I am playing around with Progressive Growing of Gans network from Karras et al. (NVIDIA). I trained the network on a different dataset on 2x 1080 Ti cards, using the NCHW mode for all convolutions as seen here.
Now I have a trained model and I want to use the code snippet from the project's readme to import the trained network - which is mentioned in the Importing and using pre-trained networks section.
However, when I try to run it on a PC with a CPU only, the network fails with the error:
InvalidArgumentError (see above for traceback): Conv2DCustomBackpropInputOp only supports NHWC.
[[node Gs/Run/Gs/cond/8x8/Conv0_up/conv2d_transpose (defined at <string>:93) ]]
I know that the CPU does not have NCHW implemented, but I would like to know how can I work around this? I see several options out of which I do not want any:
The first thing that comes to mind is to just use the NHWC mode for generating a new image, even though the network was trained in NCHW. This, however, if I am correct, will mess up the layer's weights, since it was trained on NCHW.
I do not want to train the whole network in NHWC mode, since it should be slower than NCHW? I do not use the cuDNN from NVidia, does it mean that those two modes are the same speed then, according to this?
What else can I do? Thank you!
Related
I faced problem regarding Yolo object detection deployment on TX2.
I use pre-trained Yolo3 (trained on Coco dataset) to detect some limited objects (I mostly concern on five classes, not all the classes), The speed is low for real-time detection, and the accuracy is not perfect (but acceptable) on my laptop. I’m thinking to make it faster by multithreading or multiprocessing on my laptop, is it possible for yolo?
But my main problem is that algorithm is not running on raspberry pi and nvidia TX2.
Here are my questions:
In general, is it possible to run yolov3 on TX2 without any modification like accelerators and model compression techniques?
I cannot run the model on TX2. Firstly I got error regarding camera, so I decided to run the model on a video, this time I got the 'cannot allocate memory in static TLS block' error, what is the reason of getting this error? the model is too big. It uses 16 GB GPU memory on my laptop.The GPU memory of raspberry and TX2 are less than 8GB. As far as I know there are two solutions, using a smaller model or using tensor RT or pruning. Do you have any idea if there is any other way?
if I use tiny-yolo I will get lower accuracy and this is not what I want. Is there any way to run any object detection model with high performance for real-time in terms of both accuracy and speed (FPS) on raspberry pi or NVIDIA TX2?
If I clean the coco data for just the objects I concern and then train the same model, I would get higher accuracy and speed but the size would not change, Am I correct?
In general, what is the best model in terms of accuracy for real-time detection and what is the best in terms of speed?
How is Mobilenet? Is it better than YOLOs in terms of both accuracy and speed?
1- Yes it is possible. I already run Yolov3 on Jetson Nano.
2- It depends on model and input resolution of data. You can decrease input resolution. Input images are transferred to GPU VRAM to use on model. Big input sizes can allocate much memory. As far as I remember I have run normal Yolov3 on Jetson Nano(which is worse than tx2) 2 years ago. Also, you can use Yolov3-tiny and Tensorrt as you mention. There are many sources on the web like this & this.
3- I suggest you to have a look at here. In this repo, you can make transfer learning with your dataset & optimize the model with TensorRT & run it on Jetson.
4- Size not dependent to dataset. It depend the model architecture(because it contains weights). Speed probably does not change. Accuracy depends on your dataset. It can be better or worser. If any class on COCO is similiar to your dataset's any class, I suggest you to transfer learning.
5- You have to find right model with small size, enough accuracy, gracefully speed. There is not best model. There is best model for your case which depend on also your dataset. You can compare some of the model's accuracy and fps here.
6- Most people uses mobilenet as feature extractor. Read this paper. You will see Yolov3 have better accuracy, SSD with MobileNet backbone have better FPS. I suggest you to use jetson-inference repo.
By using jetson-inference repo, I get enough accuracy on SSD model & get 30 FPS. Also, I suggest you to use MIPI-CSI camera on Jetson. It is faster than USB cameras.
I fixed the problem 1 and 2 only by replacing import order of the opencv and tensorflow inside the script.Now I can run Yolov3 without any modification on tx2. I got average FPS of 3.
I am using the tensorflow centernet_resnet50_v2_512x512_kpts_coco17_tpu-8 object detection model on a Nvidia Tesla P100 to extract bounding boxes and keypoints for detecting people in a video. Using the pre-trained from tensorflow.org, I am able to process about 16 frames per second. Is there any way I can imporve the evaluation speed for this model? Here are some ideas I have been looking into:
Pruning the model graph since I am only detecting 1 type of object (people)
Have not been successful in doing this. Changing the label_map when building the model does not seem to improve performance.
