| /tflite-micro-3.4.0-2.7.6/third_party_static/flatbuffers/include/flatbuffers/ |
| D | stl_emulation.h | 86 using numeric_limits = std::numeric_limits<T>;
139 template <typename T> using is_scalar = std::is_scalar<T>;
140 template <typename T, typename U> using is_same = std::is_same<T,U>;
141 template <typename T> using is_floating_point = std::is_floating_point<T>;
142 template <typename T> using is_unsigned = std::is_unsigned<T>;
143 template <typename T> using is_enum = std::is_enum<T>;
144 template <typename T> using make_unsigned = std::make_unsigned<T>;
146 using conditional = std::conditional<B, T, F>;
148 using integral_constant = std::integral_constant<T, v>;
151 template <typename T> using is_scalar = std::tr1::is_scalar<T>;
[all …]
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/ |
| D | micro_mutable_op_resolver_test.cc | 63 using tflite::BuiltinOperator_CONV_2D; in TF_LITE_MICRO_TEST()
64 using tflite::BuiltinOperator_RELU; in TF_LITE_MICRO_TEST()
65 using tflite::MicroMutableOpResolver; in TF_LITE_MICRO_TEST()
66 using tflite::OpResolver; in TF_LITE_MICRO_TEST()
102 using tflite::BuiltinOperator_CONV_2D; in TF_LITE_MICRO_TEST()
103 using tflite::BuiltinOperator_RELU; in TF_LITE_MICRO_TEST()
104 using tflite::MicroMutableOpResolver; in TF_LITE_MICRO_TEST()
|
| D | micro_utils_test.cc | 23 using tflite::FloatToQuantizedType; in TF_LITE_MICRO_TEST()
38 using tflite::FloatToQuantizedType; in TF_LITE_MICRO_TEST()
56 using tflite::FloatToSymmetricQuantizedType; in TF_LITE_MICRO_TEST()
78 using tflite::FloatToSymmetricQuantizedType; in TF_LITE_MICRO_TEST()
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/magic_wand/train/ |
| D | README.md | 9 The following document contains instructions on using the scripts to train a
61 Using a random split results in higher training accuracy than a person split,
74 Using a person data split results in lower training accuracy but better
92 To obtain new training data using the
95 and deploy it using the Ambiq SDK.
100 [Using SparkFun Edge Board with Ambiq Apollo3 SDK](https://learn.sparkfun.com/tutorials/using-spark…
136 [SparkFun's guide](https://learn.sparkfun.com/tutorials/using-sparkfun-edge-board-with-ambiq-apollo…
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/kernels/internal/ |
| D | compatibility.h | 81 using int8 = std::int8_t;
82 using uint8 = std::uint8_t;
83 using int16 = std::int16_t;
84 using uint16 = std::uint16_t;
85 using int32 = std::int32_t;
86 using uint32 = std::uint32_t;
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/kernels/ |
| D | tanh_test.cc | 150 using tflite::testing::tanh_input_vec_fp; in TF_LITE_MICRO_TEST()
151 using tflite::testing::tanh_output_vec_fp; in TF_LITE_MICRO_TEST()
152 using tflite::testing::tanh_vec_size; in TF_LITE_MICRO_TEST()
167 using tflite::testing::tanh_input_vec_fp; in TF_LITE_MICRO_TEST()
168 using tflite::testing::tanh_output_vec_fp; in TF_LITE_MICRO_TEST()
169 using tflite::testing::tanh_vec_size; in TF_LITE_MICRO_TEST()
195 using tflite::testing::tanh_input_vec_fp; in TF_LITE_MICRO_TEST()
196 using tflite::testing::tanh_output_vec_fp; in TF_LITE_MICRO_TEST()
197 using tflite::testing::tanh_vec_size; in TF_LITE_MICRO_TEST()
|
| D | space_to_depth_test.cc | 23 using tflite::ElementCount;
24 using tflite::testing::CreateTensor;
25 using tflite::testing::IntArrayFromInts;
94 using value_type = float; in TF_LITE_MICRO_TEST()
116 using value_type = int8_t; in TF_LITE_MICRO_TEST()
138 using value_type = int8_t; in TF_LITE_MICRO_TEST()
160 using value_type = int8_t; in TF_LITE_MICRO_TEST()
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/hello_world/ |
| D | README.md | 5 This example is designed to demonstrate the absolute basics of using [TensorFlow
33 board. General information and instructions on using the board with TensorFlow
75 3. Build the example using
87 5. To run application from the board using microSD card:
103 * To run application from the console using it type `make run`.
111 …urrently an experimental feature. General information and instructions on using embARC MLI Library…
132 TCF file for VPX Processor can be generated using tcfgen tool which is part of [MetaWare Developmen…
133 The following command can be used to generate TCF file to run applications on VPX Processor using n…
137 VPX Processor configuration may require a custom run-time library specified using the BUILD_LIB_DIR…
155 2. Build the example using
[all …]
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/person_detection/ |
| D | README.md | 25 board. General information and instructions on using the board with TensorFlow
84 3. Build the example using
96 5. To run application from the board using microSD card:
112 * To run application from the console using it type `make run`.
120 …urrently an experimental feature. General information and instructions on using embARC MLI Library…
141 TCF file for VPX Processor can be generated using tcfgen tool which is part of [MetaWare Developmen…
142 The following command can be used to generate TCF file to run applications on VPX Processor using n…
146 VPX Processor configuration may require a custom run-time library specified using the BUILD_LIB_DIR…
164 2. Build the example using
271 // Comment out the next #defines if you are not using an SD Card to store the JPEGs
[all …]
|
| D | training_a_model.md | 4 250 KB embedded vision model using scripts that are easy to run. You can use
10 recommend using a [Google Cloud Deep
18 using tf.slim, an older interface. It is still widely used but deprecated, so
24 started you'll need to download it from GitHub using a command like this:
47 current Jupyter session, so if you're using bash directly, you should add it to
114 One of the nice things about using tf.slim to handle the training is that the
147 - The architecture we'll be using is defined by the `--model_name` argument.
