View Source Changelog

v0.4.0-rc4 (2026-08-21)

Browse the Repository | Released Assets

Two processes sharing one interpreter used to get each other's answers -- silently, without a crash, 147 times in 400 on a real model. Most of this release is about that, and about checking that a downloaded binary is the one we published.

Added

  • tflite_beam_interpreter_server, an interpreter that lives inside a process so that feeding it, running it and reading the result back is one step nothing can interleave with. Concurrent callers are serialised by the process and each gets the answer to its own input.

    The direct API mirrors TfLite's C API faithfully, and that is the problem it is answering: nothing in the C API says those three calls have to be treated as one operation. Two processes taking turns badly get each other's results -- measured on a real model, 147 wrong answers in 400 calls, silently and without a crash. The direct API is unchanged for callers who would rather serialise access themselves.

  • tflite_beam_interpreter:controlling_process/1,2, following gen_tcp:controlling_process/2: while an interpreter belongs to nobody any process may take it, and once it belongs to someone only that process may hand it on. Every other process is then refused. A controlling process that dies releases it, since an interpreter has no equivalent of a socket being closed. Interpreters start out belonging to nobody, which is how they have always behaved.

Changed

  • Calls into one interpreter that genuinely overlap in time are now refused instead of being allowed to race. Two processes sharing an interpreter used to reach TfLite on two OS threads at once with nothing in the way; the second one is now told. This is the only change here that alters existing behaviour, and only for code that was already racing.

Security

  • Precompiled tarballs are checked against a sha256 manifest before being unpacked. They were written to disk and extracted unverified, while every comparable BEAM package -- evision, xla, emlx -- verifies. The manifest, checksum.term, ships inside the package, because a checksum fetched alongside the thing it vouches for vouches for nothing.

    A tarball that does not match is deleted and the build fails, rather than being left in the cache to fail identically forever. The cached path is checked too: a tarball that was already on disk has no more claim to being the right one than a freshly fetched one. A checkout with no manifest -- a git tag, whose tarballs are built after it exists -- says so loudly and carries on, since the manifest is the trust root rather than something to fetch.

v0.4.0-rc3 (2026-08-19)

Browse the Repository | Released Assets

Delegates. A delegate is now a thing you can hold, configure and attach, rather than something TfLite did to your model without telling you -- and any vendor's delegate library can be loaded at runtime, the Edge TPU included.

Still a release candidate: the one behaviour change here, XNNPACK moving from TfLite's invisible lazy application to an explicit attachment at build time, is worth having in the open before it becomes 0.4.0.

Added

  • tflite_beam_interpreter_builder:add_delegate/2,3, and the delegate resource behind it. This is the attachment point rather than a usable feature yet: nothing in this release constructs a delegate, so the constructors arrive with the delegate kinds themselves. A delegate is kept alive by the builder and by every interpreter built from it, for as long as either needs it, which is why there is no way to detach or free one -- an early release is exactly the use-after-free class that 0.4.0-rc2 spent its time removing.

  • add_delegate/3 takes #{on_decline => error | fallback}. TfLite reports a delegate that cannot take the graph, but leaves it runnable, as kTfLiteApplicationError, and then discards the whole interpreter -- so without this a delegate that merely does not fit turns build/2 into an error with no interpreter at all, where a C++ caller would still hold a working CPU one. error, the default, keeps that loud. fallback builds again without the delegates that were added with it and answers {ok, delegate_declined}; nothing else is retried.

  • tflite_beam_delegate:available/0, reporting which delegate kinds were compiled into this build. It answers "was it compiled in", not "is a device present" -- those have different answers on the same binary. It lists xnnpack everywhere except armv6 and armv7l, where XNNPACK is not compiled in at all, and external on every target, since loading a plugin needs nothing but the dynamic loader.

  • tflite_beam_delegate:xnnpack/0,1, with num_threads, flags and weight_cache_file_path. Flags are atoms mapped by name -- qs8, force_fp16, disable_subgraph_reshaping and the rest -- and are added to XNNPACK's defaults rather than replacing them, because TfLite spells turning a default off as its own flag. Nothing positional would be right in any case: one bit in the middle of the range is unassigned.

