I plot all my weights of my neural network on tensorboard, I found that some
weights of some layer is normally distributed:
but, some are not.
what does this imply? should I increase or decrease the capacity of this layer?
Update:
My network is a LSTM-based netowrk. the non-normal distributed weights is the weights multiply with input feature, the normal distributed weights is the weights multiply with states.
one explanation base on convolutional networks might be this(I don't know if this is true for any other kind of artificial neural models or not), hence the first layer tries to find distinct small features weights are distributed very widely and network tries to find any useful feature it can, then in the next layers combination of these distinct features are used, which make sense to put a normal distribution of weights hence every one of the previous features are going to be part of a single bigger or more representative feature in next layers.
but this was only my intuition I am not sure if this is the reason with proof now.
Related
I am training a yolov4 (fully convolutional) in tensorflow 2.3.0.
I would like to change the spatial input shape of the network during training, to further adjust the weights to different scales.
Is this possible?
EDIT:
I know of the existence of darknet, but it suffers from some very specific augmentations I use and have implemented in my repo, that is why I ask explicitly for tensorflow.
To be more precisely about what I want to do.
I want to train for several batches at Y1xX1xC then change the input size to Y2xX2xC and train again for several batches and so on.
It is not possible. In the past people trained several networks for different scales but the current state-of-the-art approach is feature pyramids.
https://arxiv.org/pdf/1612.03144.pdf
Another great candidate is to use dilated convolution which can learn long distance dependencies among pixels with varying distance. You can concatenate the outputs of them and the model will then learn which distance is important for which case
https://towardsdatascience.com/review-dilated-convolution-semantic-segmentation-9d5a5bd768f5
It's important to mention which TensorFlow repository you're using. You can definitely achieve this. The idea is to keep the fixed spatial input dimension in a single batch.
But even better approach is to use the darknet repository from AlexeyAB: https://github.com/AlexeyAB/darknet
Just set, random = 1 https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov4.cfg [line 1149]. It will train your network with different spatial dimensions randomly.
One thing you can do is, start your training with AlexeyAB repo with random=1 set, then take the trained weights file to tensorflow for fine-tuning.
This is a more general version of a question I've already asked: Significant difference between outputs of deep tensorflow keras model in Python and tensorflowjs conversion
As far as I can tell, the layers of a tfjs model when run in the browser (so far only tested in Chrome and Firefox) will have small numerical differences in the output values when compared to the same model run in Python or Node. The cumulative effect of these small differences across all the layers of the model can cause fairly significant differences in the output. See here for an example of this.
This means a model trained in Python or Node will not perform as well in terms of accuracy when run in the browser. And the deeper your model, the worse it will get.
Therefore my question is, what is the best way to train a model to use with tfjs in the browser? Is there a way to ensure the output will be identical? Or do you just have to accept that there will be small numerical differences and, if so, are there any methods that can be used to train a model to be more resilient to this?
This answer is based on my personal observations. As such, it is debatable and not backed by much evidence. Some things that I follow to get accuracy of 16-bit models close to 32 bit models are:
Avoid using activations that have small upper and lower bounds, such as sigmoid or tanh, for hidden layers. These activations cause the weights of the next layer to become very sensitive to small values, and hence, small changes. I prefer using ReLU for such models. Since it is now the standard activation for hidden layers in most models, you should be using it in any case.
Avoid weight decay and L1/L2 regularizations on weights while training (the kernel_regularizer parameter in keras), since these increase sensitivity of weights. Use Dropout instead, I didn't observe a major drop in performance on TFLite when using it instead of numerical regularizers.
This tutorial has the tensor-flow implementation of batch normal layer for training and testing phases.
When we using transfer learning is it ok to use batch normalization layer? Specially when data distributions are different.
Because in the inference phase BN layer just uses fixed mini batch mean and variance(Which is calculated with the help of training distribution).
So if our model has a different distribution of data , can it give wrong results?
With transfer learning, you're transferring the learned parameters from a domain to another.
Usually, this means that you're keeping fixed the learned values of the convolutional layer whilst adding new fully connected layers that learn to classify the features extracted by the CNN.
When you add batch normalization to every layer, you're injecting values sampled from the input distribution into the layer, in order to force the output layer to be normally distributed.
In order of doing that, you compute the exponential moving average of the layer output and then in the testing phase, you subtract this value from the layer output.
Although data dependent, this mean values (for every convolutional layer) are computed on the output of the layer, thus on the transformation learned.
Thus, in my opinion, the various averages that the BN layer subtracts from its convolutional layer output are general enough to be transferred: they are computed on the transformed data and not on the original data.
