deepC
deepC copied to clipboard
vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers
Current installation of deepC is over 10MiB. Explore if it can possibly fit in [micropython](https://micropython.org/) boards available.
Make sure that loops are being vectorized in operators GCC reference : https://gcc.gnu.org/projects/tree-ssa/vectorization.html LLVM reference : https://llvm.org/docs/Vectorizers.html
## Problem If we specify clang++ verison 8 in **[Makefile.common](https://github.com/ai-techsystems/dnnCompiler/blob/master/Makefile.common)** like this: ```Makefile /usr/bin/clang++-8 ``` It won't work in clang++-9 though version 9 is supported. But clang versions below 8...
### [CI/CD on Google Cloud](https://cloud.google.com/docs/ci-cd/) Look over to **[Tensorflow Official Build Status](https://github.com/tensorflow/tensorflow#continuous-build-status)**. We can have different badges for different mediums of deployment by using Google Cloud.
Test may not crash on internal machines, it consistently crashes on google colab - a platform we support. ## how to reproduce on Colab ``` !sudo apt-get update !sudo apt-get...
## [test / swig / tensorAssignmentOperators.py](https://github.com/ai-techsystems/dnnCompiler/blob/operators/test/swig/tensorAssignmentOperators.py) (Line No. 619, 627, 651) ### Here is the snippet of code ```python # float_tensor /= bool_scalar def test_Assignment_True_Div_float_tensor_bool_scalar (self): temp_np = self.np_float_0_4.copy() temp_np...
Watch https://www.youtube.com/watch?v=3TqN_M1L4ts on the value it adds to deepC
1. Either convert them into onnx and continue reading onnx **OR** 1. Read Tensorflow models natively.
How to Reproduce ============ **Step 1** Change gemm operator in *swig/dnnc.api* file to add int shown below: ``` tensor gemm(tensor &a, tensor &b, tensor &c, float alpha = 1.0, float...