227
edits
Changes
Jump to navigation
Jump to search
'''5/1/2019'''
*Research on how to feed Mixed data: categorical + images to our model
**https://www.pyimagesearch.com/2019/02/04/keras-multiple-inputs-and-mixed-data/
*Object detection using CNN
**https://gluon.mxnet.io/chapter08_computer-vision/object-detection.html
Listing Page Classifier Progress (view source)
Revision as of 19:37, 17 May 2019
, 19:37, 17 May 2019→Progress Log
***TensorFlow: Flexibility, Contains several ready-to-use ML models and ready-to-run application packages, Scalability with hardware and software, Large online community, Supports only NVIDIA GPUs, A slightly steep learning curve
*Initiate the idea of data preprocessing: create proper input dataset for the CNN model
'''5/2/2019'''
'''5/13/2019'''
*Set up initial CNN model using Keras
**issue: Keras freezes on last batch of first epoch, make sure the following: steps_per_epoch = number of train samples//batch_size validation_steps = number of validation samples//batch_size
'''5/14/2019'''
*implement generate_dataset.py and sitmap tool
**regenerate dataset using updated data and tool
'''5/16/2019'''
*implementation on CNN
*Some problems to consider:
**some websites have more than 1 cohort page: a list of cohorts for each year
**class label is highly imbalanced:
https://towardsdatascience.com/deep-learning-unbalanced-training-data-solve-it-like-this-6c528e9efea6
'''5/17/2019'''
*have to go back with the old plan of separating image data :(
*documentation on wiki
*test run on the GPU server
