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…
Deciding a metric when evaluating a ML project can be difficult. From an engineer’s perspective, they might want to optimize, word-level accuracy or query-level accuracy. On the other hand, for a businessmen’s perspective, they’d rather focus on revenue and user-engagement.…
Andrew Ng proposed a scoping process for AI projects like the following. Brainstorm Business Problems (Not AI) Asking questions which are NOT AI problems can help you distinguish between the PROBLEM and the SOLUTION. You don’t know whether you should…
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…
Gnu-Screen can help your process keep running even when you disconnect from your gpu. This is useful when you are using ssh to connect to your GPU machine, AND the model training process is taking a LONG time. I mean,…
There are several ways to evaluate your semantic segmentation model, and one way is to calculate the IOU(Intersection Over Union). This is basically calculating how much area is intersecting between the region proposed by the model and the actual region.…
I was finally able to fine-tune a model and get decent results. I’ve used a new dataset from kaggle. This has more and simple images of water surfaces so that helped a lot. Results The model was able to learn…
I trained L-RASPP again to detect cracks with 110 images.The results are the above. Comparing to Deeplabv3(Image Below),trained with the same dataset, you can see there are a lot of noise in the results from the L-RASPP model. > Reference:…
I retrained a L-RASPP(Light-Reduced Astrous Spatial Pyramid Pooling) model to detect water level using Pytorch. I used the WSOC dataset containing 496 images for training and 278 images for testing. The ROC score was close to 1 by epoch 25.…