I was writing a neural net to train Resnet on CIFAR-10 dataset.
The paper Deep Residual Learning For Image Recognition mentions training for around 60,000 epochs.
I was wondering - what exactly does an epoch refer to in this case? Is it a single pass through a minibatch of size 128 (which would mean around 150 passes through the entire 50000 image training set?
Also how long is this expected to take to train(assume CPU only, 20-layer or 32-layer ResNet)? With the above definition of an epoch, it seems it would take a very long time...
I was expecting something around 2-3 hours only, which is equivalent to about 10 passes through the 50000 image training set.
The paper never mentions 60000 epochs. An epoch is generally taken to mean one pass over the full dataset. 60000 epochs would be insane. They use 64000 iterations on CIFAR-10. An iteration involves processing one minibatch, computing and then applying gradients.
You are correct in that this means >150 passes over the dataset (these are the epochs). Modern neural network models often take days or weeks to train. ResNets in particular are troublesome due to their massive size/depth. Note that in the paper they mention training the model on two GPUs which will be much faster than on the CPU.
If you are just training some models "for fun" I would recommend scaling them down significantly. Try 8 layers or so; even this might be too much. If you are doing this for research/production use, get some GPUs.
Related
I am working on deep learning model to detect regions of timesteps with anomalies. This model should classify each timestep as possessing the anomaly or not.
My labels are something like this:
labels = [0 0 0 1 0 0 0 0 1 0 0 0 ...]
The 0s represent 'normal' timesteps and the 1s represent the existence of an anomaly. In reality, my dataset is very very imbalanced:
My training set consists of over 7000 samples, where only 1400 samples = 20% of those contain at least 1 anomaly (timestep = 1)
I am feeding samples with 4096 timesteps each. The average number of anomalies, in the samples that contain them, is around 2. So, assuming there is an anomaly, the % of anomalous timesteps ranges from 0.02% to 0.04% for each sample.
With that said, I do need to shift from the standard binary cross entropy to something that highlights the anomalous timesteps from the anomaly free timesteps.
So, I experimented adding weights to the anomalous class in such a way that the model is forced to learn from the anomalies and not just reduce its loss from the anomaly-free timesteps. It actually worked well and the model seems to learn to detect anomalous timesteps. One problem however is that training can become quite unstable (and unpredictable), with sudden loss spikes appearing and affecting the learning process. Below, you can see the effects on the loss and metrics charts for two of my trainings:
After going through a debugging process for the trainings, I am confident that the problem comes from ocasional predictions given for the anomalous timesteps. That is, in some samples of a certain epoch, and in some anomalous timesteps, the model is giving a very low prediction, e.g. 0.01, for the 1s label (should be close to 1 ofc). Considering the very high (but supposedly necessary) weights given to the anomalous timesteps, the penaly is really extreme and the loss just skyrockets.
Going deeper, if I inspect the losses of the sample where the jump happened and look for the batch right before the loss jumped, I see that the losses are all around 10^-2 - 0.0053, 0.004, 0.0041... - not a single sample with a loss over those values. Overall, an average loss of 0.005. However, if I inspect the loss of the following batch, in that same sample, the avg. loss of the batch is already 3.6, with a part of the samples with a low loss but another part with a very high loss - e.g. 9.2, 7.7, 8.9... I can confirm that all the high losses come from the penalties given at predicting the 1s timesteps. The following batches of the same sample and some of the batches of the next epoch get affected and take some time to start decreasing again and going back to a stable learning process.
With this said, I am having this problem for some weeks already and really need some guidance in what I could try to deal with the spikes, which I assume that arise on the gradient updates associated with anomalous timesteps that are harder to learn.
I am currently using a simple 2-layer keras LSTM model with 64 units each and a dense as the last layer with a 1 unit dense layer with sigmoid activation. As for the optimizer I am using Adam. I am training with batch size 128. Some things to consider also:
I have tried changes in weights and other loss functions. Ultimately, if I reduce the weights given to the anomalous timesteps the model doesn't give so much importance to them and the loss reduces by considering only the anomalous free timesteps. I have also considered focal binary cross entropy loss but it doesn't seem to do anything that could avoid those jumps as, in the end, it is all about adding or reducing weights for certain timesteps.
My current learning rate is the Adam's default, 10⁻3. I have tried reducing the learning rate which leads to less impactful spikes (they're still there though) but the model also takes much more time or gets stuck. Not sure if it would be the way to go in this case, as the training seems to go well except for these cases. Decaying learning rate might also not make too much sense as the spikes can happen earlier in the training and not only on later epochs. Not sure if this is the way to go.
