pipeline_tag: image-classification
4
+ tags:
5
+ - keras
6
+ - tensorflow
7
+ - computer-vision
8
+ - image-classification
9
+ - fire-detection
10
+ - wildfire-detection
11
+ - binary-classification
12
+ - transfer-learning
13
+ ---
14
+
15
+ # Fire Detection Models
16
+
17
+ A collection of trained deep learning models for binary fire detection.
18
+
19
+ These models classify an input image into one of two classes:
20
+
21
+ - **Fire**
22
+ - **No Fire**
23
+
24
+ The repository contains multiple CNN architectures trained as part of a broader deep learning project focused on fire detection and wildfire-related computer vision.
25
+
26
+ ## Models
27
+
28
+ | Model | Architecture | Task |
29
+ |---|---|---|
30
+ | `Custom_CNN_binary_classification.keras` | Custom CNN | Fire / No Fire |
31
+ | `efficientnetb0_binary_classification.keras` | EfficientNetB0 | Fire / No Fire |
32
+ | `resnet50_binary_classification.keras` | ResNet50 | Fire / No Fire |
33
+ | `vgg16_binary_classification_finalized.keras` | VGG16 | Fire / No Fire |
34
+
35
+ ## Model Format
36
+
37
+ All models are saved using the Keras `.keras` format.
38
+
39
+ ```python
40
+ import tensorflow as tf
41
+
42
+ model = tf.keras.models.load_model(
43
+ "efficientnetb0_binary_classification.keras"
44
+ )
45
+
46
+ model.summary()
47
+ ```
48
+
49
+ Replace the filename with the model you want to load.
50
+
51
+ ## Intended Use
52
+
53
+ These models are intended for:
54
+
55
+ - research
56
+ - experimentation
57
+ - educational purposes
58
+ - model comparison
59
+ - further fine-tuning
60
+ - development of fire-detection applications
61
+
62
+ ## Limitations
63
+
64
+ Model performance depends on the dataset, preprocessing pipeline, image quality, and deployment environment.
65
+
66
+ The models should be independently evaluated on an appropriate test dataset before being used in real-world or safety-critical applications.
67
+
68
+ ## Project Context
69
+
70
+ These models are part of a larger deep learning project containing:
71
+
72
+ - fire detection
73
+ - fire severity classification
74
+ - feature extraction
75
+ - dimensionality reduction
76
+ - clustering
77
+ - recommendation generation
78
+ - supporting datasets and notebooks
79
+
80
+ ## License
81
+
82
+ No standardized open-source license has been specified for this repository.
83
+
84
+ Please refer to the original project and dataset terms before redistribution or commercial use.