pankaja0285/era_v1_session11_pankaja

Purpose: Use Residual block and create a CNN model for training on CiFAR 10 dataset.

Based on CiFAR 10 dataset

Basic structure for the model:-

• convolution layer - 1
• Layer1 -
  X = Conv 3x3 (s1, p1) >> MaxPool2D >> BN >> RELU
  R1 = ResBlock( (Conv-BN-ReLU-Conv-BN-ReLU))(X)
  
• Add(X, R1)
• Layer 2 - Conv 3x3
  MaxPooling2D
  BN
  ReLU
  
• Layer 3 - X = Conv 3x3 (s1, p1) >> MaxPool2D >> BN >> RELU
  R2 = ResBlock( (Conv-BN-ReLU-Conv-BN-ReLU))(X)
  Add(X, R2)
  MaxPooling with Kernel Size 4
  
• Layer 4 - X = Conv 3x3 (s1, p1) >> MaxPool2D >> BN >> RELU
  R2 = ResBlock( (Conv-BN-ReLU-Conv-BN-ReLU))(X)
  Add(X, R2)
  MaxPooling with Kernel Size 4
  
• FC Layer
• SoftMax Uses One Cycle Policy such that:
  

Uses this transform -RandomCrop 32, 32 (after padding of 4) >> FlipLR >> Followed by CutOut(16, 16)
Batch size = 512
Use SGD, and CrossEntropyLoss

Project Setup:

Clone the project as shown below:-

$ git clone [email protected]:pankaja0285/era_v1_session11_pankaja.git
$ cd era_v1_session11_pankaja

About the file structure
|__config __config.yaml
|__data |__data_analysis |__data_loader __load_data.py
__albumentation.py
|__models __resnet.py
|__utils
__engine.py
__gradcam_viz.py
__helper.py
__plot_metrics.py
__test.py
__train.py
|__CiFAR_S10.ipynb
|__README.md

NOTE: List of libraries required: torch and torchsummary, tqdm for progress bar, which are installed using requirements.txt

One of 2 ways to run any of the notebooks, for instance Submission_CiFAR_S11_GradCam.ipynb notebook:

1. Using Anaconda prompt - Run as an administrator start jupyter notebook from the folder era_v1_session11_pankaja and run it off of your localhost
   NOTE: Without Admin privileges, the installs will not be correct and further import libraries will fail.
   

jupyter notebook

2. Upload the notebook folder era_v1_session11_pankaja to google colab at colab.google.com and run it on colab
   

In Submission_CiFAR_S11_GradCam.ipynb - Use case With RandomCrop ONLY:

File used: models/resnet.py **

Target: - Resnet18 model with grad-CAM applied and with RandomCrop

Results:

• Total parameters: 11,173,962
• Train accuracy of 91.05 and test accuracy of 89.17

Analysis:

• To see how the grad-cam - heat map of the presence of the object

In Submission_CiFAR_S11_GradCam.ipynb - With Cutout applied via Albumentations:

File used: models/resnet.py **

Target: - Resnet18 model with grad-CAM applied and with RandomCrop and cutout applied via Albumentations

Results:

• Total parameters: 11,173,962
• Train accuracy of 84.52 and test accuracy of 88.66

Analysis:

• To see how the grad-cam visualizes in the 4th layer - basically a heat map for the presence of the object

Contributing:

For any questions, bug(even typos) and/or features requests do not hesitate to contact me or open an issue!