- Getting data in
- (Non-recurrent) convolutional networks
- Recurrent networks
- Keras: The recommended way of using tensorflow
- Getting models out
- Training in the cloud because you don’t have NVIDIA sponsorship
- Misc HOWTOs
- Hessians and higher order optimisation
- Probabilistic networks
A C++/Python/etc neural network toolkit by Google. I was using it for solving general machine-learning problems, and frequently enough that I have notes. My, do I have notes.
See, of course, nostalgebraist’s rant from December 2019 (supplemental from April 2021) about how I am not just imagining it, Tensorflow was (is?) a horrible mess, which lures you in with easy examples in tutorials that are completely unreflective of the nasty chaos of doing anything non-trivial with it, even morse so than average for software.
…“Datasets” and “TFRecords” containing “tf.Examples” (who knew serializing dicts of ints could be so painful?) and “Estimators” / “Strategies” (which do overlapping things but are mutually exclusive!) and “tf.functions” with “GradientTapes” because the “Strategies” apparently require lazily-defined eagerly-executed computations instead of eagerly-defined lazily-executed computations, and “object-based checkpoints” which are the new official™ thing to do instead of the old Saver checkpoints except the equally official™ “Estimators” do the old checkpoints by default, and oh by the way if you have code that just defines tensorflow ops directly instead of getting them via
tf.kerasobjects (which do all sorts of higher-level management and thus can’t serve as safe drop-in equivalents for “legacy” code using raw ops, and by “legacy” I mean “early 2019″) then fuck you because every code example of a correct™ feature gets its ops from
tf.keras, and aaaaaaaaaaaaaargh!!
Yes, very much so. I had very similar difficulties (some of the names were changed because I was doing it slightly earlier) not to mention it was a nightmare to even install the cursed thing. Anyway, consider yourself warned. I hated tensorflow enough to abandon it. I now use julia or jax instead and the advice is not current. AFAICT the (only?) modern reason to use tensorflow it its remaining advantage: Good tooling for Edge ML. Which is not my area.
Corollary: Some of the below content is obsolete and based on tensorflow 0.7-1.0, which is ancient now far from current.
No idea if any of these are still current.
Tensor2Tensor, or T2T for short, is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research. T2T is actively used and maintained by researchers and engineers within the Google Brain team and a community of users.
tensorflowslim eases some boring bits.
There are some other frontends, which seem a bit less useful to my mind:
tflearn wraps the tensorflow machine in scikit-learn (Although the implementation is not very enlightening, nor the syntax especially clear.)
estimator is a tensorflow generic estimator class. Relationship to other wrappers is not clear to me, but finding out would be tedious, so I will never know.
My objection to these latter abstractions is that they
seem to make the easy bits not easier but different, and the hard bits no
tflearn might be useful if you need to plug into an existing
- Tensorflow for poets.
- A Google beginners guide.
- Implementing odd ops in tensorflow such as rotational transformations
keras tutorials below.
Google’s own Tensorflow without a phd.
- Not in mid training? Explicitly fetch, and print (or do whatever you want) using
- Tensorboard Histogram and Image Summary (see next section)
tf.Print(input, data, message=None, first_n=None, summarize=None, name=None)(link)
tf.Assert(condition, data, summarize=None, name=None)(link)
- Interpose any python codelet in the computation graph
- A step-by-step debugger
tfdbg_: The TensorFlow debugger
Getting data in
This is a depressingly complex topic; Likely it’s more lines of code than building your actual learning algorithm.
For example, things break differently if
you are inputting data of variable dimensions via python which requires a “feed”, which requires keeping references to a placeholder
Oparound, and ALWAYS resubmitting the data every time you run an op, even if the data is not required for the current Op, or
Or inputting a
Variable(which may also be feeds, just to mess with you, and claim to also be variable dimensions but that never works for me) via C++.
These interact in various different ways that seem irritating, but are probably to do with enabling large scale data reading workflows, so that you might accidentally solve a problem for Google and they can get your solution for cheap.
My experience is that stuff is so horribly messy that you should just build different graphs for the estimation and deployment phases of your model and implement them each according to convenience. This of course is asking for trouble with inconsistencies; You can mitigate that by building sub-graphs of the model and re-using them.
I’m not yet sure how to easily transmit the estimated parameters between graphs in these two separate phases… I’ll make notes about THAT when i come to it.
(Non-recurrent) convolutional networks
NB CNN axis ordering is easy to mess up. The Theano guide to convolutions is clearer if you want to work out the actual dimensions your tensors should have. It also gives an intelligible account of how you invert convolutions for decoding.
The Tensorflow convolution guide is more lackadaisical, but it does get us there:
SAMEpadding, the output height and width are computed as:
out_height = ceil(float(in_height) / float(strides)) out_width = ceil(float(in_width) / float(strides))
VALIDpadding, the output height and width are computed as:
out_height = ceil(float(in_height - filter_height + 1) / float(strides)) out_width = ceil(float(in_width - filter_width + 1) / float(strides))
NCHW(cuDNN default). The best practice is to build models that work with both
NHWCas it is common to train using NCHW on GPU, and then do inference with NHWC on CPU.
