Can I train 2 distinct NNs on 2 distinct GPUs simultaneously? - machine-learning

I never had 2 GPUs, but I am going have 2 on one PC soon.
Sometimes I would like to train a model using both cards, to train as fast as possible. However I imagine a situation, where I will want to train two distinct models simultaneously.
Will it be possible using frameworks like Tensorflow or PyTorch?

You can use very simple method. Start two distinct python scripts one with first model and one with second. In TensorFlow you can explicitly specify device by using with tf.device('/gpu:0'):, with tf.device('/gpu:1'): etc. For more information look at documentation TensorFlow Using GPUs.

Related

Cascading two Machine Learning models

I built a machine learning (ML) model to classify real-time network traffic as an attack or normal traffic using a dataset consisting of approximately 3 million records.
Then, I built a second ML model to classify the real-time network traffic according to their application, i.e., Google, Facebook, YouTube, etc. using another dataset consisting of approximately 1.5 million records.
Now I want to cascade these two models so that if the traffic is normal, then the traffic should be classified by the second ML model. Otherwise, it should be discarded since there is no need to pass through the second model.
Can I cascade these two models even though they are built using different datasets? And if so, how can I do that?
I do the cascading logic simply in a programming language code C++ or Python, not using ML-tool features. If the data from the second model, doesn't contribute to the decision of the first model - just keep the models separated.

Azure ML - Train a model on segments of the data-set

I could really use some help!
The company I work for is made up of 52 very different businesses so I can't predict at the company level but instead need to predict business by business then roll up the result to give company wide prediction.
I have written an ML model in studio.azureml.net
It works great with a 0.947 Coefficient of Determination, but this is for 1 of the businesses.
I now need to train the model for the other 51.
Is there a way to do this in a single ML model rather than having to create 52 very similar models?
Any help would be much appreciated !!!
Kind Regards
Martin
You can use Ensembles, combining several models to improve predictions. The most direct is stacking when the outputs of all the models are trained on the entire dataset.
The method that, I think, corresponds the best to your problem is bagging (bootstrap aggregation). You need to divide the training set into different subsets (each corresponding to a certain business), then train a different model on each subset and combine the result of each classifier.
Another way is boosting but it is difficult to implement in Azure ML.
You can see an example in Azure ML Gallery.
Quote from book:
Stacking and bagging can be easily implemented in Azure Machine
Learning, but other ensemble methods are more difficult. Also, it
turns out to be very tedious to implement in Azure Machine Learning an
ensemble of, say, more than five models. The experiment is filled with
modules and is quite difficult to maintain. Sometimes it is worthwhile
to use any ensemble method available in R or Python. Adding more
models to an ensemble written in a script can be as trivial as
changing a number in the code, instead of copying and pasting modules
into the experiment.
You may also have a look at sklearn (Python) and caret (R) documentation for further details.

MobileNet vs SqueezeNet vs ResNet50 vs Inception v3 vs VGG16

I have recently been looking into incorporating the machine learning release for iOS developers with my app. Since this is my first time ever using anything ML related I was very lost when I started reading the different model descriptions that Apple has made available. They have the same purpose/description, the only difference being the actual file size. What is the difference between these models and how would you know which one is best fit ?
The models Apple makes available are just for simple demo purposes. Most of the time, these models are not sufficient for use in your own app.
The models on Apple's download page are trained for a very specific purpose: image classification on the ImageNet dataset. This means they can take an image and tell you what the "main" object is in the image, but only if it's one of the 1,000 categories from the ImageNet dataset.
Usually, this is not what you want to do in your own apps. If your app wants to do image classification, typically you want to train a model on your own categories (like food or cars or whatever). In that case you can take something like Inception-v3 (the original, not the Core ML version) and re-train it on your own data. That gives you a new model, which you then need to convert to Core ML again.
If your app wants to do something other than image classification, you can use these pretrained models as "feature extractors" in a larger neural network structure. But again this involves training your own model (usually from scratch) and then converting the result to Core ML.
So only in a very specific use case -- image classification using the 1,000 ImageNet categories -- are these Apple-provided models useful to your app.
If you do want to use any of these models, the difference between them is speed vs. accuracy. The smaller models are fastest but also least accurate. (In my opinion, VGG16 shouldn't be used on mobile. It's just too big and it's no more accurate than Inception or even MobileNet.)
SqueezeNets are fully convolutional and use Fire modules which have a squeeze layer of 1x1 convolutions which vastly decreases parameters as it can restrict the number of input channels each layer. This makes SqueezeNets extremely low latency, in addition to the fact they don't have dense layers.
MobileNets utilise depth-wise separable convolutions, very similar to inception towers in inception. These also reduce the number of a parameters and hence latency. MobileNets also have useful model-shrinking parameters than you can call before training to make it exact size you want. The Keras implementation can use ImageNet pre-trained weights too.
The other models are very deep, large models. The reduced number of parameters / style of convolution is not used for low latency but just for the ability to train very deep models, essentially. ResNet introduced residual connections between layers which were originally believed to be key in training very deep models. These aren't seen in the previously mentioned low latency models.

