Attention Unet highlights only relevant activations during training. This can not only perform better when the target you want to detect is relatively tiny compared to the size of the picture, but it can also reduce unnecessary computations. The overall…
If I were to restart a semantic segmentation model project again, I would choose the loss function by considering the following. Is there any imbalance in your data? ⇒（NO）⇒ Binary Cross Entropy ⇓ (YES) ⇓ Is the area you want…
The traditional way to detect cracks inside concretes is to use A) Radar data of the section of the concrete and B) Label Image of the section to train a pix2pix model. But, this methodology struggles to detect depending on…
I did an experiment to compare how model performance change when converted to TensorRT engine. These are the steps I took. 1. Train Several Binary Segmentation Model 2. Randomly Choose 30 images from the dataset 3. Run inference with the…
Argmax compares pixels in the same position across channels, and acquires the index of the highest channel. This can be useful for semantic segmentation. Semantic segmentation models outputs the same width and height as the input image and creates a…
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…