Searched full:with (Results 1 – 25 of 207) sorted by relevance
123456789
| /cmsis-nn-3.6.0-3.5.0/ |
| D | LICENSE.txt | 17 control with that entity. For the purposes of this definition,
81 with the Work to which such Contribution(s) was submitted. If You
90 Work or Derivative Works thereof in any medium, with or without
113 documentation, if provided along with the Derivative Works; or,
127 reproduction, and distribution of the Work otherwise complies with
136 with Licensor regarding such Contributions.
151 risks associated with Your exercise of permissions under this License.
168 or other liability obligations and/or rights consistent with this
181 boilerplate notice, with the fields enclosed by brackets "{}"
182 replaced with your own identifying information. (Don't include
[all …]
|
| D | README.md | 19 Processors with DSP extension uses Single Instruction Multiple Data(SIMD) instructions for optimiza…
20 processors here are Cortex-M4 or a Cortex-M33 configured with optional DSP extension.
23 Processors with Arm Helium Technology use the Arm M-profile Vector Extension(MVE) instructions for …
24 Examples are Cortex-M55 or Cortex-M85 configured with MVE.
46 * Variable and function names are lower case with an underscore separator.
90 performance. With only optimization level -O0, *ARM_MATH_AUTOVECTORIZE* needs to be defined for pro…
101 …x. It should be possible to use the C implementation and compile for host with minor stubbing effo…
|
| /cmsis-nn-3.6.0-3.5.0/Tests/UnitTest/ |
| D | README.md | 10 It has been tested with Python 3.6 and it has been tested on Ubuntu 16, 18 and 20.
29 …they are command-line tools. These packages have been tested for Python2, with the following versi…
57 …e actual reference output. Python package tflite_runtime can be installed with pip and it can also…
113 Generating new test data is done with the following script. Use the -h flag to get more info.
120 …, i.e. it need a test set data name as input. It will then generate files with that name as prefix…
123 …est test in the load_all_testdatasets() function. Run the generate script with that new test set a…
144 …nction under test there is a folder with the same name with test_ prepended to the name and it con…
152 The python test scripts should be formatted with yapf.
|
| D | unittest_targets.py | 8 # not use this file except in compliance with the License.
49 " So basically the different options can be listed with:"
108 with open(target_json, "r") as read_file:
123 error_handler(168, 'Unsupported target: {} with architecture: {}'.format(
162 print("Running {} on {} target: {} with compiler: {} in directory: {} test: {}\n".format(
406 with open(test_runner, "r") as f:
408 with open(test_runner, "w") as f:
476 with read_file:
|
| /cmsis-nn-3.6.0-3.5.0/.github/workflows/ |
| D | build.yaml | 6 # not use this file except in compliance with the License.
34 with:
43 with:
|
| D | microspeech.yaml | 6 # not use this file except in compliance with the License.
69 with:
75 with:
109 with:
|
| /cmsis-nn-3.6.0-3.5.0/Source/NNSupportFunctions/ |
| D | arm_nn_depthwise_conv_nt_t_s8.c | 7 * not use this file except in compliance with the License.
22 * Description: Depthwise convolution on matrices with no padding.
27 * Target Processor: Cortex-M processors with MVE extension.
42 …* Depthwise convolution of rhs matrix with 4 lhs matrices with no padding. Dimensions are the same…
|
| D | arm_nn_depthwise_conv_nt_t_s16.c | 7 * not use this file except in compliance with the License.
22 * Description: Depthwise convolution on matrices with no padding.
27 * Target Processor: Cortex-M processors with MVE extension
42 …* Depthwise convolution of rhs matrix with 4 lhs matrices with no padding. Dimensions are the same…
|
| D | arm_q7_to_q15_with_offset.c | 7 * not use this file except in_q7x4 compliance with the License.
22 * Description: Converts the elements of the Q7 vector to Q15 vector with an added offset
75 /* First part of the processing with loop unrolling. Compute 4 outputs at a time. */ in arm_q7_to_q15_with_offset()
|
| D | arm_nn_depthwise_conv_nt_t_padded_s8.c | 7 * not use this file except in compliance with the License.
22 * Description: Depthwise convolution with padded matrices.
27 * Target Processor: Cortex-M processors with MVE extension
49 …* Depthwise convolution of transposed rhs matrix with 4 lhs matrices. One or more of the rhs matri…
|
| D | arm_s8_to_s16_unordered_with_offset.c | 7 * not use this file except in_q7x4 compliance with the License.
22 * Description: Converts the elements of the S8 vector to S16 vector with an added offset
|
| /cmsis-nn-3.6.0-3.5.0/DoxyGen/ |
| D | nn.dxy.in | 6 # not use this file except in compliance with the License.
65 # With the PROJECT_LOGO tag one can specify a logo or an icon that is included
102 # Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages),
103 # Korean, Korean-en (Korean with English messages), Latvian, Lithuanian,
132 # following values are used ($name is automatically replaced with the name of
270 # documentation, which will result in a user-defined paragraph with heading
276 # with the commands \{ and \} for these it is advised to use the version @{ and
320 # parses. With this tag you can assign which parser to use for a given
346 # mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in
432 # Note that this feature does not work in combination with
[all …]
|
| D | check_links.sh | 8 # not use this file except in compliance with the License.
