- 12 8月, 2021 1 次提交
-
-
由 deqiangc 提交于
* Refactor Makefile: split the kernel test into its own Makefile.inc. After this change, only non-test kernel files are in Makefile. BUG=http://b/195938386 * Add copyright notice to Makefile.inc
-
- 11 8月, 2021 3 次提交
-
-
由 TFLM-bot 提交于
-
由 deqiangc 提交于
This also adds a Hifi3z test script. BUG=http://b/195937824
-
由 Artem Tsvetkov 提交于
* Makefiles and scripts update to work with embARC MLI Library 2.0 * Updated few files to meet repository changes.
-
- 10 8月, 2021 7 次提交
-
-
由 deqiangc 提交于
BUG=http://b/195937824Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 rockyrhodes 提交于
* Fix a couple of issues with the BUILD file caught with the Google buildifier check. * Add back in layering_check to see if buildifier is happy. BUG=
-
由 Nat Jeffries 提交于
-
由 Advait Jain 提交于
* Add special TARGET_ARCH=project_generation to cortex_m_generic. * This enables use to use the create_tflm_tree.py script correctly for all the examples. * The special behavior for project_generation is to also include the micro_speech example (and its dependencies) is the list of sources. * We do not want to have micro_speech dependencies as part of a non-project generation build because it means that libtensorflow-microlite.a will have kissfft symbols which can lead to symbol collisions. Also, improved the CI for project generation with cortex_m_generic, which needed some of the TF_LITE_REMOVE_VIRTUAL_DELETE calls to be moved from private to public sections. BUG=http://b/193823889 * addressed review comment. * Fix setting of the path with readable_run.
-
由 David Davis 提交于
* Add files from TfLite Added batch_matmul.h and tensor_utils_common.h that are needed for the BATCH_MATMUL operator. * Add FAQ section Add frequently asked questions section with regard to memory allocation and tensor structure manipulation. bug=Add FAQ to reference op porting document #383 Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 nyadla-sys 提交于
Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 Artem Tsvetkov 提交于
* Added Model Adaptation Tool to prepare models before use with embARC MLI Library 2.0 * Fixed formatting for adaptation_tool.py
-
- 07 8月, 2021 5 次提交
-
-
由 deqiangc 提交于
* Add a new test case for conv operator (#329) This new test case is based on issue #329 to increase coverage on optimized kernel's data precision for conv operator. In this test, input, output and filter are all 8 bits and filter tensor is of dimension 8x3x3x3 with different scales per output channel. TESTED= local test with x86 and HiFi4. * Move large test data variable into its own folder and use one flat top namespace instead of nested namespace. BUG=195779890
-
由 David Davis 提交于
* Add files from TfLite Added batch_matmul.h and tensor_utils_common.h that are needed for the BATCH_MATMUL operator. * Arduino library creation for CI build. Issue# 256 * fix bug with include file path flattening * fix examples path generation Some files in examples source and headers list are not in the examples directory. They can be tensorflow files or third-party files. The code is corrected so that these files end up inside the generated directory tree. Previously, these files were being placed outside the generated directory tree and were thus invisible to follow-on targeted generation scripts. * remove/revert files that go into the arduino-examples repo * Format with: ``` tensorflow/lite/micro/tools/ci_build/test_code_style.sh --fix_formatting ``` * request changes to PR * Removed symbolic link for micro_speech example from Makefile. Added additional include flags to Makefile. Adjusted header file transformations during base tree creation. * Fix formatting. * Move Arduino specific code to seperate repo Remove ARDUINO defines. Fix incorrect NDEBUG use. Issue #256 * Fix cortex_m_generic makefile Fix typo in cortex_m_generic makefile so that the correct list of header files is generated by the create_tflm_tree.py script. bug=Arduino library creation external to the tflite-micro repository #256 Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com> Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 Advait Jain 提交于
-
由 Advait Jain 提交于
-
由 Artem Tsvetkov 提交于
-
- 06 8月, 2021 3 次提交
-
-
由 David Davis 提交于
* Add files from TfLite Added batch_matmul.h and tensor_utils_common.h that are needed for the BATCH_MATMUL operator. * Arduino library creation for CI build. Issue# 256 * fix bug with include file path flattening * fix examples path generation Some files in examples source and headers list are not in the examples directory. They can be tensorflow files or third-party files. The code is corrected so that these files end up inside the generated directory tree. Previously, these files were being placed outside the generated directory tree and were thus invisible to follow-on targeted generation scripts. * remove/revert files that go into the arduino-examples repo * Format with: ``` tensorflow/lite/micro/tools/ci_build/test_code_style.sh --fix_formatting ``` * request changes to PR * Removed symbolic link for micro_speech example from Makefile. Added additional include flags to Makefile. Adjusted header file transformations during base tree creation. * Fix formatting. * Move Arduino specific code to seperate repo Remove ARDUINO defines. Fix incorrect NDEBUG use. Issue #256 Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com> Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 TFLM-bot 提交于
* Sync from upstream TF. * Fix build errors. * more fixes. * one more fix. Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 Nat Jeffries 提交于
-
- 05 8月, 2021 1 次提交
-
-
由 Nat Jeffries 提交于
* Fix typo in test_code_style.sh * Format python code. * Reset code style.