  • tflite_beam_coral:edge_tpu_delegate/0,1, which reaches an Edge TPU the same way as any other delegate. libedgetpu has always been a TfLite delegate plugin -- the bundled runtime exports tflite_plugin_create_delegate and tflite_plugin_destroy_delegate -- so this is external/2 pointed at it, plus a default path to the copy in priv/libedgetpu. Pass lib_path to name a runtime installed elsewhere, which is how a build made without Coral support can still reach a device.

    What it buys over make_edge_tpu_interpreter/2, which is unchanged and still works: that function builds its own interpreter internally, so nothing set on a builder ever reaches it -- neither set_num_threads/2 nor any other delegate. Going through the plugin puts an Edge TPU interpreter on the ordinary builder path. Both routes were checked to produce byte-identical output on a USB Coral accelerator with libedgetpu 0.1.14 on macOS arm64, and asking for a device that is not attached is an ordinary error rather than a crash.

  • tflite_beam_delegate:external/1,2, which loads a delegate out of any shared library implementing TfLite's plugin interface -- Edge TPU, a GPU delegate built elsewhere, a vendor delegate this library has never heard of. Options are handed over as strings, since that is the whole of the plugin ABI, so atoms and integers are converted and at most 256 pairs fit.

    It does not go through TfLiteExternalDelegateCreate. That function returns a pointer into a wrapper whose delegate it fills in only when the library loaded and the plugin returned a delegate, so a missing file, a library that is not a plugin, or a plugin that declines -- no device attached, say -- all hand back a non-null delegate whose Prepare is indeterminate. Attaching one of those jumps through a wild function pointer and takes the emulator with it. The plugin is loaded here instead, which has no such gap and gives every failure a name, including the plugin's own explanation of why it refused.

  • tflite_beam_ops_builtin_builtin_resolver:new/1 takes #{apply_default_delegates => boolean()}, deciding whether TfLite may apply its own delegates lazily inside allocate_tensors/1.

Changed

  • XNNPACK is now attached explicitly, by tflite_beam_interpreter_builder:build/2, instead of being applied invisibly by TfLite inside allocate_tensors/1. The acceleration is the same and so is the output; what changes is that the delegation is visible in the execution plan as soon as build/2 returns rather than only after allocation, and that it can be configured or declined at all. set_num_threads/2 still reaches XNNPACK: the delegate is built with the builder's thread count, or with one thread when it was never set, which is what TfLite's own default has always been.

    Attach your own delegate and the default is not added. Ask the resolver for #{apply_default_delegates => true} and TfLite goes back to delegating by itself. On armv6 and armv7l, where XNNPACK is not compiled in, nothing is attached and nothing errors.

  • tflite_beam_interpreter_builder:build/2 and tflite_beam_interpreter:allocate_tensors/1 now run on a dirty CPU scheduler. Every delegate's Prepare and all of TfLite's graph partitioning happen inside those two, which is more than a regular scheduler should be asked to hold. coral_make_edgetpu_interpreter/2, which does build, delegate and allocate in one call, was already classified this way.

Documented

  • An interpreter, and any delegate attached to it, belongs to one process at a time. This was already true -- invoke/1 has run on a dirty scheduler for a long time, and there is no lock anywhere in the bindings -- it was simply never written down.

v0.4.0-rc2 (2026-08-19)

Browse the Repository | Released Assets

Bug fixes only, no new API. Three of these interlock: a build that fails without saying so produces an empty interpreter, a guard that was supposed to reject empty interpreters waves it through, and the next accessor call takes the VM down with it. None of the three needs anything unusual to reach.

Changed

  • tflite_beam_interpreter_builder:build/2 returns {error, Reason} when the build fails. It returned ok unconditionally and discarded the status TFLite handed it, so a model that could not be built reported success and left an empty interpreter behind. Code that matched ok = build(...) on a model that was quietly failing will now fail at that match, which is the point.

    In tflite_elixir this reaches TFLiteElixir.InterpreterBuilder.build!/2, which starts raising through deferror where callers used to meet a MatchError further down. That suite has no negative test for build/2 -- every call site in it is a happy path -- so nothing there will notice the difference.

Fixed

  • Reaching into an interpreter that a failed build/2 had emptied killed the VM with SIGSEGV. Every resource accessor set an error term when it found a null value and then returned the resource anyway, while every caller tests only the returned pointer, so the guard passed and the next line dereferenced null. All eight of them now return nothing, and the calls that used to crash return {error, Reason}.

