Is Metal performing better than OpenCL and OpenGL (ES) when doing neural network computation?

Hello,
I am a newbie in iOS and Deep learning. I went through the basics of Deep learning and Neural networks. The documentation doesn't say how to use this library?

I have a model with me which was written using Caffe Framework. How can I integrate it with DeepLearningKit?

Any detailed documentation available online?

P.S
I ran the DeepLearningiOSDemo app which is working perfectly on my iPhone.

Any help would be appreciated.
Thank you.

Hi,

Thanks for open sourcing this great project.

I fine tuned Caffe's NIN with my own data, and tried to convert the model binary to json.

It successfully finished, but noticed data elements were skipped as follows.

46          if len(js_value) > 64 or (field.name == 'data' and len(js_value) > 8):
47              head_n = 5
48              js_value = js_value[:head_n] + ['(%d elements more)' % (len(js_value) - head_n)]

I commented out them, and produced the complete file.

Shouldn't they be commented out for DeepLearningKit?

I've been looking at a lot of MIT licensed based Swift AI and Deep Learning efforts and they are more than sufficient to do good work.

It begs the question, why the Apache License? Why not the MIT license?

If I build an App that uses the Google Cloud Platform and DeepLearningKit, aren't I under obligation, more obligation than MIT license, that prohibits my sale of the application or other requirements?

Hi,

I am trying to convert trained caffemodel of size 33MB to JSON for deeplearning kit using caffemodel2json.py, surprisingly the size of the JSON output file is 10x, in my case it comes to 330MB. I feel accommodating that big file on iOS app will not be feasible option. Could you please guide me on how to procceed with this? Is there a way to reduce the file size by configuring py script?

Thanks

Dear,

Thanks for sharing your code!
I'm running ios demo app on iPhone 6 and getting ~750ms. Is it ok? I saw your video and you got ~90ms...

Dear author, I have some question with metal programming about thread number and thread group number setting. I change the thredsPerGroup from (1,1,1) to (32,1,1), and change the threadGroups from
(1,1,1) to (number,1,1), where number is (vectorcount+31)/32. But I didn't see any change or improve at processing time. I wonder know did i do the right setting? thanks.

The DeepLearningKitForiOSDemoApp project file references bundle resources named "conv1.json" and "nin_cifar10_full.json", but fails to copy them to the application bundle because the files do not exist.

Probably just forgot to add these files to the github repository.

Hi,

I'm super stoked to see DeepLearningKit. It is a great starting point for neural nets using Metal and swift. I had this idea since Apple revealed Metal the first time and it is great to see that someone has started to work on it :)

For me personally as I start to experimenting with DeepLearningKit and thinking of integrating it into real apps the first thing that comes to mind is:

• Would be great if DeepLearningKit was a library (easy to drop into any project)
• A library with unit tests, bench-marking and other nice metrics
• CI support that supports the collaboration and fast evolution/development

I don't know if someone is already doing something familiar, but my plans are:

1. Turn DeepLearningKit in a library project
2. Add unit testing
3. Setup travis for CI - build and testing
4. Publish in CocoaPods and Carthage
5. Change the example code to use the library instead of the common files directly

Cheers,
Rafael

Convert to Swift 3

there is a caffe implementation of q learning on https://github.com/muupan/dqn-in-the-caffe/blob/master/dqn.prototxt - can perhaps be used.

main purpose would be to show that the q-learning loop i.e. the data input and the conv.net inside the q-learning algorithm is feasible to run on iphone. this can potentially be used to create better Game AI on e.g. Apple TV and iPhone/iPad

Quoting the contribute page:

DeepLearningKit is missing basic conversion from e.g. UIImage to RGB (the example network supports 32x32x3 CIFAR RGB Image Format, but has no conversion from UIImage to it). Check out e.g. Drawing Images From Pixel Data – In Swift and Image Processing in iOS Part 1: Raw Bitmap Modification for inspiration.

Just starting and hence not head first too much. But it may be the new Swift 3 break the whole thing. I covert it but there is lot of changes. and accept them does not work.

document json format, i.e. how other tools can convert conv.net into format that can be used directly in DeepLearningKit

I see in the code that
MetalTensorDimensions(n: weight_shape[0], channels: weight_shape[1], width: weight_shape[2], height: weight_shape[3]).
Shouldn't the width to be the last dimension since caffe uses a row-major format? It is fine when the image is squared but not the general case.

My mac OS version is Yousemite and do not support Metal.
Do we need El Captain to run this library on iOS?

Thank you for providing such an awesome library!

Hi,

I am getting error while converting the caffe model 2 json using caffemodel2json.py

Command run:
python ./caffemodel2json.py caffe-master/src/caffe/proto/caffe.proto bvlc_alexnet.caffemodel > dump.json

Error:

protobuf: calling protoc Traceback (most recent call last): File "./caffemodel2json.py", line 65, in <module> subprocess.check_call(['protoc', '--proto_path', os.path.dirname(args.caffe_proto), '--python_out', args.codegenDir, args.caffe_proto]) File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/subprocess.py", line 535, in check_call retcode = call(*popenargs, **kwargs) File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/subprocess.py", line 522, in call return Popen(*popenargs, **kwargs).wait() File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/subprocess.py", line 710, in __init__ errread, errwrite) File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/subprocess.py", line 1335, in _execute_child raise child_exception OSError: [Errno 2] No such file or directory

Could you please help with this.
Thanks

ref: https://github.com/DeepLearningKit/caffemodel2json

it is in prune-mode (to get a human-previewable/browsable json) - solution: comment out line 46-48