Is anyone aware of how long the training took to achieve the mAP and FPS of YoloV4 on the MS COCO dataset as referenced in https://github.com/AlexeyAB/darknet and the corresponding paper: https://arxiv.org/abs/2004.10934.
Trying to estimate training time and final mAP for RTX 3050 without running the full training, as it is projected to take ~1500 hours.
Have not been able to find any stats for how long the training took for the Tesla V100 and RTX 2070 referenced in the paper.
Ideally could take length of time RTX 2070 took and scale according to the difference in BFLOPS, and assume accuracy is roughly similar.
Related
Im training yolov4 tiny custom dataset, and suddenly loss and other markers drop to -nan
As you can see on the chart, all progress is lost after some iterations (around 800 iterations).
Yolov4 accuracy chart
Training log for given chart:
Darknet training log
Any ideas on given problem? It is running on ubuntu with 4 x GeForce GTX 1080 6GB.
When testing the same network on PC with single GeForce GTX 1060 6GB, it does not crash.
I'm running a Mask R-CNN model on an edge device (with an NVIDIA GTX 1080). I am currently using the Detectron2 Mask R-CNN implementation and I archieve an inference speed of around 5 FPS.
To speed this up I looked at other inference engines and model implementations. For example ONNX, but I'm not able to gain a faster inference speed.
TensorRT looks very promising to me but I did not found a ready "out-of-the-box" implementation for it.
Are there any other mature and fast inference engines or other techniques to speed up the inference?
It's almost impossible to get higher inference speed for Mask R-CNN on GTX 1080. You may check detectron2 by Facebook AI Research.
Otherwise, I'd suggest to use YOLACT - (You Only Look At CoefficienTs), it can achieve real-time instance segmentation.
On the other hand, if you don't need instance segmentation, you can use YOLO, SSD, etc for object detection.
OpenCV 4.5.0 with DNN_BACKEND_CUDA and DNN_TARGET_CUDA/DNN_TARGET_CUDA_FP16.
Mask RCNN with 1024 x 1024 input image
Device | FPS
------------------ | -------
GTX 1080 Ti (FP32) | 29
RTX 2080 Ti (FP16) | 60
FPS measured includes NMS but excludes other preprocessing and postprocessing. The network fully runs end-to-end on GPU.
Benchmark code: https://gist.github.com/YashasSamaga/48bdb167303e10f4d07b754888ddbdcf
As #kkHarshit already mentioned it is very hard to speed up a Mask R-CNN any further.
The fastest instance segmentation model that I found is YolactEdge: Real-time Instance Segmentation on the Edge (Jetson AGX Xavier: 30 FPS, RTX 2080 Ti: 170 FPS).
It's perfomance is worse than Mask R-CNN or Yolact even but still very good.
I'm new to deep learning. I wanted to build an image classifier using CNN to classify clothing images. I decided to train over the fashion MNIST-dataset which is a dataset of 60,000 images. But I'm aware that training is a very heavy task.
I wanted to know how long will my PC take to train over this dataset and should I go for pre-trained models instead with a compromise of accuracy.
My PC configurations are:
- Intel Core i5-6400 CPU # 2.70 GHz
- 8GB RAM.
- NVIDIA GeForce GTX 1050 Ti.
Even though it depends on data-set size & number of EPOCS(i tried with 50 Epocs) ,here it is small that is 32x32.
So for me when i tried on a machine with
Intel Core i7-6400 CPU # 2.70 GHz
8GB RAM.
NVIDIA GeForce GTX 1050 Ti.
with image size(28x28) as provided in MNIST dataset in Tensorflow.org it took less than 5 minutes.
I am running deep learning CNN (4-CNN layers and 3 FNN layers) model (written in Keras with tensorflow as backend) on two different machines.
I have 2 machines (A: with a GTX 960 graphics GPU with 2GB memory & clock speed: 1.17 GHz and B: with a Tesla K40 computation GPU with 12GB memory & clock speed: 745MHz)
But when I run the CNN model on A:
Epoch 1/35
50000/50000 [==============================] - 10s 198us/step - loss: 0.0851 - acc: 0.2323
on B:
Epoch 1/35
50000/50000 [==============================] - 43s 850us/step - loss: 0.0800 - acc: 0.3110
The numbers are not even comparable. I am quite new to deep learning and running code on GPUs. Could someone please help me explain why the numbers are so different?
