blueoil
blueoil copied to clipboard
blue-oil
Bring Deep Learning to small devices
## What this patch does to fix the issue. I converted blueoil/layer with the command line tool tf_upgrade_v2 to run on tensorflow2. Since tf.contrib is not supported, I change it...
In `Base` dataset class, `classes`, `num_classes`, `extend_dir` are defined as static method. So when we want to change those method, we must duplicate Dataset Class. Sometimes this is inconvenient. For...
For example, memory layout of weights of kernels will be one of three layouts: `OHWI` (Arm w/ NEON, , x86 w/ AVX2), `HWOI` (generic), `ChHWBCl` (w/ FPGA). Since converter doesn't...
Now test is not perfect for configuration of aarch64 CPU with FPGA. The test is only applied for building binaries like `lm_aarch64_fpga.elf`, `libdlk_aarch64_fpga.so` and `libdlk_aarch64_fpga.a`. We need to run those...
## Introduction We don't really need GPU for `convert` part, but the current docker image provided by us needs GPU driver to run. I think it is better to provide...
The IOU calculation method used in Object Detection, etc. is not used in Blueoil. It does not seem to be consistent. This could produce differences in learning and inference results...
This network is experimental, so far it could not run on FPGAs. ## Description This network brings several recent ideas to our YOLOv2 implementation. In short, GlazedYolo = YoloV2 +...
## What this patch does to fix the issue. Conversion between floating point value :left_right_arrow: decimal string representation cause some small error. In this pull request, I removed floating point...
## Motivation and Context Debug options should not be default, so I made the time measurement feature a togglable option for the blueoil.sh script. For running `make` inside of the...
## Motivation and Context Scale augmentation is an important augmentation especially for detection tasks. This PR implements Scale class to support scale augmentation for all existing tasks. ## Description -...
