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.…
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.
I’ve experimented how standardization affect a binary segmentation model’s performance by comparing 2 outputs. Inference result from model trained with standardization using ImageNet RGB mean and standard deviation Inference result from model trained without standardization I’ve found out that the…
When I was evaluating the model, both f1 score and jaccard score, for some reason, was decreasing as the model finishes more epochs. (Which is quite insane.) I’ve been checking the dimensions of the variables I was using to calculate…
When testing out your model’s output for computer vision tasks, you’ll need to apply the same preprocessing methods you’ve applied during training, to the images you want to test out. Here is one way to implement. Import Images from PIL…
Depending on the loss function, you might need to change the data structure of the tensor coming out from the model. In my case, I’m currently doing a binary semantic segmentation using pytorch, and the output of the model is…
I’ve learned that, for semantic segmentation, the Binary Cross Entropy as the loss function, instead of MSE, might be the one to first test out. Motivation When you check the derivative for MSE(Mean Squared Error)’s cost function, you’ll notice that…
Labeling 3d data points manually can be time-consuming and has a high chance of mistaking. So instead of labeling each point like the picture on the left side, using clustering can help you group similar data points first and then…
It’s my first time using, RealSense Depth Camera D435i, and so I’m excited about the potential of this camera! For example, it would make detection tasks much easier because you can literally distinguish between objects by the depth measured from…
Auxiliary Classifier is a classifier head which is not connected to the end of the network. This is helpful to improve convergence during training, because by having an output near the lower-level side of the network, the gradients can be…