  • build/2 no longer leaves previously fetched tensors pointing into freed memory. TFLite destroys the interpreter it is building into on the way in -- before it can fail, so this applies to failed builds too -- but the tensor handles cached by tflite_beam_interpreter:tensor/2 were never cleared. Fetching a tensor and then building again was a use-after-free.

  • Tensor handles now report that their interpreter has gone instead of reading freed memory. The interpreter marked each cached tensor when it was torn down, but nothing ever read that mark: all six NIFs taking a tensor checked only that its pointer was non-null, which a dangling pointer is.

    This is visible in one more place than the two above: a handle does not keep its interpreter alive, so reading through one whose interpreter has already been collected now returns {error, Reason}' where it used to return whatever was left in the freed memory. Keep the interpreter reachable for as long as its tensors are in use -- which is what the code doing this correctly already does, or it would have been crashing. ### Added - A test suite,rebar3 ct, covering model loading, the builder, interpreters, tensors, invocation and signature runners, along with the failure cases above. It runs in CI on Linux x86_64 and macOS arm64. The four model fixtures it uses come from TensorFlow's own testdata and live intest/, which is not part of the published package. ## v0.4.0-rc1 (2026-08-19) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.4.0-rc1) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.4.0-rc1) A release candidate. Everything here is new surface rather than changed behaviour, but it is a lot of it at once, so it is worth a look before it becomes 0.4.0. Depend on it explicitly -- a pre-release is not picked up by a requirement like"~> 0.3". ### Added - Signature runners. A model's signatures could be listed withinterpreter:signaturekeys/1andget_signature_defs/1, but there was no way to run one, so tensors still had to be addressed by index and the order of a model's outputs guessed at.tflite_beam_interpreter:get_signature_runner/2now returns a runner, andtflite_beam_signature_runnerdrives it: names and counts of its inputs and outputs, reading and writing them by name, resizing them, allocating, invoking and cancelling. Passingnilas the key asks for the primary subgraph, which works on models that declare no signatures at all, so this is usable with older exports too. A runner belongs to the interpreter that handed it out and holds a reference to it, so it stays usable even after the interpreter's own term is collected. Like the interpreter it is not safe to use from several processes at once. -tflite_beam_interpreter:enable_cancellation/1andcancel/1. An invocation runs on a dirty scheduler and could not be interrupted;cancel/1does not block and is safe to call from another process, so a long inference can now be given up on. Withoutenable_cancellation/1beforehand, cancelling is an error. -tflite_beam_interpreter:release_non_persistent_memory/1, which hands back the memory that is only needed while invoking. Invoking again reallocates it, trading time for memory on devices short of the latter. -tflite_beam_interpreter:reset_variable_tensors/1, resetting all of a model's variable tensors. Only a single-tensor version existed. -tflite_beam_interpreter:get_allow_fp16_precision_for_fp32/1andset_allow_fp16_precision_for_fp32/2. -tflite_beam_interpreter:signature_inputs/2,signature_outputs/2,get_subgraph_index_from_signature/2andsubgraphs_size/1, which describe a model's signatures and subgraphs without having to build a runner. -tflite_beam_interpreter:resize_input_tensor/3andresize_input_tensor_strict/3. Input shapes could not be changed at all before, so a model with a variable dimension could only ever be fed whatever shape it was exported with. Callallocate_tensors/1again afterwards. The strict variant only touches dimensions the model left unknown. -tflite_beam_flatbuffer_model:verify_and_build_from_buffer/1,2. A verifying counterpart existed for files but not for buffers, so a model already in memory could only be built unchecked. ### Fixed - Theminimum_runtimefield of thetflite_beam_flatbuffer_modelrecord held a boolean. Three of the four places that fill the record askedflatbuffer_model_initializedfor it, so anyone reading