Dataset: CIFAR-10 (32x32 RGB images)
Model batch size: 128
Model number of parameters: 1.2M
OS: Ubuntu 16.04
Nvidia driver version: 384.111
Cuda version: 7.5, V7.5.17
Please let me know if you need any more data.
Edit 1: (adding CPU info)
Machine A (GTX 960): 8 cores - Intel(R) Core(TM) i7-6700 CPU # 3.40GHz
Machine B (Tesla K40c):8 cores - Intel(R) Xeon(R) CPU E5-2637 v4 # 3.50GHz
TL;DR: Measure again with a larger batch size.
Those results do not surprise me much. It's a common mistake to think that an expensive Tesla card (or a GPU for that matter) will automatically do everything faster. You have to understand how GPUs work in order to harness their power.
If you compare the base clock speeds of your devices, you will find that your Xeon CPU has the fastest one:
Nvidia K40c: 745MHz
Nvidia GTX 960: 1127MHz
Intel i7: 3400MHz
Intel Xeon: 3500MHz
This gives you a hint of the speeds at which these devices operate and gives a very rough estimate of how fast they can crunch numbers if they would only do one thing at a time, that is, with no parallelization.
So as you see, GPUs are not fast at all (for some definition of fast), in fact they're quite slow. Also note how the K40c is in fact slower than the GTX 960.
However, the real power of a GPU comes from its ability to process a lot of data simultaneously! If you now check again at how much parallelization is possible on these devices, you will find that your K40c is not so bad after all:
Nvidia K40c: 2880 cuda cores
Nvidia GTX 960: 1024 cuda cores
Intel i7: 8 threads
Intel Xeon: 8 threads
Again, these numbers give you a very rough estimate of how many things these devices can do simultaneously.
Note: I am severely simplifying things: In absolutely no way is a CPU core comparable to a cuda core! They are very very different things. And in no way can base clock frequencies be compared like this! It's just to give an idea of what's happening.
So, your devices needs to be able to process a lot of data in parallel in order to maximize their throughput. Luckily tensorflow already does this for you: It will automatically parallelize all those heavy matrix multiplications for maximum throughput. However this is only going to be fast if the matrices have a certain size. Your batch size is set to 128 which means that almost all of these matrices will have the first dimension set to 128. I don't know the details of your model, but if the other dimensions are not large either, then I suspect that most of your K40c is staying idle during those matrix multiplications. Try to increase the batch size and measure again. You should find that larger batch sizes will make the K40c faster in comparison with the GTX 960. The same should be true for increasing the model's capacity: increase the number of units in the fully-connected layers and the number of filters in the convolutional layers. Adding more layers will probably not help here. The output of the nvidia-smi tool is also very useful to see how busy a GPU really is.
Note however that changing the model's hyper-parameter and/or the batch size will of course have a huge impact on how the model is able to train successfully and naturally you might also hit memory limitations.
Perhaps if increasing the batch size or changing the model is not an option, you could also try to train two models on the K40c at the same time to make use of the idle cores. However I have never tried this, so it might not work at all.
I'm experiencing running AlexNet model from here in TensorFlow for evaluating time spent on GPU by library, with the following parameters and hardware:
1024 images on train dataset
10 epochs with mini-batch sizes of 128
using GPU GTX Titan X
I stated that the real execution time on GPU is just a fraction of the all execution time of training (the graph belows compares TensorFlow and AlexNet vs Caffe and its AlexNet implementation)
(information captured with nvidia-smi. 'Porcentagem' means percentage and 'Tempo (s)' means time (seconds))
The GPU utilization rate oscilates frenetically between 0 and 100% in training. Why that? Caffe doesn't oscilates to much beyond 40%
Also, Tensorflow spent many time doing memory copy from Host to Device, while Caffe doesn't. But why?
(tensorflow)
(caffe)