NCHW is, to be clear,
(batch, channels, height, width).
Theano by contrast, is AFAICT always
The documentation for these is abysmal.
To write: How to create standard linear filters in Tensorflow.
The Tensorflow RNN documentation, as bad as it is, is not even easy to find, being scattered across several non-obvious locations without consistent crosslinks.
- keras RNN seems to be the new way.
- Other docs of confusing relation to the prior docs
- tutorial docs.
- stateful minibatch training requires the catchy SequenceQueueingStateSaver
To make it actually make sense without unwarranted time wasting and guessing, you will then need to read other stuff.
seq2seqmodels with GRUs : Fun with Recurrent Neural Nets.
Denny Britz’s blog posts
- RNNs in Tensorflow, a practical guide and undocumented features.
- He also gives a good explanation of vanishing gradients.
Philippe Remy, Stateful LSTM in Keras
pro tip: SequenceQueueingStateSaver makes things easy.
Keras: The recommended way of using tensorflow
You probably want to start using a higher level
unless your needs are extraordinarily esoteric or
you like reinventing wheels.
Keras is a good choice, since it removes a lot of boilerplate,
and makes even writing new boilerplate easier.
It adds only a few minor restrictions to your abilities, but by creating a consistent API, has become something of a standard for early access to complex new algorithms you would never have time to re-implement yourself.
I would use it if I were you for anything involving standard neural networks, especially any kind of recurrent network. If you want to optimise a generic, non-deep neural model, you might find the naked tensorflow API has less friction.
- Easing pain via Keras.
- Jason Brownlee’s HOWTO guide.
- Recurrent neural networks’ gradients are truncated to the sequence length, which might not be obvious. But this is the TBPTT parameter.
- recurrentshop makes it easier to manage recurrent topologies using keras.
Getting models out
- For a local app: Hamed MP, Exporting trained TensorFlow models to C++ the RIGHT way!
- For serving it online, Tensorflow
servingis the preferred method. See the Serving documentation.
- for mobile app the HBO joke hotdog app HOWTO gives a wonderful explanation.
Training in the cloud because you don’t have NVIDIA sponsorship
See practical cloud computing, which has a couple of sections on that.
Tedious. One could imply not install it but rather containerize via Tensorman. See also pop-os/tensorman: Utility for easy management of Tensorflow containers.
Here (or build your own)
NVIDIA_VISIBLE_GPU to the least loaded GPU.
TF_CPP_MIN_LOG_LEVEL=1 primusrun python run_job.py args
Hessians and higher order optimisation
here’s mine — works for high-dimensional Jacobians (numerator and denominator have >1 dimension), undefined batch sizes, and tensors that are not statically known.
def tf_jacobian(tensor2, tensor1, feed_dict, sess = tf.get_default_session()): """ Computes the tensor d(tensor2)/d(tensor1) recursively. :param tensor2: numerator of Jacobian :param tensor1: denominator of Jacobian :param feed_dict: input data (need this if tensors are not statically known) :return: a tensor of dimension (dim_tensor2 x dim_tensor1) """ # can’t do tensor.get_shape() because it doesn’t work for undefined batch size shape = list(sess.run(tf.shape(tensor2), feed_dict)) if shape: # split tensor2 along first dimension and recur # int trick from https://github.com/tensorflow/tensorflow/issues/7754 tensor2_split = tf.split(axis = 0, num_or_size_splits = int(shape), value = tensor2) grad_split = [tf_jacobian(tf.squeeze(M, squeeze_dims = 0), tensor1, feed_dict) for M in tensor2_split] return tf.stack(grad_split) else: # calculate gradient of scalar grad = tf.gradients(tensor2, tensor1) if grad != None: return tf.squeeze(grad, squeeze_dims = ) else: # replace any undefined gradients with zeros return tf.zeros_like(tensor1)
And here’s one for batched tensors:
def batch_tf_jacobian( tensor2, tensor1, feed_dict, sess = tf.get_default_session()): """ Computes the matrix d(tensor2)/d(tensor1) recursively. Tensorflow doesn’t really have its own Jacobian operator (tf.gradients sums over all dims of tensor2). :param tensor2: numerator of Jacobian, first dimension is batch :param tensor1: denominator of Jacobian, first dimension is batch :param feed_dict: input data (need this if tensors are not statically known) :return: batch Jacobian tensor """ shape2 = list(sess.run(tf.shape(tensor2), feed_dict)) shape1 = list(sess.run(tf.shape(tensor1), feed_dict)) jacobian = tf_jacobian(tensor2, tensor1, feed_dict) batch_size = shape2 batch_jacobian = [ tf.slice( jacobian, [i] + *(len(shape2)-1) + [i] + *(len(shape1)-1),  + [-1]*(len(shape2)-1) +  + [-1]*(len(shape1)-1) ) for i in range(batch_size)] batch_jacobian = [ tf.squeeze(tensor, squeeze_dims = (0, len(shape2))) for tensor in batch_jacobian] batch_jacobian = tf.stack(batch_jacobian) return batch_jacobian
Simplify distributed training using Horovod.