I am newbie in Tensorflow
Actually, I am testing some example in Tensorflow web-site, and I start to understand some features of the framwork, but what I don't understand is how I can design my architecture, I mean number of layers, type of Layer "conv, pool...", and if it is necessery to do that, because there are many predifined architectures like AmexNet,
Thanks,
I would strongly recommend working through their hands on tutorial, depending on if you have previous ML experience (https://www.tensorflow.org/get_started/mnist/pros) or not (https://www.tensorflow.org/get_started/mnist/beginners). The questions you are asking are answered in there.
The question on using predefined architectures or self defined depends on your use case. If you want to do something easy like classifying if there is only a car in the scene or not a more shallow architecture might work better, because it is faster and a more deep one is overkill. However most architectures are similar to the ones already defined in literature.
Another question that arises naturally, while talking about pre defined architecture is about transfer learning / fine tuning. Often pre defined architectures are already learned on some big dataset (mostly ImageNet) and already perform really well out of the box for many tasks. With little training data it makes a lot of sense to use this. With lots of training data it can hinder your progress though.
Related
I successfully trained multi-classificator model, that was really easy with simple class related folder structure and keras.preprocessing.image.ImageDataGenerator with flow_from_directory (no one-hot encoding by hand btw!) after i just compile fit and evaluate - extremely well done pipeline by Keras!
BUT! when i decided to make my own (not cats, not dogs, not you_named) object detector - this is became a nightmare...
TFRecord and tf.Example are just madness! but ok, i almost get it (my dataset is small, i have plenty of ram, but who cares, write f. boilerplate, so much meh...)
The main thing - i just can't find any docs/tutorial how to make it with plain simple tf/keras, everyone just want to build up it on top of someone model, YOLO SSD FRCNN, even if they trying to detect completely new objects!!!
There two links about OD in official docs, and they both using some models underneath.
So my main question WHY ??? or i just blind..? -__-
It becomes a nightmare because Object Detection is way way harder than classification. The most simple object detector is this: first train a classifier on all your objects. Then when you want to detect objects in your image, slide a window over your image, and classify each window. Then, if your classifier is certain that a certain window is one of the objects, mark it as a successful detection.
But this approach has a lot of problems, mainly it's way (like waaaay) too slow. So, researcher improved it and invented RCNNs. That had it problems, so they invented Faster-RCNN, YOLO and SSD, all to make it faster and more accurate.
You won't find any tutorials online on how to implement the sliding window technique because it's not useful anyway, and you won't find any tutorials on how to implement the more advanced stuff because, well, the networks get complicated pretty quick.
Also note that using YOLO doesn't mean you should use the same weights as in YOLO. You can always train YOLO from scratch on your own data if you want by randomly initiliazing all the weights in the network layers. So the even if they trying to detect completely new objects!!! you mentioned isn't really valid. Also also note that I still would advise you to do use the weights they used in Yolo network. Transfer Learning is generally looked at as being a good idea, especially when starting out and especially in the image processing world, as many images share common features (like edges, for example).
I am having pretty much the same problem as my images are B/W diagrams, quite different from regular pictures, I want to train a custom model on just only diagrams.
I have found this documentation section in Tensorflow models repo:
https://github.com/tensorflow/models/blob/master/research/object_detection/README.md
It has a couple of sections explaining how to bring your own model and dataset in "extras" that could be a starting point.
I'm trying to train a model for a sentence classification task. The input is a sentence (a vector of integers) and the output is a label (0 or 1). I've seen some articles here and there about using Bert and GPT2 for text classification tasks. However, I'm not sure which one should I pick to start with. Which of these recent models in NLP such as original Transformer model, Bert, GPT2, XLNet would you use to start with? And why? I'd rather to implement in Tensorflow, but I'm flexible to go for PyTorch too.
Thanks!
It highly depends on your dataset and is part of the data scientist's job to find which model is more suitable for a particular task in terms of selected performance metric, training cost, model complexity etc.
When you work on the problem you will probably test all of the above models and compare them. Which one of them to choose first? Andrew Ng in "Machine Learning Yearning" suggest starting with simple model so you can quickly iterate and test your idea, data preprocessing pipeline etc.
Don’t start off trying to design and build the perfect system.
Instead, build and train a basic system quickly—perhaps in just a few
days
According to this suggestion, you can start with a simpler model such as ULMFiT as a baseline, verify your ideas and then move on to more complex models and see how they can improve your results.
Note that modern NLP models contain a large number of parameters and it is difficult to train them from scratch without a large dataset. That's why you may want to use transfer learning: you can download pre-trained model and use it as a basis and fine-tune it to your task-specific dataset to achieve better performance and reduce training time.
I agree with Max's answer, but if the constraint is to use a state of the art large pretrained model, there is a really easy way to do this. The library by HuggingFace called pytorch-transformers. Whether you chose BERT, XLNet, or whatever, they're easy to swap out. Here is a detailed tutorial on using that library for text classification.
EDIT: I just came across this repo, pytorch-transformers-classification (Apache 2.0 license), which is a tool for doing exactly what you want.
Well like others mentioned, it depends on the dataset and multiple models should be tried and best one must be chosen.