the field to decide whether a runtime is new enough was readingtrue. - Building a model from a buffer no longer leaks the copy of that buffer when the model turns out not to parse. ## v0.3.12 (2026-08-19) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.12) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.12) ### Fixed - Interpreters, interpreter builders and the resources they borrow (the op resolver and the flatbuffer model) now hold real references to each other. Previously only a hand-rolled counter recorded the link, so the VM was free to collect a resource that was still in use, and the destructor's decrement landed in whatever resource had been given that memory next. On arm64 this brought down the emulator with SIGBUS. - Resources are no longer read uninitialised.enif_alloc_resourcehands back raw memory, so fields that looked initialised in the struct definition were not, andNifResTfLiteTensorcould reachdeleteon a wild pointer. - Everytflite::FlatBufferModeland everytflite::Interpreterwas leaked; both are now released with the resource that owns them. - Creating an Edge TPU interpreter no longer leaks its resource when the interpreter cannot be built or its tensors cannot be allocated. - Tensor resources are no longer leaked. Each one was created with a reference that nobody ever gave back, on top of the one the interpreter's cache holds, so none of them could be freed. Failing partway through reading a tensor leaked one as well. - Edge TPU context resources are no longer leaked, for the same reason: the reference fromenif_alloc_resourcewas never released. -allocate_tensorsno longer reportsunknown errorfor three of the statuses TFLite can return. A model carrying ops the interpreter cannot resolve -- an Edge TPU model given to a plain builtin resolver, say -- now saysUnresolvedOpsinstead. The mapping lived in two places, one of which had drifted; there is now only one. - The Edge TPU itself is handed back when nothing is using it any more. Contexts were parked in a global map that was written to and never read, purely so theirshared_ptrcould not run out, which held the device until the VM exited. Each context resource now owns its share directly, and an Edge TPU interpreter holds a reference to the context it delegates to, so the device outlives every interpreter built on it and is released once the last one is gone. ## v0.3.11 (2026-08-15) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.11) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.11) ### Fixed - Platform-specific binaries now go to the consuming app's_build/<target><env>/lib/tflitebeam/privinstead ofdeps/tflitebeam/priv, so switchingMIX_TARGETno longer picks up another target'stflite_beam.so.rm -rf deps/tflite_beamis no longer needed when cross-compiling ([#73](https://github.com/cocoa-xu/tflite_beam/issues/73)). - Building from source no longer fails on hosts that have gflags installed system-wide (e.g.brew install gflags). glog resolved gflags throughfind_package, which picked up the system copy and collided with the targets the bundled gflags had already defined. ## v0.3.10 (2026-06-30) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.10) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.10) ### Changed - [deps] Use libedgetpu v0.1.14. - Use tensorflow v2.21.0. ## v0.3.9 (2025-04-03) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.9) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.9) ### Changed - [deps] Use libedgetpu v0.1.12. - Use tensorflow v2.19.0. ## v0.3.8 (2025-02-10) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.8) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.8) ### Changed - [deps] Use libedgetpu v0.1.10. - Use tensorflow v2.18.0. ## v0.3.7 (2024-09-03) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.7) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.7) ### Fixed - fixed project build directory ## v0.3.6 (2024-03-17) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.6) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.6) ### Changed - [deps] Use libedgetpu v0.1.9. - Use tensorflow v2.16.1. - Use libusb v1.0.27. - Use Erlang/OTP 25.x for precompiled binaries. This unified the required Erlang/OTP NIF version to2.16for precompiled binaries. - Detect and useHTTP_PROXY,HTTPS_PROXY,http_proxyandhttps_proxywhen fetch preocmpiled binary from