Steven (Szu-Han) Chen

I have implemented the adapter design pattern for generating and saving json reports instead of CSV without breaking the API. This allows flexibility to create different types of reports like...

I have implemented the factory design pattern for generating and saving reports in data_prep.py. This allows flexibility to create different types of reports like log, trend and agg data.

Applied aggregate pattern to data prep to generate and save log report

Summary - Applied new aggregate classes to the data_prep module to help encapsulate domain objects like cases, countries and reports List of changes - Created a new aggregate module consisting...

Training code for dlib face recognition resnet model

2

Is there a training code or example available for the model dlib_face_recognition_resnet_model_v1 from https://github.com/davisking/dlib-models? Also curious if there are any document on what the ResNet architecture look like and etc....

Could not connect to RPi

13

When I try running python3 cluster.py initialize, I get "Could not connect to {'address': 'pi@..., 'notes': 'Test', 'wlan': 'wlan0'}" Any way to debug this? Thank you.

Where in the code is the program scanning for access points and signal strengths

1

Can someone kindly point me to it?

PSNR calculation

4

Hi, How come you are calculating PSNR between the bicubic image and predicted image? Shouldn't it be the PSNR between ground truth and predicted?

Training parameters

1

Hi, 1. Why did you do zero-padding? 2. Why use Adam instead of the SGD? How come you didn't just use SG like the paper? 3. Why remove the weights...

Different PSNR values from the paper

10

After training and testing it, I'm getting a different PSNR value which is lower than the one reported from the original paper. Is anyone able to replicate the same PSNR?