-
- 03 8月, 2021 4 次提交
-
-
由 Artem Tsvetkov 提交于
-
由 Advait Jain 提交于
* Remove files from the tflite_files list that should not be shared. This was added with https://github.com/tensorflow/tflite-micro/pull/134/. However, the correct approach would be to only pull in the portable implementations from: * https://github.com/tensorflow/tensorflow/blob/be7a4de6adfbd303ce08be4332554dff70362612/tensorflow/lite/kernels/internal/reference/portable_tensor_utils.cc * https://github.com/tensorflow/tensorflow/blob/be7a4de6adfbd303ce08be4332554dff70362612/tensorflow/lite/kernels/internal/reference/portable_tensor_utils.h * https://github.com/tensorflow/tensorflow/blob/be7a4de6adfbd303ce08be4332554dff70362612/tensorflow/lite/kernels/internal/reference/portable_tensor_utils_impl.h * Added the portable_tensor_utils to the files to sync.
-
由 David Davis 提交于
* Add files from TfLite Added batch_matmul.h and tensor_utils_common.h that are needed for the BATCH_MATMUL operator. * Arduino library creation for CI build. Issue# 256 * fix bug with include file path flattening * fix examples path generation Some files in examples source and headers list are not in the examples directory. They can be tensorflow files or third-party files. The code is corrected so that these files end up inside the generated directory tree. Previously, these files were being placed outside the generated directory tree and were thus invisible to follow-on targeted generation scripts. * remove/revert files that go into the arduino-examples repo * Format with: ``` tensorflow/lite/micro/tools/ci_build/test_code_style.sh --fix_formatting ``` * request changes to PR * Removed symbolic link for micro_speech example from Makefile. Added additional include flags to Makefile. Adjusted header file transformations during base tree creation. Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com> Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 Lauren Murphy 提交于
On commit 5c7c11e of the tensorflow repo at tensorflow/lite/micro/tools/make/Makefile:664, MICROLITE_CC_SRCS contains MICROLITE_CC_KERNEL_SRCS. In the new tflite-micro repo, it does not contain MICROLITE_CC_KERNEL_SRCS. This commit adds MICROLITE_CC_KERNEL_SRCS to tensorflow/lite/micro/examples/hello_world/zephyr_riscv/Makefile.inc so that the generated Zephyr CMakeLists.txt doesn't miss these files. Similar fix made to corresponding file for magic_wand sample. Signed-off-by: NLauren Murphy <lauren.murphy@intel.com> Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
- 29 7月, 2021 2 次提交
-
-
由 Pete Warden 提交于
* Add RISC-V badge to README * Fix badge label Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 TFLM-bot 提交于
Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
- 28 7月, 2021 7 次提交
-
-
由 Artem Tsvetkov 提交于
-
由 Pete Warden 提交于
* Fixes for RISCV build * Consolidate compiler flags * Added RISC-V continuous integration script * Added workflow for RISC-V CI action Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 cad-audio 提交于
* REF_CODE_REFACTOR: hard_swish Refactoring the reference code for hard_swish operator. BUG=refactoring existing code. * Remove uint8 support. * fix formatting. Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 cad-audio 提交于
* REF_CODE_REFACTOR: logicalAND and logicalOR Refactoring the reference code for logicalAND and logicalOR operators. BUG=refactoring existing code. * Fix formatting. * fix bad merge (copyright year). Co-authored-by: NAdvait Jain <advaitjain@google.com> Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 Pete Warden 提交于
* Fixes for RISCV build * Consolidate compiler flags * Added RISC-V continuous integration script Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com>
-
由 cad-audio 提交于
* REF_CODE_REFACTOR: logistic Refactoring the reference code for logistic operator. BUG=refactoring existing code. * Fix formatting Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com> Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 cad-audio 提交于
Updated the script to download HiFi 4 Neural Network Library v2.4.1. Removed the hifi4 patch Updates in v2.4.1 library: + Fixed the issue related to special case handling in xa_nn_dot_prod_16x16_asym8s. Moved the special cases handling for vec_length=8/32 to the start of the function. + Removed legacy condition checks for depthwise_conv kernels. + Fixed the non-bit-exact issue related to xa_nn_conv2d_std_per_chan_sym8sxasym8s. updated to select correct vec values in case of vec_align_val is 1 and
-
- 27 7月, 2021 3 次提交
-
-
由 Artem Tsvetkov 提交于
-
由 cad-audio 提交于
* REF_CODE_REFACTOR: activations.cc Refactoring the reference code for activations operators. BUG=refactoring existing code. * Remove uint8 support. * Ran `test_code_style.sh --fix_formatting` * Fix the build. Co-authored-by: NAdvait Jain <advaitjain@users.noreply.github.com> Co-authored-by: NAdvait Jain <advaitjain@google.com>
-
由 Pete Warden 提交于
* Fixes for RISCV build * Consolidate compiler flags
-
- 24 7月, 2021 4 次提交
-
-
由 TFLM-bot 提交于
-
由 Advait Jain 提交于
With http://cl/386537127 (tensorflow/tensorflow@d4987a9) we do not run into the type-limits warning and -Wno-type-limits can be removed. BUG=http://b/194523886
-
由 TFLM-bot 提交于
-
由 TFLM-bot 提交于
-