However, sharing my experience, XLNet beats all other models so far by a good margin. Hence if learning is not the objective, i would simple start with XLNET and then try a few more down the line and conclude. It just saves time in exploring.
Below repo is excellent to do all this quickly. Kudos to them.
https://github.com/microsoft/nlp-recipes
It uses hugging face transformers and makes them dead simple. 😃
I have used XLNet, BERT, and GPT2 for summarization tasks (English only). Based on my experience, GPT2 works the best among all 3 on short paragraph-size notes, while BERT performs better for longer texts (up to 2-3 pages). You can use XLNet as a benchmark.
Suppose that I have want to make a model that does something. Now when I search about the topic in Google or YouTube, I find many related tutorials and it seems like some clever programmer had already implemented that model with Deep learning.
But how do they know that what type of layers, what type of activation functions, loss functions, optimizer, number of units etc. they need to solve that certain problem using deep learning.
Are there any techniques for knowing this, or its just a matter of understanding and experience? Also it would be very helpful if somebody could point me to some videos or articles answering my question.
This is more of a matter of understanding and experience. When building a model from scratch, you must understand which optimizer, loss, etc. makes sense for your particular problem. In order to choose these appropriately, you must understand the differences between the available optimizers, loss functions, etc.
In regards to choosing how many layers and nodes, what batch size, what learning rate, etc.-- these are all hyperparameters that you will need to test and tune as you experiment with your model.
I have a Deep Learning Fundamentals YouTube playlist that you may find helpful. It covers the fundamental basics of each of these topics in short videos. Additionally, this Deep Learning with Keras playlist may also be beneficial if you're wanting to focus more on coding after getting the basic concepts down.
Thanks for the question.
The CS231n Stanford lectures on CNN is the best for beginners refer to the video lectures here and class notes are available here
After watching the lectures and completing the assignments, you will get a basic idea of what Deep Learning is and all the algorithms available etc.
But when it comes to solving real-world problems this won't be sufficient So take this course by Jeremy Howard where he teaches more on how to approach a problem using Kaggle platform.
Keep on solving more problems experimenting new models and algorithms using several platforms like hackerearth, Kaggle, topcoder etc.
I want to study on the research of deep learning, but I don't know which framwork should I choice between TensorFlow and PaddlePaddle. who can make a contrast between the two frameworks? which one is better? especially in the running efficiency of CPU
It really depends what you are shooting for...
If you plan on training, CPU is not going to work well for you. Use colab or kaggle.
Assuming you do get a GPU, it depends if you want to focus on classification or object detection.
If you focus on classification, Keras is probably the easiest to work with or pytorch if you want some advanced stuff and to be able to change things.
If you plan on object detection, things are getting complicated... Inference is reasonably easy but training is complicated. There are actually 4 platforms you should consider:
Tensorflow - powerful but very difficult to work with. If you do not use Keras (and for OD you usually can't), you need to preprocess the dataset into tfrecords and it is a pain. The OD Api has very cryptic messages and it is very sensitive to the combination of tf version and api version. On the other hand, cool models like efficientdet are more or less easy to use.
MMdetection - very powerful framework, has lots of advanced models and once you understand how to work with it, you can easily work with and of the models it supports. Downside is that some models are slow to arrive (efficientdet, for example)
paddlepaddle - if you know Chinese, this should work ok, maybe. The documentation is a bit behind and usually requires lots of improvisation. Basically it is similar to mmdetection just with a few unique models and a few missing models.
detectron2 - I didn't work with this one, but it seems to support only a few models.
You probably need first to define for yourself what do you want to do and then choose.
Good luck!
It is not that trivial. Some models run faster with one kind of framework others with another. Furthermore, it depends on the hardware as well. See this blog. If inference is your only concern, then you can develop your model in any of the popular frameworks like TensorFlow, PyTorch, etc. In the end convert your model to ONNX format and benchmark its performance with DNN-Bench to choose the best inference engine for your application.
Currently, there are a lot of deep learning models developed in Caffe instead of tensorflow. If I want to re-write these models in tensorflow, how to start? I am not familiar with Caffe structure. It seems to me that there are some files storing the model architecture only. My guess is that I only need to understand and transfer those architecture design into Tensorflow. The input/output/training will be re-written anyway. Is this thought meaningful?
I see some Caffe implementation also need to hack into the original Caffe framework down to the C++ level, and make some modifications. I am not sure under what kind of scenario the Caffe model developer need to go that deep? If I just want to re-implement their models in Tensorflow, do I need to go to check their C++ modifications, which are sometimes not documented at all.
I know there are some Caffe-Tensorflow transformation tool. But there are always some constraints, and I think re-write the model directly maybe more straightforward.
Any thougts, suggestions, and link to tutorials are highly appreciated.
I have already asked a similar question.
To synthetise the possible answers :
You can either use pre-existing tools like etheron's kaffe(which is really simple to use). But its simplicity comes at a cost: it is not easy to debug.
As #Yaroslav Bulatov answered start from scratch and try to make each layer match. In this regard I would advise you to look at ry's github which is a remarkable example where you basically have small helper functions which indicate how to reshape the weights appropriately from caffe to Tensorflow, which is the only real thing you have to do to make simple models match and also provides activations check layer by layer.