recodehive · sanjay-kv · Oct 8, 2024 · Oct 8, 2024
diff --git a/Algorithms and Deep Learning Models/Tiger Identification Project/Dataset/README.md b/Algorithms and Deep Learning Models/Tiger Identification Project/Dataset/README.md
@@ -0,0 +1,7 @@
+## Dataset 
+Dataset link : https://www.kaggle.com/datasets/quadeer15sh/amur-tiger-reidentification?select=Amur+Tigers
+
+### Description 
+The Amur tiger population is concentrated in the Far East, particularly the Russian Far East and Northeast China. The remaining wild population is estimated to be 600 individuals, so conservation is of crucial importance. Re-identification of a species plays an important role in the conservation of wild life. With the help of WWF, a third-party company (MakerCollider) collected more than 8,000 Amur tiger video clips of 92 individuals from ~10 zoos in China. We organize efforts to make bounding-box, keypoint-based pose, and identity annotations for sampled video frames and formuate the ATRW (Amur Tiger Re-identification in the Wild) dataset. Figure 1 illustrates some example bounding box and pose keypoint annotations in our ATRW dataset. Our dataset is the largest wildlife re-ID dataset to date, Table 1 lists a comparison of current wildlife re-ID datasets. The dataset will be divided into training, validation, and testing subsets. The training/validation subsets along with annotations will be released to public, with the annotations for the test subset withheld by the organizers. The dataset paper is released on Arxiv: 1906.05586.
+
+Dataset contains cropped images with manual annotaetd ID and keypoints. Similar to most existing Re-ID tasks, the plain Re-ID task requires to build models on training-set, and evaluating on the test-set. During testing, each image will be taken as query image, while all the remained images in the test-set as "gallery" or "database", the query results should be rank-list of images in "gallery".
diff --git a/...d Deep Learning Models/Tiger Identification Project/Images/DenseNet_results.png b/...d Deep Learning Models/Tiger Identification Project/Images/DenseNet_results.png
diff --git a/... Learning Models/Tiger Identification Project/Images/EfficientNetB3_results.png b/... Learning Models/Tiger Identification Project/Images/EfficientNetB3_results.png
diff --git a/...d Deep Learning Models/Tiger Identification Project/Images/ResNet50_results.png b/...d Deep Learning Models/Tiger Identification Project/Images/ResNet50_results.png
diff --git a/... and Deep Learning Models/Tiger Identification Project/Images/VGG16_results.png b/... and Deep Learning Models/Tiger Identification Project/Images/VGG16_results.png
diff --git a/...p Learning Models/Tiger Identification Project/Model/Tiger_re-indentification_VGG16.ipynb b/...p Learning Models/Tiger Identification Project/Model/Tiger_re-indentification_VGG16.ipynb
diff --git a/...earning Models/Tiger Identification Project/Model/Tiger_re_indentification_DenseNet.ipynb b/...earning Models/Tiger Identification Project/Model/Tiger_re_indentification_DenseNet.ipynb
diff --git a/...g Models/Tiger Identification Project/Model/Tiger_re_indentification_EfficientNetB3.ipynb b/...g Models/Tiger Identification Project/Model/Tiger_re_indentification_EfficientNetB3.ipynb
diff --git a/...earning Models/Tiger Identification Project/Model/Tiger_re_indentification_Resnet50.ipynb b/...earning Models/Tiger Identification Project/Model/Tiger_re_indentification_Resnet50.ipynb
diff --git a/Algorithms and Deep Learning Models/Tiger Identification Project/Model/readme.md b/Algorithms and Deep Learning Models/Tiger Identification Project/Model/readme.md
@@ -0,0 +1,15 @@
+## Model Architectures
+The following deep learning architectures were implemented and evaluated for the tiger Re-ID task:
+
+1) DenseNet: Known for its dense connections between layers, which enhance feature propagation and reduce vanishing gradients.
+2) VGG16: A deep convolutional neural network with 16 layers, known for its simplicity and effectiveness in image classification tasks.
+3) ResNet50: A 50-layer deep network utilizing residual connections to facilitate training of deeper networks by addressing the vanishing gradient problem.
+4) EfficientNet: A family of models that scale up both the depth and width of networks while balancing the input resolution, providing state-of-the-art performance with fewer parameters.
+
+### Prerequisites
+- Python 3.7+
+- TensorFlow 2.x
+- Keras
+- NumPy
+- OpenCV
+- Matplotlib