I am still investigating gradient clipping as a solution. I am still not sure on what values to use and if it is actually an effective solution for my case, but from what I understood of it, it should allow to counter those jumps resulting from those 'almost' exploding gradients.
The spikes could originate from sample noise / bad samples. However, since I am already using batch size 128 and I have already tested training with simple synthetic samples I have created and the spikes were still there, I guess it is not a problem with specific samples.
The imbalance obviously plays the bigger role here. Not sure if undersampling the majority class of samples of 4096 timesteps (like increasing from 20% to 50% the amount of samples with at least an anomalous timestep) would make a big difference here since each sample of timesteps is by itself very imbalanced as it contains around 2 timesteps with anomalies. It is a problem with the imbalance within each sample.
I know it might be quite some context but honestly I am already into my limit of trying stuff for weeks.
The solutions I am inclined to go for next are either gradient clipping or just changing my samples to be more centered around the anomalous timesteps, in such a way that it contains less anomaly free timesteps and hopefully allows for convergence without having to apply such drastic weights to anomalous timesteps. This last option is more difficult for me to opt for due to some restrictions, but I might look at it if I have nothing else available.
What do you think? I am able to provide more information if needed.
I am using YOLOv4-tiny for a custom dataset of 26 classes that I collected from Open Images Dataset. The dataset is almost balanced(850 images per class but different number of bounding boxes). When I used YOLOv4-tiny to train on just 3 classes the loss was near 0.5, it was fairly accurate. But for 26 classes as soon as the loss goes below 2 the model starts to overfit. The prediction are also very inaccurate.
I have tried to change the parameters like the learning rate, the momentum and the size but whatever I do the models becomes worse then before. Using regular YOLOv4 model rather then YOLO-tiny does not help either. How can I bring the loss further down?
Have you tried training with mAP? You can take a subset of your training set and make it the validation set. This can be done in the same way you made your training and test set. Then, you can run darknet.exe detector train data/obj.data yolo-obj.cfg yolov4.conv.137 -map. This will keep track of the loss in your validation set. When the error in the validation say goes up, this is the time to stop training and prevent overfitting (this is called: early stopping).
You need to run the training for (classes*2000)iterations. However, for the best scores, you need to train your model for at least 6000 iterations (also known as max_batches). Also please remember if you are using a b&w image, change the channels=3 to channels=1. You can stop your training once the avg loss becomes something like this: 0.XXXX.
Here's my mAP graph for 6000 iterations that ran for 6.2 hours:
avg loss with 6000 max_batches.
Moreover, you can follow this FAQ documentation here by Stéphane Charette.
I have tried training three UNet models using keras for image segmentation to assess the effect of multi-GPU training.
First model was trained using 1 batch size on 1 GPU (P100). Each training step took ~254ms. (Note it is step, not epoch).
Second model was trained using 2 batch size using 1 GPU (P100). Each training step took ~399ms.
Third model was trained using 2 batch size using 2 GPUs (P100). Each training step took ~370ms. Logically it should have taken the same time as the first case, since both GPUs process 1 batch in parallel but it took more time.
Anyone who can tell whether multi-GPU training results in reduced training time or not? For reference, I tried all the models using keras.
I presume that this is due to the fact that you use a very small batch_size; in this case, the cost of distributing the gradients/computations over two GPUs and fetching them back (as well as CPU to GPU(2) data distribution) outweigh the parallel time advantage that you might gain versus the sequential training(on 1 GPU).
Expect to see a bigger difference for a batch size of 8/16 for instance.
When I execute the cifar10 model as described at https://www.tensorflow.org/tutorials/deep_cnn I achieve 86% accuracy after approx 4 hours using a single GPU , when I utilize 2 GPU's the accuracy drops to 84% but reaching 84% accuracy is faster on 2 GPU's than 1.
My intuition is
that average_gradients function as defined at https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10/cifar10_multi_gpu_train.py returns a less accurate gradient value as an average of gradients will be less accurate than the actual gradient value.
If the gradients are less accurate then the parameters than control the function that is learned as part of training is less accurate. Looking at the code (https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10/cifar10_multi_gpu_train.py) why is averaging the gradients over multiple GPU's less accurate than computing the gradient on a single GPU ?
Is my intuition of averaging the gradients producing a less accurate value correct ?
Randomness in the model is described as :
The images are processed as follows:
They are cropped to 24 x 24 pixels, centrally for evaluation or randomly for training.
They are approximately whitened to make the model insensitive to dynamic range.