162 camera we're using on the SparkFun Edge board is monochrome, so to get the
211 instances. If you're using Google Cloud's AI Platform, you can start up a new
432 using the original v1 since it required the smallest amount of RAM at runtime.
[all …]
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/kernels/internal/reference/ |
| D | tanh.h | 63 using F0 = gemmlowp::FixedPoint<std::int16_t, 0>; in Tanh()
65 using F3 = gemmlowp::FixedPoint<std::int16_t, 3>; in Tanh()
106 using FixedPoint4 = gemmlowp::FixedPoint<int32_t, 4>; in Tanh()
107 using FixedPoint0 = gemmlowp::FixedPoint<int32_t, 0>; in Tanh()
111 using gemmlowp::RoundingDivideByPOT; in Tanh()
|
| D | logistic.h | 37 // Rational for using approximation in reference kernel. in Logistic()
77 using F0 = gemmlowp::FixedPoint<std::int16_t, 0>; in Logistic()
79 using F3 = gemmlowp::FixedPoint<std::int16_t, 3>; in Logistic()
102 // Rational for using approximation in reference kernel. in Logistic()
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/micro_speech/ |
| D | README.md | 38 board. General information and instructions on using the board with TensorFlow
98 3. Build the example using
110 5. To run application from the board using microSD card:
126 * To run application from the console using it type `make run`.
134 …urrently an experimental feature. General information and instructions on using embARC MLI Library…
155 TCF file for VPX Processor can be generated using tcfgen tool which is part of [MetaWare Developmen…
156 The following command can be used to generate TCF file to run applications on VPX Processor using n…
160 VPX Processor configuration may require a custom run-time library specified using the BUILD_LIB_DIR…
178 2. Build the example using
202 microphone. If you're using a different Arduino board and attaching your own
[all …]
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/kernels/test_data_generation/ |
| D | README.md | 3 As a Custom operator, detection_postprocess is using Flexbuffers library. In the
6 targets (basically only on X86), since it is using std::vector and std::map.
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/tools/make/templates/ |
| D | library.properties | 6 …amples, you can recognize speech, detect people using a camera, and recognise "magic wand" gesture…
|
| D | README_MAKE.md.tpl | 4 and project files needed to build a single TensorFlow Lite Micro target using
15 This should attempt to build the target locally on your platform, using the
|
| D | README_MBED.md.tpl | 4 and project files needed to build a single TensorFlow Lite Micro target using
33 you're targeting. For example, using a Discovery STM3246G board, you can deploy
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/docs/rfc/ |
| D | 001_preallocated_tensors.md | 32 using TensorFlow Lite Micro. An illustration of this can be seen in the image
58 Our second motivation was that by using a buffer outside of the memory arena,
62 An initial investigation into these matters, using the person detection model as
82 buffer using the RegisterPreallocatedTensor() function.
113 When using an accelerator, the total inference time will be significantly less
126 One good tool for understanding tensor layout in the tensor arena is using
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/kernels/arc_mli/ |
| D | README.md | 52 TFLM can be built using [embARC MLI Library 2.0](https://github.com/foss-for-synopsys-dwc-arc-proce…
53 To build TFLM using the embARC MLI Library 2.0, add the following tag to the command:
59 Some of configurations may require a custom run-time library specified using the BUILD_LIB_DIR opti…
76 used for some nodes and you need to revert to using TFLM reference kernels.
|
| D | pooling_slicing_test.cc | 188 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
213 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
245 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
275 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
312 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
338 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
371 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
402 using tflite::testing::F2QS; in TF_LITE_MICRO_TEST()
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/network_tester/ |
| D | README.md | 6 (expected_output_data.h). The header files were created using the `xxd` command.
31 the new model. This is done by using the `ARENA_SIZE` option when running
57 The output is printed in JSON format using printf: `num_of_outputs: 1
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/micro_speech/apollo3/ |
| D | README.md | 18 * captured\_data.txt can be turned into a \*.wav file using
47 * Also prints out the number of cycles the code took to execute (using the
65 * Also prints out the number of cycles the code took to execute (using the
74 creates a \*.wav file using
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/examples/magic_wand/ |
| D | README.md | 148 board. To understand more about using this board, please check
173 - burn application to flash by using xmodem send application binary
205 2. Build the example using
289 If you're new to using this board, we recommend walking through the
311 the SparkFun Edge. The scripts we are using come from the Ambiq SDK, which is
353 **Note:** If you're using the
405 it, establish a serial connection to the board using a baud rate of `115200`. On
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/kernels/internal/reference/integer_ops/ |
| D | logistic.h | 45 using FixedPoint4 = gemmlowp::FixedPoint<int32_t, kInputIntegerBits>; in Logistic()
50 using gemmlowp::RoundingDivideByPOT; in Logistic()
102 // Interpolation is done using the fractional bit. in Logistic()
|
| /tflite-micro-3.4.0-2.7.6/tensorflow/lite/micro/tools/make/templates/arc/ |
| D | README_ARC.md.tpl | 3 … project files needed to build a single TensorFlow Lite Micro application using make tool and a Sy…
37 6. Run the application with the nSIM simulator, but using the MetaWare Debugger GUI for further exe…
|
