Home
last modified time | relevance | path

Searched refs:quantized (Results 1 – 25 of 69) sorted by relevance

123

/external/tensorflow/tensorflow/core/api_def/base_api/
Dapi_def_QuantizedAdd.pbtxt6 The float value that the lowest quantized `x` value represents.
12 The float value that the highest quantized `x` value represents.
18 The float value that the lowest quantized `y` value represents.
24 The float value that the highest quantized `y` value represents.
30 The float value that the lowest quantized output value represents.
36 The float value that the highest quantized output value represents.
42 summary: "Returns x + y element-wise, working on quantized buffers."
Dapi_def_QuantizedMul.pbtxt6 The float value that the lowest quantized `x` value represents.
12 The float value that the highest quantized `x` value represents.
18 The float value that the lowest quantized `y` value represents.
24 The float value that the highest quantized `y` value represents.
30 The float value that the lowest quantized output value represents.
36 The float value that the highest quantized output value represents.
42 summary: "Returns x * y element-wise, working on quantized buffers."
Dapi_def_QuantizedBatchNormWithGlobalNormalization.pbtxt12 The value represented by the lowest quantized input.
18 The value represented by the highest quantized input.
32 The value represented by the lowest quantized mean.
38 The value represented by the highest quantized mean.
52 The value represented by the lowest quantized variance.
58 The value represented by the highest quantized variance.
71 The value represented by the lowest quantized offset.
77 The value represented by the highest quantized offset.
91 The value represented by the lowest quantized gamma.
97 The value represented by the highest quantized gamma.
Dapi_def_QuantizedConv2D.pbtxt12 The float value that the lowest quantized input value represents.
18 The float value that the highest quantized input value represents.
24 The float value that the lowest quantized filter value represents.
30 The float value that the highest quantized filter value represents.
36 The float value that the lowest quantized output value represents.
42 The float value that the highest quantized output value represents.
68 summary: "Computes a 2D convolution given quantized 4D input and filter tensors."
70 The inputs are quantized tensors where the lowest value represents the real
72 This means that you can only interpret the quantized output in the same way, by
Dapi_def_QuantizedBiasAdd.pbtxt12 The float value that the lowest quantized input value represents.
18 The float value that the highest quantized input value represents.
24 The float value that the lowest quantized bias value represents.
30 The float value that the highest quantized bias value represents.
36 The float value that the lowest quantized output value represents.
42 The float value that the highest quantized output value represents.
Dapi_def_QuantizedMatMul.pbtxt18 The float value that the lowest quantized `a` value represents.
24 The float value that the highest quantized `a` value represents.
30 The float value that the lowest quantized `b` value represents.
36 The float value that the highest quantized `b` value represents.
42 The float value that the lowest quantized output value represents.
48 The float value that the highest quantized output value represents.
70 summary: "Perform a quantized matrix multiplication of `a` by the matrix `b`."
Dapi_def_Requantize.pbtxt6 The float value that the minimum quantized input value represents.
12 The float value that the maximum quantized input value represents.
18 The float value that the minimum quantized output value represents.
24 The float value that the maximum quantized output value represents.
51 summary: "Convert the quantized \'input\' tensor into a lower-precision \'output\', using the"
57 input_max is 1.0f, and we are dealing with quint16 quantized data, then a 0
Dapi_def_QuantizeV2.pbtxt18 The quantized data produced from the float input.
37 used to convert the float values to their quantized equivalents. The
39 when rounding float values to their quantized equivalents.
67 quantized = round(input * range_scale) - round(range_min * range_scale) +
69 quantized = max(quantized, numeric_limits<T>::min())
70 quantized = min(quantized, numeric_limits<T>::max())
123 they will be separated by a small epsilon value to prevent ill-formed quantized
125 quantized values map to the same float value, which causes problems for
Dapi_def_QuantizedMaxPool.pbtxt12 The float value that the lowest quantized input value represents.
18 The float value that the highest quantized input value represents.
24 The float value that the lowest quantized output value represents.
30 The float value that the highest quantized output value represents.
53 summary: "Produces the max pool of the input tensor for quantized types."
Dapi_def_QuantizedAvgPool.pbtxt12 The float value that the lowest quantized input value represents.
18 The float value that the highest quantized input value represents.
24 The float value that the lowest quantized output value represents.
30 The float value that the highest quantized output value represents.