For training, we additionally apply a series of random distortions to artificially increase the data set size:
Randomly flip the image from left to right.
Randomly distort the image brightness.
Randomly distort the image contrast.
src : https://www.tensorflow.org/tutorials/deep_cnn
Does this have an effect on training accuracy ?
Update :
Attempting to investigate this further, the loss function value training with different number of GPU's.
Training with 1 GPU : loss value : .7 , Accuracy : 86%
Training with 2 GPU's : loss value : .5 , Accuracy : 84%
Shouldn't the loss value be lower for higher for higher accuracy, not vice versa ?
In the code you linked, using the function average_gradient with 2 GPUs is exactly equivalent (1) to simply using 1 GPU with twice the batch size.
You can see it in the definition:
grad = tf.concat(axis=0, values=grads)
grad = tf.reduce_mean(grad, 0)
Using a larger batch size (given the same number of epochs) can have any kind of effect on your results.
Therefore, if you want to do exactly equivalent (1) calculations in 1-GPU or 2-GPU cases, you may want to halve the batch size in the latter case. (People sometimes avoid doing it, because smaller batch sizes may also make the computation on each GPU slower, in some cases)
Additionally, one needs to be careful with learning rate decay here. If you use it, you want to make sure the learning rate is the same in the nth epoch in both 1-GPU and 2-GPU cases -- I'm not entirely sure this code is doing the right thing here. I tend to print the learning rate in the logs, something like
print sess.run(lr)
should work here.
(1) Ignoring issues related to pseudo-random numbers, finite precision or data set sizes not divisible by the batch size.
There is a decent discussion of this here (not my content). Basically when you distribute SGD, you have to communicate gradients back and forth somehow between workers. This is inherently imperfect, and so your distributed SGD typically diverges from a sequential, single-worker SGD at least to some degree. It is also typically faster, so there is a trade off.
[Zhang et. al., 2015] proposes one method for distributed SGD called elastic-averaged SGD. The paper goes through a stability analysis characterizing the behavior of the gradients under different communication constraints. It gets a little heavy, but it might shed some light on why you see this behavior.
Edit: regarding whether the loss should be lower for the higher accuracy, it is going to depend on a couple of things. First, I am assuming that you are using softmax cross-entropy for your loss (as stated in the deep_cnn tutorial you linked), and assuming accuracy is the total number of correct predictions divided by the total number of samples. In this case, a lower loss on the same dataset should correlate to a higher accuracy. The emphasis is important.
If you are reporting loss during training but then report accuracy on your validation (or testing) dataset, it is possible for these two to be only loosely correlated. This is because the model is fitting (minimizing loss) to a certain subset of your total samples throughout the training process, and then tests against new samples that it has never seen before to verify that it generalizes well. The loss against this testing/validation set could be (and probably is) higher than the loss against the training set, so if the two numbers are being reported from different sets, you may not be able to draw comparisons like "loss for 1 GPU case should be lower since its accuracy is lower".
Second, if you are distributing the training then you are calculating losses across multiple workers (I believe), but only one accuracy at the end, again against a testing or validation set. Maybe the loss being reported is the best loss seen by any one worker, but overall the average losses were higher.
Basically I do not think we have enough information to decisively say why the loss and accuracy do not seem to correlate the way you expect, but there are a number of ways this could be happening, so I wouldn't dismiss it out of hand.
I've also encountered this issue.
See Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour from Facebook which addresses the same issue. The suggested solution is simply to scale up the learning rate by k (after some reasonable warm-up epochs) for k GPUs.
In practice I've found out that simply summing up the gradients from the GPUs (rather than averaging them) and using the original learning rate sometimes does the job as well.
on tensorflow.org in the beginner-mnist tutorial they train with 1000 steps, 100 examples. Which is more than the training set which only includes 55,000 points ? In the expert-mnist tutorial they train with 20000 steps, 50 examples.
I think the training steps are done, so that one could every training step make a print-output what loss or/and accuracy one got without waiting till the end or processing.
But could one also simply pipe all examples through the train_operation in 1 step and then look at the outcome, or is not possible ?
Training on the whole dataset at each iteration is called batch gradient descent. Training on minibatches (e.g. 100 samples at a time) is called stochastic gradient descent. You can read more about the two and the reasons for choosing larger or smaller batch sizes in this question on Cross Validated.
Batch gradient descent typically isn't feasible because it requires too much RAM. Each iteration will also take significantly longer and the tradeoff often isn't worth it even if you have the computational resources.
That said, the batch size is a hyperparameter that you can play around with to find a value that works well.