23 echo " <src> Directory with doxygen source files."
|
| /cmsis-nn-3.6.0-3.5.0/Source/LSTMFunctions/ |
| D | arm_lstm_unidirectional_s8_s16.c | 7 * not use this file except in compliance with the License.
22 * Description: S8 LSTM function with S16 gate output
44 * S8 LSTM function for TensorFlow Lite with S16 gate output
54 * LSTM unidirectional function with 8 bit input and output and 16 bit weights
|
| /cmsis-nn-3.6.0-3.5.0/Include/ |
| D | arm_nnsupportfunctions.h | 7 * not use this file except in compliance with the License.
61 // A layer with lower number of channels than CH_IN_BLOCK_MVE will result in higher
62 // scratch buffer usage and a layer with higher number of channels than CH_IN_BLOCK_MVE
121 * @brief Converts the elements from a s8 vector to a s16 vector with an added offset
141 * @brief Converts the elements from a s8 vector to a s16 vector with an added offset
149 * No additonal ordering is done with the result that output elements are not in order.
151 * Note this is for processors with DSP extension only.
197 * @brief General Matrix-multiplication function with per-channel requantization.
233 …* @brief Matrix-multiplication function for convolution with per-channel requantization for 16 bit…
249 * with 2 columns from im2col and produces two elements/output_channel. The outputs are
[all …]
|
| D | arm_nnfunctions.h | 7 * not use this file except in compliance with the License.
53 …* CMSIS-NN targets Cortex-M processors with typically three different implementations for each fun…
56 * - Processors with DSP extension (e.g Cortex-M4)
57 * - Processors with Arm M-Profile Vector Extension(MVE) instructions (e.g Cortex-M55)
83 * - `ARM_MATH_DSP` - Selects code for processors with DSP extension.
107 …* A collection of functions to perform basic operations for neural network layers. Functions with …
141 …* @brief s8 convolution layer wrapper function with the main purpose to call the optimal kernel av…
212 …* @brief Get the required buffer size for arm_convolve_wrapper_s8 for processors with DSP extensio…
225 …* @brief s16 convolution layer wrapper function with the main purpose to call the optimal kernel a…
283 …* @brief Get the required buffer size for arm_convolve_wrapper_s16 for for processors with DSP ext…
[all …]
|
| /cmsis-nn-3.6.0-3.5.0/Source/BasicMathFunctions/ |
| D | arm_elementwise_mul_s16_s8.c | 7 * not use this file except in compliance with the License.
22 * Description: Elementwise multiplication of 16 bit input with 8 bit output
43 * s16 elementwise multiplication with s8 output
|
| /cmsis-nn-3.6.0-3.5.0/Source/SoftmaxFunctions/ |
| D | arm_nn_softmax_common_s8.c | 7 * not use this file except in compliance with the License.
22 * Description: Softmax with s8 input and output of s8 or s16.
51 * Softmax function with s8 input and output of s8 or s16.
|
| /cmsis-nn-3.6.0-3.5.0/Source/ConvolutionFunctions/ |
| D | arm_nn_mat_mult_kernel_s8_s16.c | 7 * not use this file except in compliance with the License.
34 * Matrix-multiplication function for convolution with per-channel requantization.
73 /* Init accumulator with bias for channel N and N + 1 */ in arm_nn_mat_mult_kernel_s8_s16()
228 /* return the new output pointer with offset */ in arm_nn_mat_mult_kernel_s8_s16()
|
| D | arm_convolve_wrapper_s16.c | 7 * not use this file except in compliance with the License.
22 …* Description: s16 convolution layer wrapper function with the main purpose to call the optimal k…
|
| /cmsis-nn-3.6.0-3.5.0/Source/FullyConnectedFunctions/ |
| D | arm_fully_connected_s16.c | 7 * not use this file except in compliance with the License.
22 * Description: Fully connected function compatible with TF Lite.
|
| D | arm_fully_connected_s8.c | 7 * not use this file except in compliance with the License.
22 * Description: Fully connected function compatible with TF Lite.
|
| /cmsis-nn-3.6.0-3.5.0/Source/ActivationFunctions/ |
| D | arm_relu_q15.c | 7 * not use this file except in compliance with the License.
54 /* Run the following code for M cores with DSP extension */ in arm_relu_q15()
|
| D | arm_relu_q7.c | 7 * not use this file except in compliance with the License.
54 /* Run the following code for M cores with DSP extension */ in arm_relu_q7()
|
| /cmsis-nn-3.6.0-3.5.0/Tests/UnitTest/Corstone-300/ |
| D | linker.ld | 7 * not use this file except in compliance with the License.
81 * with other linker script that defines memory regions ITCM and RAM.
144 * must be set, either with the command line option �--section-start� or in a linker script,
189 * Location counter can end up 2byte aligned with narrow Thumb code but
311 ASSERT(__StackLimit >= __HeapLimit, "region DTCM overflowed with stack")
|
123456789