How intensive is training a machine learning algorithm?

I'd like to make an app using iOS's new CoreML framework that does image recognition. To do so I'd probably have to train my own model, and I'm wondering exactly how much data and compute power it would require. Is it something I could feasibly accomplish on an dual core i5 Macbook Pro using Google Images for source data or would it be much more involved?
It depends on what sort of images you want to train your model to recognize.
What is often done is fine-tuning an existing model. You take a pretrained version of Inception-v3 (let's say) and then replace the final layer with your own. You train this last layer on your own images.
You still need a fair number of training images (a few 100 per category, but more is better) but you can do this on your MacBook Pro in anywhere between 30 minutes to a few hours.
TensorFlow comes with a script that makes it really easy to do this. Keras has a great blog post on how to do this. I used the TensorFlow script to re-train Inception-v3 to tell apart my two cats, from 50 or so images of each cat.
If you want to train from scratch you probably want to do this in the cloud using AWS, Google's Cloud ML Engine, or something easy like FloydHub.

How do you add new categories and training to a pretrained Inception v3 model in TensorFlow?

I'm trying to utilize a pre-trained model like Inception v3 (trained on the 2012 ImageNet data set) and expand it in several missing categories.
I have TensorFlow built from source with CUDA on Ubuntu 14.04, and the examples like transfer learning on flowers are working great. However, the flowers example strips away the final layer and removes all 1,000 existing categories, which means it can now identify 5 species of flowers, but can no longer identify pandas, for example. https://www.tensorflow.org/versions/r0.8/how_tos/image_retraining/index.html
How can I add the 5 flower categories to the existing 1,000 categories from ImageNet (and add training for those 5 new flower categories) so that I have 1,005 categories that a test image can be classified as? In other words, be able to identify both those pandas and sunflowers?
I understand one option would be to download the entire ImageNet training set and the flowers example set and to train from scratch, but given my current computing power, it would take a very long time, and wouldn't allow me to add, say, 100 more categories down the line.
One idea I had was to set the parameter fine_tune to false when retraining with the 5 flower categories so that the final layer is not stripped: https://github.com/tensorflow/models/blob/master/inception/README.md#how-to-retrain-a-trained-model-on-the-flowers-data , but I'm not sure how to proceed, and not sure if that would even result in a valid model with 1,005 categories. Thanks for your thoughts.
After much learning and working in deep learning professionally for a few years now, here is a more complete answer:
The best way to add categories to an existing models (e.g. Inception trained on the Imagenet LSVRC 1000-class dataset) would be to perform transfer learning on a pre-trained model.
If you are just trying to adapt the model to your own data set (e.g. 100 different kinds of automobiles), simply perform retraining/fine tuning by following the myriad online tutorials for transfer learning, including the official one for Tensorflow.
While the resulting model can potentially have good performance, please keep in mind that the tutorial classifier code is highly un-optimized (perhaps intentionally) and you can increase performance by several times by deploying to production or just improving their code.
However, if you're trying to build a general purpose classifier that includes the default LSVRC data set (1000 categories of everyday images) and expand that to include your own additional categories, you'll need to have access to the existing 1000 LSVRC images and append your own data set to that set. You can download the Imagenet dataset online, but access is getting spotier as time rolls on. In many cases, the images are also highly outdated (check out the images for computers or phones for a trip down memory lane).
Once you have that LSVRC dataset, perform transfer learning as above but including the 1000 default categories along with your own images. For your own images, a minimum of 100 appropriate images per category is generally recommended (the more the better), and you can get better results if you enable distortions (but this will dramatically increase retraining time, especially if you don't have a GPU enabled as the bottleneck files cannot be reused for each distortion; personally I think this is pretty lame and there's no reason why distortions couldn't also be cached as a bottleneck file, but that's a different discussion and can be added to your code manually).
Using these methods and incorporating error analysis, we've trained general purpose classifiers on 4000+ categories to state-of-the-art accuracy and deployed them on tens of millions of images. We've since moved on to proprietary model design to overcome existing model limitations, but transfer learning is a highly legitimate way to get good results and has even made its way to natural language processing via BERT and other designs.
Hopefully, this helps.
Unfortunately, you cannot add categories to an existing graph; you'll basically have to save a checkpoint and train that graph from that checkpoint onward.

Resources