mirror of
https://github.com/frankwxu/AI4DigitalForensics.git
synced 2026-02-20 13:40:40 +00:00
add lab word embedding
This commit is contained in:
@@ -35,7 +35,9 @@ https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/
|
||||
|
||||
- Lab 2: [Gun detection](https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/lab02_Gun_detection_fasterRCNN/gun_detection_fasterRCNN.ipynb)
|
||||
|
||||
- Lab 3: [Retrieval-Augmented Generation](https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/lab3_RAG//Retrieval_Augmented_Generation_Simple.ipynb)
|
||||
- Lab 3: [Retrieval-Augmented Generation](https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/lab3_RAG/Retrieval_Augmented_Generation_Simple.ipynb)
|
||||
|
||||
- Lab 4: [Word Embedding in Digital Forensics](https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/lab04_word_embedding/Word_Embeddings_in_DF.ipynb)
|
||||
|
||||
- Lab 10: [Reinforcement Learning](https://colab.research.google.com/github/frankwxu/AI4DigitalForensics/blob/main/lab10_Reinforcement_Learning/dqn_lunar_lander_demo.ipynb)
|
||||
|
||||
|
||||
@@ -61,7 +61,7 @@ An example training image with annotations
|
||||
|
||||
## R-CNN and Fast R-CNN Algorithm
|
||||
|
||||
- The R-CNN (Region-based Convolutional Neural Network) algorithm is a foundational object detection technique in computer vision. You MUST watch [R-CNN Tutorial](https://www.youtube.com/watch?v=nJzQDpppFj) first
|
||||
- The R-CNN (Region-based Convolutional Neural Network) algorithm is a foundational object detection technique in computer vision. You MUST watch [R-CNN Tutorial](https://www.youtube.com/watch?v=nJzQDpppFj0) first
|
||||
|
||||
- [Fast R-CNN](https://www.youtube.com/watch?v=5gAq6BZ87aA&t=1454s) is an object detection algorithm that significantly improved upon the original R-CNN (Region-based Convolutional Neural Network) by addressing its speed limitations. Fast R-CNN processes the entire input image through the CNN only once This significantly reduces redundant computations.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user