Moreover, the convolutional layer learns to extract local patterns thus they're more robust and difficult to influence.
Thus, in short and in my opinion:
you can apply transfer learning of convolutional layer with batch norm applied. But on fully connected layers the influence of the computed value (that see the whole input and not only local patches) can bee too much data dependent and thus I'll avoid it.
However, as a rule of thumb: if you're insecure about something just try it and see if it works!
I read a lot of papers on convnets, but there is one thing I don't understand, how the filters in convolutional layer are initialized ?
Because, for examples, in first layer, filters should detect edges etc..
But if it randomly init, it could not be accurate ? Same for next layer and high-level features.
And an other question, what are the range of the value in those filters ?
Many thanks to you!
You can either initialize the filters randomly or pretrain them on some other data set.
Some references:
http://deeplearning.net/tutorial/lenet.html:
Notice that a randomly initialized filter acts very much like an edge
detector!
Note that we use the same weight initialization formula as with the
MLP. Weights are sampled randomly from a uniform distribution in the
range [-1/fan-in, 1/fan-in], where fan-in is the number of inputs to a
hidden unit. For MLPs, this was the number of units in the layer
below. For CNNs however, we have to take into account the number of
input feature maps and the size of the receptive fields.
http://cs231n.github.io/transfer-learning/ :
Transfer Learning
In practice, very few people train an entire Convolutional Network
from scratch (with random initialization), because it is relatively
rare to have a dataset of sufficient size. Instead, it is common to
pretrain a ConvNet on a very large dataset (e.g. ImageNet, which
contains 1.2 million images with 1000 categories), and then use the
ConvNet either as an initialization or a fixed feature extractor for
the task of interest. The three major Transfer Learning scenarios look
as follows:
ConvNet as fixed feature extractor. Take a ConvNet pretrained on ImageNet, remove the last fully-connected layer (this layer's outputs
are the 1000 class scores for a different task like ImageNet), then
treat the rest of the ConvNet as a fixed feature extractor for the new
dataset. In an AlexNet, this would compute a 4096-D vector for every
image that contains the activations of the hidden layer immediately
before the classifier. We call these features CNN codes. It is
important for performance that these codes are ReLUd (i.e. thresholded
at zero) if they were also thresholded during the training of the
ConvNet on ImageNet (as is usually the case). Once you extract the
4096-D codes for all images, train a linear classifier (e.g. Linear
SVM or Softmax classifier) for the new dataset.
Fine-tuning the ConvNet. The second strategy is to not only replace and retrain the classifier on top of the ConvNet on the new
dataset, but to also fine-tune the weights of the pretrained network
by continuing the backpropagation. It is possible to fine-tune all the
layers of the ConvNet, or it's possible to keep some of the earlier
layers fixed (due to overfitting concerns) and only fine-tune some
higher-level portion of the network. This is motivated by the
observation that the earlier features of a ConvNet contain more
generic features (e.g. edge detectors or color blob detectors) that
should be useful to many tasks, but later layers of the ConvNet
becomes progressively more specific to the details of the classes
contained in the original dataset. In case of ImageNet for example,
which contains many dog breeds, a significant portion of the
representational power of the ConvNet may be devoted to features that
are specific to differentiating between dog breeds.
Pretrained models. Since modern ConvNets take 2-3 weeks to train across multiple GPUs on ImageNet, it is common to see people release
their final ConvNet checkpoints for the benefit of others who can use
the networks for fine-tuning. For example, the Caffe library has a
Model Zoo where people
share their network weights.
When and how to fine-tune? How do you decide what type of transfer learning you should perform on a new dataset? This is a function of
several factors, but the two most important ones are the size of the
new dataset (small or big), and its similarity to the original dataset
(e.g. ImageNet-like in terms of the content of images and the classes,
or very different, such as microscope images). Keeping in mind that
ConvNet features are more generic in early layers and more
original-dataset-specific in later layers, here are some common rules
of thumb for navigating the 4 major scenarios:
New dataset is small and similar to original dataset. Since the data is small, it is not a good idea to fine-tune the ConvNet due to
overfitting concerns. Since the data is similar to the original data,
we expect higher-level features in the ConvNet to be relevant to this
dataset as well. Hence, the best idea might be to train a linear
classifier on the CNN codes.
New dataset is large and similar to the original dataset. Since we have more data, we can have more confidence that we won't overfit
if we were to try to fine-tune through the full network.
New dataset is small but very different from the original dataset. Since the data is small, it is likely best to only train a
linear classifier. Since the dataset is very different, it might not
be best to train the classifier form the top of the network, which
contains more dataset-specific features. Instead, it might work better
to train the SVM classifier from activations somewhere earlier in the
network.
