I am currently working on a project, which needs some backpack images and information. After spending some time googling, I found a handy tool called Scrapy--a python module which helps me crawl Amazon.com easily and neatly. In this post, I want to write down how I implemented this. Since I am a newbie in Scrapy, … Continue reading How to use Scrapy to scrape Amazon.com and save to sqlite
I've been playing with fast-rcnn for a while. This amazing and wonderful project helps me understand more about deep learning and its beautiful power. However, there's only a pre-trained fast rcnn model for pascal voc with 20 classes. To use this project in real applications, I need to train a model on the ImageNet detection … Continue reading How to train fast rcnn on imagenet
In my latest project, I created a Django website and use it to process long tasks for users, a problem is that the process time is loooong and we need a progress bar so that the users won't think the website is dead or so. After some googling, I found [Celery](http://www.celeryproject.org), which is an asynchronous task queue/job queue based on distributed message passing. Thus, I was able to achieve these functionalities for my website:
Recently, by hacking on Assignment2 of the awesome open class [cs231n](http://vision.stanford.edu/teaching/cs231n/syllabus.html), I finally stop bumping my head to the wall every time I came across backpropagation, now I even feel a little bit enjoy when hacking the backpropagation process! In this post, I will show how to use computation graph to implement both forward and backward process of Batch Normalization, Convolution and Pooling.
I have been bumping my head to the wall for days to implement this function. From GitHub to StackOverFlow, finally, it worked like a charm. So I decided to keep a note in case it might be helpful to others.