I found out why my TensorRT engine model was not working as expected. I messed up with configuring the preprocessing step for Deepstream. When you use Deepstream to run inference, there is a property called net-scale-factor and offsets which you…
I’ve compared the performance between the model before and after converting to TensorRT engine. The output from the TensorRT engine is flattened to a 1d array, so I had to convert that back to a 2d array to display the…
A semantic segmentation model outputs a tensor shaped [Batch_size,Channel(Number of Classes),Img_Height,Img_Width] (If using Pytorch), but if you convert that to a TensorRT engine for faster inference, the output is flattened to a 1d array. Therefore the shaping being, [(Batch_size)X(Channel)X(Img_Height)X(Img_Width),] Considering…
Unet++ is useful when you want to improve image segmentation accuracy. This was first designed for medical use where accuracies are critical. In a nutshell, Unet++ adds convolution layers between skip connection. The original Unet skip connect without any additional…
This is how an AI learns how to classify my dog. I’ve found a blog post visualizing the feature maps of a classification model, so I tried it out! I’m going to use Resnet18 and visualize the feature maps for…
I’ve quantitatively evaluated binary segmentation models using IOU as my metric. The reason why I used IoU is because IoU penalizes a single instance of classification error more compared to other metrics such as f1 scores, therefore lowering the value.…
Pre-fetching your data can help your data pre-processing pipeline more smoother. Without pre-fetching, the cpu would wait for the process in the GPU to end, and then start to prepare the next data. You can do this process in parallel…
I’ve compared Image segmentation performance depending on the loss function. Mean Squared Error Binary Cross Entropy I was able to achieve higher average IOU using BCE instead of MSE.
Labeling Data is time-consuming and boring. Active Machine Learning may help reduce that labeling process down to 10~20%. Fig.1 – Active Learning Workflow The basic workflow is as follows: 1. Label Data Partially 2. Train Model only with the labeled…
Jacobian Matrix is a matrix which stores all the partial derivatives for multiple functions. For example, let’s consider ex1 (top left). F(x) is a function containing 1 variable. If you calculate the derivative of F(x) it would be 2x. Now,…