nntrainer
nntrainer copied to clipboard
nnstreamer
NNtrainer is Software Framework for Training Neural Network Models on Devices.
Initial implementaion of cache pool. It inherites from memory pool to utilize optimized memory information. And, swap device class is introduce. It operates with cache memory and keeps data permantly...
- [ ] Implement multi head attention - [x] implement forwarding - #1961 - [x] implement backwarding - #1963 - [ ] implement attention mask - [x] support float type...
- Check inplace for softmax is available and if it is implement inplace softmax
Commit1: [positional encoding] implement positional encoding layer - Positional encoding just needed to be calculated only once so make its lifespan as max lifespan Signed-off-by: hyeonseok lee Commi2: [unittest] generate...
It adds several annotations for memory profiling. Each of them can help to teach profile steps. Signed-off-by: Jiho Chu It depends on #1965
It proposes Memory Swap to reduce memory usage. Unused tensor data is swap-out to the external storage with its data, and it will be swap-in when it needs the data....
This patch includes implementation of sgemv function with ARM NEON. Later, more arm neon optimized function will be added **Self evaluation:** 1. Build test: [X]Passed [ ]Failed [ ]Skipped 2....
When it comes to think of the derivative of deviation(2) there are 2 incoming derivative. One from the variance(3) and the other from intermediate output(5). These 2 incoming derivative should...
Can this application be built along with gbs and/or pdebuild so that "nntrainer-example-alexnet.rpm/deb" can be published ? If that's possible, you can generate an automated memory & latency test easily:...
If layer name is changed which is get by getLayer(), We can not get the layer ussing getLayer() with the changed name. below is sudo code. and it is working...
Metadata
Owner
Metadata
NNtrainer is Software Framework for Training Neural Network Models on Devices.