GitHub. ## v0.3.5 (2024-01-24) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.5) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.5) ### Changed - Precompiled version for armv6 devices. - RemovedTFBEAM_XNNPACK_ENABLE_ARM_I8MMoption as it should work as long as a newer C compiler is used. - Updated metadata_schema to 1.5.0 ## v0.3.4 (2024-01-23) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.4) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.4) ### Changed - [deps] Use libedgetpu v0.1.8. - Use tensorflow v2.15.0. ## v0.3.3 (2023-07-21) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.3) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.3) ### Changed - [deps] Use libedgetpu v0.1.7. - Use tensorflow v2.13.0. ## v0.3.2 (2023-04-03) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.2) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.2) ### Fixed - [precompiled-nerves] Guess correctTARGET_ARCHfromTARGET_CPU. ## v0.3.1 (2023-04-03) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.1) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.1) ### Fixed - [deps] Use libedgetpu v0.1.6. ### Changed - [examples] Examples moved to [cocoa-xu/tflite_elixir](https://github.com/cocoa-xu/tflite_elixir). ## v0.3.0 (2023-04-02) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.3.0) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.3.0) ### Breaking Change - This repo will now be the TensorFlow Lite Erlang bindings. For Elixir bindings, please visit [cocoa-xu/tflite_elixir](https://github.com/cocoa-xu/tflite_elixir). ### Fixed - [erlang] Generate correct error message from a list of errors. - [c_src] Initialize resource pointers withnullptr. - Implemented tokenizers for MobileBERT (#57) by @cocoa-xu. - [make] Ensure priv dir exist. ## v0.2.1 (2023-04-02) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.2.1) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.2.1) ### Changed - [deps] Use TensorFlow Lite version 2.11.1. ### Fixed - [erlang] Generate correct error message from a list of errors. - [c_src] Initialize resource pointers withnullptr. - Implemented tokenizers for MobileBERT (#57) by @cocoa-xu. - [make] Ensure priv dir exist. ## v0.2.0 (2023-03-30) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.2.0) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.2.0) ### Breaking Changes - Renamed root namespace fromTFLiteElixirtoTFLiteBEAM### Changes -bufferwill be copied and managed when usingTFLiteBEAM.FlatBufferModel.build_from_buffer/1. -TFLiteBEAM.TFLiteTensor.dims/1returns a list (following TensorFlow Lite's C++ API convention) whileTFLiteBEAM.TFLiteTensor.shape/1returns a tuple (folllowingnx's convention.) ### Added - Erlang support. - [example] added pose estimation example (#43) by @mnishiguchi - [example] use thunder model instead of lightning in pose estimation (#45) by @mnishiguchi - [example] added audio classification example - Experimental high-level moduleTFLiteBEAM.ImageClassification. ```elixir iex> alias TFLiteBEAM.ImageClassification iex> {:ok, pid} = ImageClassification.start("test/test_data/mobilenet_v2_1.0_224_inat_bird_quant.tflite") iex> ImageClassification.predict(pid, "test/test_data/parrot.jpeg") %{class_id: 923, score: 0.70703125} iex> ImageClassification.set_label_from_associated_file(pid, "inat_bird_labels.txt") :ok iex> ImageClassification.predict(pid, "test/test_data/parrot.jpeg") %{class_id: 923, label: "Ara macao (Scarlet Macaw)", score: 0.70703125} iex> ImageClassification.predict(pid, "test/test_data/parrot.jpeg", top_k: 3) [ %{class_id: 923, label: "Ara macao (Scarlet Macaw)", score: 0.70703125}, %{ class_id: 837, label: "Platycercus elegans (Crimson Rosella)", score: 0.078125 }, %{ class_id: 245, label: "Coracias caudatus (Lilac-breasted Roller)", score: 0.01953125 } ] ``` ## v0.1.7 (2023-03-22) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.1.7) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.1.7) ### Breaking Changes - DeprecatedTFLiteElixir.Interpreter.allocate_tensors!/1- Deprecated Access behaviour forTFLiteElixir.FlatBufferModel### Fixed - Properly implementedTFLiteElixir.FlatBufferModel.read_all_metadata/1`. ```elixir iex> filename = Path.join([__DIR, "test", "test_data", "mobilenet_v2_1.0_224_inat_bird_quant.tflite"]) iex> %FlatBufferModel{} = model = FlatBufferModel.build_from_buffer(File.read!