Adarsh Ghimire

Not getting real time performance on face detection

1

I am using open-cv to read the camera feed and passing to `facenet-pytorch mtcnn` module for face detection. The bottleneck I see is in the `mtcnn.detect()` which takes `0.08 to...

Toolkit usage on custom dataset

1

I want to generate Precision, Recall, and F-Score measures on my custom dataset. Looking for suggestions and help on how to generate those curves for custom dataset.

5.14 Training Convnet with data-augmentation generators

2

Why the `batchsize = 32`, should it not be 20? Since the `steps_per_epoch = 100` and there is issue when using the generator in this way, since the `batchsize` is...

I tried running the code in CPU and GPU from parameter setting. However, I am getting the same `11 FPS` on both devices. `CPU = Intel i7, 11th Gen` and...

How about adding meta phone scoring as well to match the strings. Since, same strings can be written in different way, for example, "Mira" and "Meera" should have similar score,...