New dataset is large and very different from the original dataset. Since the dataset is very large, we may expect that we can
afford to train a ConvNet from scratch. However, in practice it is
very often still beneficial to initialize with weights from a
pretrained model. In this case, we would have enough data and
confidence to fine-tune through the entire network.
Practical advice. There are a few additional things to keep in mind when performing Transfer Learning:
Constraints from pretrained models. Note that if you wish to use a pretrained network, you may be slightly constrained in terms of the
architecture you can use for your new dataset. For example, you can't
arbitrarily take out Conv layers from the pretrained network. However,
some changes are straight-forward: Due to parameter sharing, you can
easily run a pretrained network on images of different spatial size.
This is clearly evident in the case of Conv/Pool layers because their
forward function is independent of the input volume spatial size (as
long as the strides "fit"). In case of FC layers, this still holds
true because FC layers can be converted to a Convolutional Layer: For
example, in an AlexNet, the final pooling volume before the first FC
layer is of size [6x6x512]. Therefore, the FC layer looking at this
volume is equivalent to having a Convolutional Layer that has
receptive field size 6x6, and is applied with padding of 0.
Learning rates. It's common to use a smaller learning rate for ConvNet weights that are being fine-tuned, in comparison to the
(randomly-initialized) weights for the new linear classifier that
computes the class scores of your new dataset. This is because we
expect that the ConvNet weights are relatively good, so we don't wish
to distort them too quickly and too much (especially while the new
Linear Classifier above them is being trained from random
initialization).
Additional References
CNN Features off-the-shelf: an Astounding Baseline for Recognition trains SVMs on features
from ImageNet-pretrained ConvNet and reports several state of the art
results.
DeCAF reported similar findings in 2013. The framework in this paper (DeCAF) was a Python-based precursor to the C++ Caffe library.
How transferable are features in deep neural networks? studies the transfer
learning performance in detail, including some unintuitive findings
about layer co-adaptations.
I'm using TensorFlow to train a Convolutional Neural Network (CNN) for a sign language application. The CNN has to classify 27 different labels, so unsurprisingly, a major problem has been addressing overfitting. I've taken several steps to accomplish this:
I've collected a large amount of high-quality training data (over 5000 samples per label).
I've built a reasonably sophisticated pre-processing stage to help maximize invariance to things like lighting conditions.
I'm using dropout on the fully-connected layers.
I'm applying L2 regularization to the fully-connected parameters.
I've done extensive hyper-parameter optimization (to the extent possible given HW and time limitations) to identify the simplest model that can achieve close to 0% loss on training data.
Unfortunately, even after all these steps, I'm finding that I can't achieve much better that about 3% test error. (It's not terrible, but for the application to be viable, I'll need to improve that substantially.)
I suspect that the source of the overfitting lies in the convolutional layers since I'm not taking any explicit steps there to regularize (besides keeping the layers as small as possible). But based on examples provided with TensorFlow, it doesn't appear that regularization or dropout is typically applied to convolutional layers.
The only approach I've found online that explicitly deals with prevention of overfitting in convolutional layers is a fairly new approach called Stochastic Pooling. Unfortunately, it appears that there is no implementation for this in TensorFlow, at least not yet.
So in short, is there a recommended approach to prevent overfitting in convolutional layers that can be achieved in TensorFlow? Or will it be necessary to create a custom pooling operator to support the Stochastic Pooling approach?
Thanks for any guidance!
How can I fight overfitting?
Get more data (or data augmentation)
Dropout (see paper, explanation, dropout for cnns)
DropConnect
Regularization (see my masters thesis, page 85 for examples)
Feature scale clipping
Global average pooling
Make network smaller
Early stopping
How can I improve my CNN?
Thoma, Martin. "Analysis and Optimization of Convolutional Neural Network Architectures." arXiv preprint arXiv:1707.09725 (2017).
See chapter 2.5 for analysis techniques. As written in the beginning of that chapter, you can usually do the following:
(I1) Change the problem definition (e.g., the classes which are to be distinguished)
(I2) Get more training data
(I3) Clean the training data
(I4) Change the preprocessing (see Appendix B.1)
(I5) Augment the training data set (see Appendix B.2)
(I6) Change the training setup (see Appendices B.3 to B.5)
(I7) Change the model (see Appendices B.6 and B.7)
Misc
The CNN has to classify 27 different labels, so unsurprisingly, a major problem has been addressing overfitting.
I don't understand how this is connected. You can have hundreds of labels without a problem of overfitting.