(filename)) iex> TFLiteElixir.FlatBufferModel.read_all_metadata(model) %{ TFLITE_METADATA: %{ description: "Identify the most prominent object in the image from a known set of categories.", min_parser_version: "1.0.0", name: "ImageClassifier", subgraph_metadata: [ %{ input_tensor_metadata: [ %{ content: %{ content_properties: %{color_space: "RGB"}, content_properties_type: "ImageProperties" }, description: "Input image to be classified.", name: "image", process_units: [ %{ options: %{mean: [127.5], std: [127.5]}, options_type: "NormalizationOptions" } ], stats: %{max: [255.0], min: [0.0]} } ], output_tensor_metadata: [ %{ associated_files: [ %{ description: "Labels for categories that the model can recognize.", name: "inat_bird_labels.txt", type: "TENSOR_AXIS_LABELS" } ], description: "Probabilities of the labels respectively.", name: "probability", stats: %{max: [255.0], min: [0.0]} } ] } ] }, min_runtime_version: "1.5.0" } `` ### Changed - ImproveTFLiteElixir.TFLiteTensor.to_nx/2(#33) by @cocoa-xu - [doc] Improve doc for to_nx (#31) by @mnishiguchi ### Added - Implemented -FlatBufferModel.{list_associated_files/1,get_associated_file/2}-TFLiteElixir.Interpreter.signature_keys/1-TFLiteElixir.Interpreter.execution_plan/1-TFLiteElixir.Interpreter.new_from_buffer/1-TFLiteElixir.Interpreter.tensors_size/1-TFLiteElixir.Interpreter.variables/1-TFLiteElixir.Interpreter.set_variables/2-TFLiteElixir.Interpreter.set_inputs/2-TFLiteElixir.Interpreter.set_outputs/2- [example] object detection example (#40) by @mnishiguchi ## v0.1.6 (2023-03-19) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.1.6) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.1.6) ### Fixed - [edgetpu] Improved edgetpu context handling, and bumped libedgetpu_runtime_version to v0.1.5. Fixed [#30](https://github.com/cocoa-xu/tflite_beam/issues/30) ### Added - [example] artistic-style-transfer example (#27) @mnishiguchi ## v0.1.5 (2023-03-18) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.1.5) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.1.5) ### Breaking Changes - Deprecated functions: -TFLiteElixir.FlatBufferModel.initialized!/1-TFLiteElixir.FlatBufferModel.get_minimum_runtime!/1-TFLiteElixir.TFLiteTensor.tensor!-TFLiteElixir.TFLiteTensor.to_nx!-TFLiteElixir.TFLiteTensor.to_binary!-TFLiteElixir.FlatBufferModel.build_from_buffer!-TFLiteElixir.FlatBufferModel.get_full_signature_list-TFLiteElixir.Coral.get_edge_tpu_context/1now takes keyword options. ### Changes - [example] Improve Inference on TPU notebook (#15) @mnishiguchi - [example] Improve Inference on TPU notebook (#16) @mnishiguchi - Alias modules in tflite_interpreter (#17) @mnishiguchi - Rename elixir files based on module names (#18) @mnishiguchi - add moduledocs (#19) @mnishiguchi ### Fixed - Fixed a few places that could lead to segmentation fault. - [example] Fixed broken ESRGAN link, Visualize the result section in the "Super Resolution" notebook. Lock downtflite_elixirandevisionversion (#29) @mnishiguchi. - [typespec] Fixed typespec forTFLiteElixir.Coral.edge_tpu_devices/0(#22) @mnishiguchi. ### Added - [test] Unit tests forTFLiteElixir.Interpreter,TFLiteElixir.InterpreterBuilderandTFLiteElixir.Ops.Builtin.BuiltinResolver. - [example] Added intro text to super_resolution_example. (#26) @mnishiguchi. -TFLiteElixir.FlatBufferModel.error_reporter/1. -TFLiteElixir.FlatBufferModel.verify_and_build_from_file/2## v0.1.4 (2023-03-14) [Browse the Repository](https://github.com/cocoa-xu/tflite_beam/tree/v0.1.4) | [Released Assets](https://github.com/cocoa-xu/tflite_beam/releases/tag/v0.1.4) ### Breaking Changes - Snake case functions (#21) @mnishiguchi ### Changes - [example] Improve Inference on TPU notebook (#15) @mnishiguchi - [example] Improve Inference on TPU notebook (#16) @mnishiguchi - Alias modules in tflite_interpreter (#17) @mnishiguchi - Rename elixir files based on module names (#18) @mnishiguchi - add moduledocs (#19) @mnishiguchi ### Fixed - Fix compilation logic when not using precompiled binaries. ### Added - ImplementedTFLiteElixir.reset_variable_tensor/1. - Add support for armv6. ### Misc - Simple workaround for cortex-a53 and cortex-a57,vcvtaq_s32_f32`. ## v0.1.3 (2023-03-09) Browse the Repository | Released Assets ### Changes - Bump TFLite version to v2.11.0. ## v0.1.2 (2023-03-08) Browse the Repository | Released Assets First release on hex.pm.