tflite-micro/tensorflow/lite/micro
Ryan Kuester bbf70db499
feat(compression): add SpecBuilder for programmatic compression specs (#3133)
Add a fluent builder API for creating compression specifications
without writing YAML strings. This is useful in scripts and
Jupyter notebooks.

Example usage:
    spec = (compression.SpecBuilder()
        .add_tensor(subgraph=0, tensor=2)
            .with_lut(index_bitwidth=4)
        .build())

BUG=#3125

Co-authored-by: suleshahid <110432064+suleshahid@users.noreply.github.com>
2025-07-10 16:32:57 -04:00
..
arc_custom
arc_emsdp
arena_allocator build(bazel): replace cc_* with tflm_cc_* in remaining TFLM code (#2768) 2024-11-15 05:08:54 +00:00
benchmarks build(bazel): replace cc_* with tflm_cc_* in remaining TFLM code (#2768) 2024-11-15 05:08:54 +00:00
bluepill
ceva
chre
compression feat(compression): add SpecBuilder for programmatic compression specs (#3133) 2025-07-10 16:32:57 -04:00
cortex_m_corstone_300
cortex_m_generic
docs docs: update compression documentation (#3020) 2024-12-17 23:37:12 +00:00
examples Remove deprecated BUILD tags (#3091) 2025-04-08 19:21:25 +00:00
hexagon
integration_tests Remove deprecated BUILD tags (#3091) 2025-04-08 19:21:25 +00:00
kernels Porting Reverse_V2 operator from TFLite (#3123) 2025-07-10 15:47:37 -04:00
memory_planner feat: enhance profiling and benchmarking (#3012) 2024-12-14 19:00:55 +00:00
models
python Remove deprecated BUILD tags (#3091) 2025-04-08 19:21:25 +00:00
riscv32_generic
testing Remove deprecated BUILD tags (#3091) 2025-04-08 19:21:25 +00:00
tflite_bridge
tools Porting Reverse_V2 operator from TFLite (#3123) 2025-07-10 15:47:37 -04:00
BUILD Missing build dep for hexdump. (#3096) 2025-04-20 14:44:45 +00:00
build_def.bzl Compression target build fixes (#3008) 2024-12-12 21:53:12 +00:00
compatibility.h
compression.h feat(compression): add decompression library (#2996) 2024-12-10 01:51:56 +00:00
debug_log.cc
debug_log.h
fake_micro_context.cc feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
fake_micro_context.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
fake_micro_context_test.cc
flatbuffer_utils.cc
flatbuffer_utils.h
flatbuffer_utils_test.cc
hexdump.cc Revert back from C/C++17 to C/C++11 (#3095) 2025-05-13 04:37:10 +00:00
hexdump.h Revert back from C/C++17 to C/C++11 (#3095) 2025-05-13 04:37:10 +00:00
hexdump_test.cc Revert back from C/C++17 to C/C++11 (#3095) 2025-05-13 04:37:10 +00:00
memory_arena_threshold_test.cc feat(compression): implement tensor decompression in op fully_connected (#3006) 2024-12-13 04:47:55 +00:00
memory_helpers.cc
memory_helpers.h
memory_helpers_test.cc
micro_allocation_info.cc
micro_allocation_info.h
micro_allocation_info_test.cc
micro_allocator.cc unchecked pointer fix (#3058) 2025-03-17 17:12:26 +00:00
micro_allocator.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_allocator_test.cc
micro_arena_constants.h
micro_common.h
micro_context.cc feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_context.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_graph.h
micro_interpreter.cc feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_interpreter.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_interpreter_context.cc Fix set_external_context() during state kInit (#3102) 2025-06-03 22:38:37 +00:00
micro_interpreter_context.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_interpreter_context_test.cc Fix set_external_context() during state kInit (#3102) 2025-06-03 22:38:37 +00:00
micro_interpreter_graph.cc Print invoke status on unsuccessful invocation (#2762) 2025-03-05 19:19:36 +00:00
micro_interpreter_graph.h
micro_interpreter_test.cc feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
micro_log.cc
micro_log.h
micro_log_test.cc
micro_mutable_op_resolver.h Porting Reverse_V2 operator from TFLite (#3123) 2025-07-10 15:47:37 -04:00
micro_mutable_op_resolver_test.cc
micro_op_resolver.cc
micro_op_resolver.h
micro_profiler.cc feat: enhance profiling and benchmarking (#3012) 2024-12-14 19:00:55 +00:00
micro_profiler.h feat: enhance profiling and benchmarking (#3012) 2024-12-14 19:00:55 +00:00
micro_profiler_interface.h
micro_resource_variable.cc feat(compression): allocate resource variables in persistent buffer (#3013) 2024-12-16 16:48:04 +00:00
micro_resource_variable.h feat(compression): allocate resource variables in persistent buffer (#3013) 2024-12-16 16:48:04 +00:00
micro_resource_variable_test.cc feat(compression): allocate resource variables in persistent buffer (#3013) 2024-12-16 16:48:04 +00:00
micro_time.cc
micro_time.h
micro_time_test.cc
micro_utils.cc
micro_utils.h feat(compression): implement tensor decompression in op depthwise conv (#3017) 2024-12-16 23:16:35 +00:00
micro_utils_test.cc
mock_micro_graph.cc
mock_micro_graph.h
recording_micro_allocator.cc feat(compression): handle tensor compression in RecordingMicroAllocator (#3011) 2024-12-13 23:37:19 +00:00
recording_micro_allocator.h feat(compression): handle tensor compression in RecordingMicroAllocator (#3011) 2024-12-13 23:37:19 +00:00
recording_micro_allocator_test.cc feat(compression): handle tensor compression in RecordingMicroAllocator (#3011) 2024-12-13 23:37:19 +00:00
recording_micro_interpreter.h
span.h
span_test.cc
static_vector.h
static_vector_test.cc
system_setup.cc
system_setup.h
test_helper_custom_ops.cc Add missing include in test_helper_custom_ops (#3009) 2024-12-13 18:28:08 +00:00
test_helper_custom_ops.h feat(compression): extend interpreter to handle compressed tensors (#3002) 2024-12-10 22:59:08 +00:00
test_helpers.cc Add 16bit support for unpack, transpose and comparisons operators (#3028) 2025-03-17 16:44:48 +00:00
test_helpers.h Add 16bit support for unpack, transpose and comparisons operators (#3028) 2025-03-17 16:44:48 +00:00
testing_helpers_test.cc