Hard coding the input size
Have not found a good way to do this.
Compiling the model to an optimized form using something like TensorRT
Initial attempts to convert to TensorRT did not have any performance improvements.
Batching predictions
It looks like the pre-trained model has the batch size hard coded to 1, and so far when I try to change this using the model_builder I see a drop in performance.
My GPU utilization is about ~75% so I don't know if there is much to gain here.
TensorRT should in most cases give a large increase in frames per second compared to Tensorflow.
centernet_resnet50_v2_512x512_kpts_coco17_tpu-8 can be found in the TensorFlow Model Zoo.
Nvidia has released a blog post describing how to optimize models from the TensorFlow Model Zoo using Deepstream and TensorRT:
https://developer.nvidia.com/blog/deploying-models-from-tensorflow-model-zoo-using-deepstream-and-triton-inference-server/
Now regarding your suggestions:
Pruning the model graph: Pruning the model graph can be done by converting your tensorflow model to a TF-TRT model.
Hardcoding the input size: Use the static mode in TF-TRT. This is the default mode and enabled by: is_dynamic_op=False
Compiling the model: My advise would be to convert you model to TF-TRT or first to ONNX and then to TensorRT.
Batching: Specifying the batch size is also covered in the NVIDIA blog post.
Lastly, for my model a big increase in performance came from using FP16 in my inference engine. (mixed precision) You could even try INT8 although then you first have to callibrate.
in order to do fast CPU inference of a frozen Tensorflow graph (.pb) I am currently using Tensorflow's C API. The inference speed is already fairly good, however (compared to CPU-specific tools like Intel's OpenVINO) I have so far no possibility to somehow optimize the graph before running it. I am interested in any sort of optimization that is suitable:
- device-specific optimization for CPU
- graph-specific optimization (fusing operations, dropping out nodes, ...)
- ... and everything else lowering the time required for inference.
Therefore I am looking for a way to optimize graphs after training and before execution. As mentioned, Tools like Intel's OpenVINO (for CPUs) and NVIDIA's TensorRT (for GPUs) do stuff like that. I am also working with OpenVINO but currently waiting for a bug fix so that I would like to try an additional way.
I thought about trying Tensorflow XLA, but I have no experience using it. Moreover I have to make sure to either get a frozen graph (.pb) or something that I can convert to a frozen graph (e.g. .h5) in the end.
I would be grateful for recommendations!
Greets
follow these steps:
freeze tensorflow trained model (frozen_graph.pb) - for that you may required trained model .pb, checkpoints & output node names
optimize your frozen model with Intel OpenVINO model optimizer -
python3 mo.py --input_model frozen_graph.pb
Additionally you may required input_shape
you will get .xml & .bin files as result. with the help of benchmark_app, you can check inference optimisation .
I'm using the Tensorflow (using the Keras API) in Python 3.0. I'm using the VGG19 pre-trained network to perform style transfer on an Nvidia RTX 2070.
The largest input image that I have is 4500x4500 pixels (I have removed the fully-connected layers in the VGG19 to allow for a fully-convolutional network that handles arbitrary image sizes.) If it helps, my batch size is just 1 image at a time currently.
1.) Is there an option for parallelizing the evaluation of the model on the image input given that I am not training the model, but just passing data through the pre-trained model?
2.) Is there any increase in capacity for handling larger images in going from 1 GPU to 2 GPUs? Is there a way for the memory to be shared across the GPUs?
I'm unsure if larger images make my GPU compute-bound or memory-bound. I'm speculating that it's a compute issue, which is what started my search for parallel CNN evaluation discussions. I've seen some papers on tiling methods that seem to allow for larger images
I have two Nvidia Titan X cards on my machine and want to finetune COCO pretrained Inception V2 model on a single specific class. I have created the train/val tfrecords and changed the config to run the tensorflow object detection training pipeline.
I am able to start the training but it hangs (without any OOM) whenever it tries to evaluate a checkpoint. Currently it is using only GPU 0 with other resource parameters (like RAM, CPU, IO etc) in normal range. So I am guessing that GPU is the bottleneck. I wanted to try splitting training and validation on separate GPUs and see if it works.
I tried to look for a place where I could do something like setting "CUDA_VISIBLE_DEVICES" differently for both the processes but unfortunately the latest tensorflow object detection API code (using tensorflow 1.12) makes it very difficult to do so. I am also unable to verify my assumption about training and validation running in same process as my machine hangs. Could someone please suggest where to look for to solve it?