### Kaggle

To Download datasets from Kaggle you can use the: kaggle-cli You can install it with pip: pip install kaggle-cli or to upgrade it using: pip install kaggle-cli –upgrade The only problem with it is that it will download all of the dataset files, which can be huge (more than 20 GBs). Another way to do…

### This is what I have learned during my first 2 days of 100 days of Machine Learning Code

The #100DaysOfMLCode is a challenge in which you spend at least 1 hour a day learning about Machine Learning and you publish what you have been learning to keep yourself accountable during that time. During my first week of #100DaysOfMLCode I’ve been working on two different courses in no particular order. Here is the list…

### YOLO (You Only Look Once)

YOLO (You Only Look Once) It is a real time object detection algorithm which prioritizes speed and recognition. YOLO will output the probabilities of the classes as well as the bounding box parameters (x,y,w,h) where x and y determines the coordinates of the center of the box and w and h are the width…

### Train set, Cross Validation set (Dev set) and Test set

Train set, Cross Validation set (Dev set) and Test set You want to have 3 different sets: Train set: data used to train your network Cross Validation set: used to test algorithms while deciding on the architecture of the network Test set: this is the secret set, and the network should never see this data…

### Basic recipe for ML

Basic recipe for ML Does the model have high bias? (training data performance) Try a bigger network, train longer (more epochs), try a different NN architecture, keep doing it until the training data fits well. Does the model have High Variance? (Dev Set performance) Add more data, data augmentation, try regularization, NN architecture. For High…

### Bias and Variance

When looking at the train set error and comparing to the cross validation error we could have the following situations:Train set error: 1% (the model is doing very well) Cross Val error: 11%There is a big variance in error between the training set and cross val. set, this is an example of High Variance, and…

### Regularization

Regularization Lamda is the regularization parameter We can use L2 regularization which is also refered as Weight Decay Regularization will help prevent overfitting \lambda

### Jobs in Computer Vision

How can I get a job in Computer Vision industry? Work on your own Computer vision projects, the best way to show your expertise is by showing what you have done rather that trying to convince others by talking about how much you know. So create something and share it with the world, post code…