Bib Racer 03 - Face and Bib Detection with YOLO network

I just made a very simple face and bib detection program following the post by Adrian Rosebrock, with the weights trained with the downloaded trail running images using method described in the previous post. The speed is not very fast, which take more than 1 second for an image. Certainly, it is Google Colab free tier, so there are lots of variables that we cannot control and even do not know.

Bib Racer 02 - Training with RBNR Dataset

In previous post, we talked about how to scrape and download photos using Selenium and BeautifulSoup, from an online photo album of a trail running event. The next step is to identify the bib numbers in the photos automatically. This can be divided into two subtasks, the first one is to identify the location of the bib in an image, and the second one is to recognize bib numbers in the identified bib.

Bib Racer 01 - Scrape Images

I had participated in trail running races for 2 years. All of those races are exciting and unforgettable, with stunning scenic views and different kinds of challenges. During each of the event, there are many enthusiastic photographers, amateur or professional, taking numerous pictures of racers and putting them online for download either freely or with fees. In order to find the photos for a particular racer, one needs to either look for those photos from countless albums each containing more that hundreds of photos one by one and by naked eyes, or some websites can let you input the bib number to and get the photos with the number for you. Course v3 Lesson 7 Notes

Basic CNN with batchnorm Question: How to calculate numbers in the output column Param? It’s shown in the doc but seems doesn’t match. ResNet from scratch A deeper network doesn’t always have better performance, in terms of training error. Deeper network has higher training error. source: Deep Residual Learning for Image Recognition, Kaiming He et al Refernces “Deep Residual Learning for Image Recognition” by Kaiming He et al.

Office 365 subscription problem

Office 365 couldn’t verify subscription Today when I open Microsoft Word, there is a yellow bar under the ribbon telling me that it cannot verify the Office 365 subscription, and asks me to check the internet connection. Microsoft Word prompts it cannot verify the subscription The warning is seen all over the Office 365 products, e.g. Word, Excel, Outlook, etc. Regardless the warning, the Office suite still functions properly, but the warning message is quite annoying. Course v3 Lesson 6 Notes To label unlabelled data for you. Tabular learner Rossmann Store Sales data set When dealing with time series data, most of the time in practice is not using recurrent neural network, which is powerful when the sequence of time point is the ONLY information we have. In real-world cases, when we are given time data, we can generate or look for more information regarding this field, such as hour, date, day of week, week, month, etc. Course v3 Lesson 5 Notes

Back propagation To calculate the loss between output layer/final activations and actual target values. Use the resulting losses to: Calculate the gradients with respect to the parameters and Update the parameters: $\text{parameters} -= \text{learning rate} \cdot \text{gradient of parameters}$. Fine tuning Example: ResNet-34 The final layer, i.e. that final weight matrix, of ResNet-34 has 1000 columns because the images can be in one of 1000 different categories, i. Course v3 Lesson 4 Notes

Sentiment analysis (IMDB) Transfer learning in NLP Difficulties in training NLP model: How to speak a language. World knowledge Start with a pre-trained model: a language model - a model that learns to predict the next word of a sentence. Get benefit from a pre-trained model from a much bigger dataset, e.g. Wikipedia. No preset label is needed: self-supervised learning - Yann LeCun, labels still exist in this kind of classification problem, but not created by human, instead, are built into the data set. Course v3 Lesson 3 Notes

Multi-label prediction with Planet Amazon dataset The data block API Classes involved: Dataset: an abstract class for retrieving an item by index and return the length of the Dataset. DataLoader: get data from Dataset and feed the data batches to processors. DataBunch: bind the DataLoaders of training dataset, validation dataset and optionally a test dataset, and is ready to be sent to the learner. General steps using the data block API to create a DataBunch: Course v3 Lesson 2 Notes

General notes regarding previous lesson No need to feel intimidated for all the good projects in lesson 1. Just open your imagination and start an interesting project! Keep going: code and experiment –> “The whole game” –> concepts –> lesson 2 Creating your own dataset from Google Images Download images After opened image search result page, run the following javascript code in javascript console, by pressing Ctrl+Shift+J in Windows/Linux or Cmd+Opt+J in Mac.