Hacker News Reader

Comment by spiderfarmer | Hacker News Reader

Question: I have a database with 1.000.000 vehicle pictures, organized by make and model. What would be the easiest way to play with this data, so that I can train it to predict the make / model? I don't want to reinvent the wheel now so much tutorials are written and software is being released. What would be the easiest way to start?

View on HN

Oh, if you don't want to get into the nitty gritty of it, you should use Digits (https://github.com/NVIDIA/DIGITS).

This is the easiest way to setup a CNN and train it with your sample images (at least compared to Caffe, Tensorflow, and Theano). I say that because it's all GUI based! Real convenient.

Wow that is cool! What if I wanted to make a model to detect cats? Can I just load a bunch of pictures from the web? Do I need negative examples?

Good question. Detecting just one class (in this case, cats) will require negative examples. Finding good negatives is somewhat of challenging task because they should be pretty comprehensive, but if you create an account on image-net (http://image-net.org/), then you can download thousands of images.

Any questions, feel free to pm me.

Will check it out, thanks!

With that number you can train a model from scratch. Alternatively, you can retrain the last layers (it requires much less data).

The easiest way is to use some well-known architecture (e.g. VGG16) and go. See: https://github.com/leriomaggio/deep-learning-keras-euroscipy...

do you have any examples of scripts/examples where only specific layers of a network are being trained?

As I said in another thread, I used that (https://www.tensorflow.org/versions/r0.9/how_tos/image_retra...) which seems to work well. I think especially with your problem since it is similar to the type of classification of ImageNet.

OT, I'm interested in this field as well. Are all these pictures USA cars or international?

Do you mind disclose where you got them?

Thanks!

It's not cars, but mostly tractors. I have been running an online community for almost 10 years now and the images have been submitted and organized by the members.

Reply on news.ycombinator.com