Skip to main content

Public

Project privacy set to public. By default, its content is available to everyone (authenticated or not). Please note that more restrictive permissions might exist on some items.

    •  
      Internship #167749 To develop the code, to train the model in pytorch, for instance if we take edge detection as the feature extraction, then you need to add this edge detection as data augmentation technique in tranform =[] list
    Actions
    #167749
    SANKALP PRAJAPATI (sankalp_prajapati)
    2024-06-20 21:34
    2024-06-10 15:57
    Details
    To develop the code, to train the model in pytorch, for instance if we take edge detection as the feature extraction, then you need to add this edge detection as data augmentation technique in tranform =[] list
    Empty
    Empty
    Empty
    State of Progress
    2024-06-11
    Empty
    2024-06-20
    SANKALP PRAJAPATI (sankalp_prajapati)
    Saurabh Kumar Pandey (saurabh)
    Empty
    Closed
    Attachments
    By SANKALP PRAJAPATI (sankalp_prajapati)
    (6 kB)
    model8.py
    Finally corrected model which is combination of Shallow CNN and resnet50
    References
    References list is empty
    Display settings

    Follow-ups

    User avatar
    SANKALP PRAJAPATI (sankalp_prajapati)2024-06-20 21:33

    Used pretrained models viz resnet50 and vgg16 to test the dataset. Modified code to save the output as images and results to be later used to display result. Finally combined Shallow CNN features along with some features of resnet50 to create a combined model.

    User avatar
    SANKALP PRAJAPATI (sankalp_prajapati)2024-06-19 10:23

    1-Trained a model on pytorch based on edge detection as augmentation technique. Trained on a sample of 80 dataset(40 spoof + 40 real). Saved their pth files and predicted a set of images. Refining this model by adding more feature extraction methods.