m7mdal7aj commited on
Commit
e924776
β€’
1 Parent(s): a4babd7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -12,12 +12,13 @@ license: apache-2.0
12
 
13
 
14
 
 
15
 
16
  ## Project File Structure
17
 
18
  ```
19
  KB-VQA
20
- β”œβ”€β”€ Files: Various files required for the demo such as samples images,..etc.
21
  β”œβ”€β”€ models
22
  | β”œβ”€β”€ deformable-detr-detic: DETIC Object Detection Model.
23
  | β”œβ”€β”€ yolov5: YOLOv5 Object Detection Model.baseline)
@@ -34,20 +35,20 @@ KB-VQA
34
  β”‚ β”‚ β”œβ”€β”€ fine_tuner.py: Main Fine-Tuning Script for LLaMa-2 Chat models.
35
  β”‚ β”‚ β”œβ”€β”€ fine_tuning_data_handler.py: Handles and prepares the data for fine-tuning LLaMA-2 Chat models.
36
  β”‚ β”‚ β”œβ”€β”€ fine_tuning_data
37
- β”‚ β”‚ β”‚ β”œβ”€β”€fine_tuning_data_detic.csv: Fine-tuning data prepared by the prompt engineering module using DETIC detector.
38
- β”‚ β”‚ β”‚ β”œβ”€β”€fine_tuning_data_yolov5.csv: Fine-tuning data prepared by the prompt engineering module using YOLOv5. detector.
39
  | β”œβ”€β”€ results
40
- β”‚ β”‚ β”œβ”€β”€ Demo_Images: Contains a pool of images used for the demo app.
41
  β”‚ β”‚ β”œβ”€β”€ evaluation.py: Provides a comprehensive framework for evaluating the KB-VQA model.
42
  β”‚ β”‚ β”œβ”€β”€ demo.py: Provides a comprehensive framework for visualizing and demonstrating the results of the KB-VQA evaluation.
43
  β”‚ β”‚ β”œβ”€β”€ evaluation_results.xlsx : This file contains all the evaluation results based on the evaluation data.
44
  | β”œβ”€β”€ tabs
45
- β”‚ β”‚ β”œβ”€β”€ home.py: Displays an introduction to the application with brief background along with the demo tools decription.
46
  β”‚ β”‚ β”œβ”€β”€ results.py: Manages the interactive Streamlit demo for visualizing model evaluation results and analysis.
47
- β”‚ β”‚ β”œβ”€β”€ run_inference.py: Responsible for the 'run inference' tool to test and use the fine-tuned models.
48
  β”‚ β”‚ β”œβ”€β”€ model_arch.py: Displays the model architecture and accompanying abstract and design details
49
  β”‚ β”‚ β”œβ”€β”€ dataset_analysis.py: Provides tools for visualizing dataset analyses.
50
- | β”œβ”€β”€ utilities
51
  β”‚ β”‚ β”œβ”€β”€ ui_manager.py: Manages the user interface for the Streamlit application, handling the creation and navigation of various tabs.
52
  β”‚ β”‚ β”œβ”€β”€ gen_utilities.py: Provides a collection of utility functions and classes commonly used across various parts
53
  | β”œβ”€β”€ config (All Configurations files are kept separated and stored as ".py" for easy reading - this will change after the project submission.)
@@ -61,4 +62,5 @@ KB-VQA
61
  β”œβ”€β”€ app.py: main entry point for streamlit - first page in the streamlit app)
62
  β”œβ”€β”€ README.md (readme - this file)
63
  β”œβ”€β”€ requirements.txt: Requirements file for the whole project that includes all the requirements for running the demo app on the HuggingFace space environment.
64
- ```
 
 
12
 
13
 
14
 
15
+ """
16
 
17
  ## Project File Structure
18
 
19
  ```
20
  KB-VQA
21
+ β”œβ”€β”€ Files: Various files required for the demo such as samples images, dissertation report ..etc.
22
  β”œβ”€β”€ models
23
  | β”œβ”€β”€ deformable-detr-detic: DETIC Object Detection Model.
24
  | β”œβ”€β”€ yolov5: YOLOv5 Object Detection Model.baseline)
 
35
  β”‚ β”‚ β”œβ”€β”€ fine_tuner.py: Main Fine-Tuning Script for LLaMa-2 Chat models.
36
  β”‚ β”‚ β”œβ”€β”€ fine_tuning_data_handler.py: Handles and prepares the data for fine-tuning LLaMA-2 Chat models.
37
  β”‚ β”‚ β”œβ”€β”€ fine_tuning_data
38
+ β”‚ β”‚ β”‚ β”œβ”€β”€fine_tuning_data_detic.csv: Fine-tuning data prepared by the prompt engineering module using DETIC detector.
39
+ β”‚ β”‚ β”‚ β”œβ”€β”€fine_tuning_data_yolov5.csv: Fine-tuning data prepared by the prompt engineering module using YOLOv5. detector.
40
  | β”œβ”€β”€ results
41
+ β”‚ β”‚ β”œβ”€β”€ Demo_Images: Contains a pool of images used for the demo app.
42
  β”‚ β”‚ β”œβ”€β”€ evaluation.py: Provides a comprehensive framework for evaluating the KB-VQA model.
43
  β”‚ β”‚ β”œβ”€β”€ demo.py: Provides a comprehensive framework for visualizing and demonstrating the results of the KB-VQA evaluation.
44
  β”‚ β”‚ β”œβ”€β”€ evaluation_results.xlsx : This file contains all the evaluation results based on the evaluation data.
45
  | β”œβ”€β”€ tabs
46
+ β”‚ β”‚ β”œβ”€β”€ home.py: Displays an introduction to the application with brief background along with the demo tools description.
47
  β”‚ β”‚ β”œβ”€β”€ results.py: Manages the interactive Streamlit demo for visualizing model evaluation results and analysis.
48
+ β”‚ β”‚ β”œβ”€β”€ run_inference.py: Responsible for the 'run inference' tool to test and use the fine-tuned models.
49
  β”‚ β”‚ β”œβ”€β”€ model_arch.py: Displays the model architecture and accompanying abstract and design details
50
  β”‚ β”‚ β”œβ”€β”€ dataset_analysis.py: Provides tools for visualizing dataset analyses.
51
+ | β”œβ”€β”€ utilities
52
  β”‚ β”‚ β”œβ”€β”€ ui_manager.py: Manages the user interface for the Streamlit application, handling the creation and navigation of various tabs.
53
  β”‚ β”‚ β”œβ”€β”€ gen_utilities.py: Provides a collection of utility functions and classes commonly used across various parts
54
  | β”œβ”€β”€ config (All Configurations files are kept separated and stored as ".py" for easy reading - this will change after the project submission.)
 
62
  β”œβ”€β”€ app.py: main entry point for streamlit - first page in the streamlit app)
63
  β”œβ”€β”€ README.md (readme - this file)
64
  β”œβ”€β”€ requirements.txt: Requirements file for the whole project that includes all the requirements for running the demo app on the HuggingFace space environment.
65
+ ```
66
+ """