53 summary: "Produces the average pool of the input tensor for quantized types."
Dapi_def_QuantizedRelu.pbtxt6 The float value that the lowest quantized value represents.
12 The float value that the highest quantized value represents.
24 The float value that the lowest quantized value represents.
30 The float value that the highest quantized value represents.
Dapi_def_QuantizedReluX.pbtxt6 The float value that the lowest quantized value represents.
12 The float value that the highest quantized value represents.
24 The float value that the lowest quantized value represents.
30 The float value that the highest quantized value represents.
Dapi_def_QuantizedRelu6.pbtxt6 The float value that the lowest quantized value represents.
12 The float value that the highest quantized value represents.
24 The float value that the lowest quantized value represents.
30 The float value that the highest quantized value represents.
Dapi_def_QuantizeDownAndShrinkRange.pbtxt6 The float value that the minimum quantized input value represents.
12 The float value that the maximum quantized input value represents.
18 The float value that the minimum quantized output value represents.
24 The float value that the maximum quantized output value represents.
39 summary: "Convert the quantized \'input\' tensor into a lower-precision \'output\', using the"
46 input_max is 1.0f, and we are dealing with quint16 quantized data, then a 0
Dapi_def_QuantizedInstanceNorm.pbtxt12 The value represented by the lowest quantized input.
18 The value represented by the highest quantized input.
30 The value represented by the lowest quantized output.
36 The value represented by the highest quantized output.
Dapi_def_QuantizedResizeBilinear.pbtxt30 summary: "Resize quantized `images` to `size` using quantized bilinear interpolation."
32 Input images and output images must be quantized types.
Dapi_def_RequantizationRange.pbtxt6 The float value that the minimum quantized input value represents.
12 The float value that the maximum quantized input value represents.
33 summary: "Given a quantized tensor described by (input, input_min, input_max), outputs a"
Dapi_def_QuantizedConcat.pbtxt40 The float value that the minimum quantized output value represents.
46 The float value that the maximum quantized output value represents.
49 summary: "Concatenates quantized tensors along one dimension."
/external/tensorflow/tensorflow/contrib/lite/toco/g3doc/
Dcmdline_reference.md46 when the output file will accept quantized input arrays.
53 between floating-point and quantized arithmetic for the inference
60 inference on a quantized input, as is common in image models operating
63 input graph is not properly quantized: `--default_ranges_min`,
82 * Whether a float or quantized TensorFlow Lite file will be produced
131 the (de-)quantization parameters of the input array, when it is quantized.
132 * The meaning of mean_value and std_value is as follows: each quantized
133 value in the quantized input array will be interpreted as a mathematical
138 quantized input, the quantized input would be immediately dequantized by
141 * When performing quantized inference
[all …]
Dcmdline_examples.md88 GraphDefs are technically always float, and the only flavor of "quantized"
113 ## Convert a TensorFlow GraphDef to TensorFlow Lite for quantized inference
115 Let us now look at a quantized model. As mentioned above, the only flavor of
116 quantized TensorFlow GraphDefs that the converter is concerned with, is
119 range information allowing to generate a quantized inference workload that is
121 during training. Indeed, the whole point of quantized training is to allow for
124 effectively helping the quantized inference process to be more accurate.
126 Given a quantized TensorFlow GraphDef, generating a quantized TensorFlow Lite
144 Here, besides changing `--input_file` to point to a (fake-)quantized GraphDef,
148 the converter to generate an output file that performs quantized inference
[all …]
/external/tensorflow/tensorflow/contrib/lite/toco/
Dtoco_flags.proto51 // by default input arrays are quantized like other arrays.
54 // we mean float arrays, and quantized arrays. This excludes plain
59 // inference. For such image models, the uint8 input is quantized, i.e.
70 // we mean float arrays, and quantized arrays. This excludes plain
80 // the output file. If they were quantized in the input file, then
82 // - If QUANTIZED_UINT8, then real-numbers arrays will be quantized
84 // then they get quantized.
95 // to estimate the performance of quantized inference, without caring about
103 // they make it easy to quantize models, but the resulting quantized model
109 // generate plain float code without fake-quantization from a quantized
[all …]
Dtypes.proto23 // Float32, not quantized
26 // Uint8, quantized
29 // Int32, not quantized
32 // Int64, not quantized
35 // String, not quantized
/external/tensorflow/tensorflow/java/src/gen/resources/
Dtftypes.csv12 QInt8,n,,n,,quantized int8
13 QUInt8,n,,n,,quantized uint8
14 QInt32,n,,n,,quantized int32
16 QInt16,n,,n,,quantized int16
17 QUInt16,n,,n,,quantized uint16
/external/gemmlowp/doc/
Dquantization.md11 of quantized 8bit values and matrices of real numbers. The choice of a
20 output pipeline, allowing the user to implement their own preferred quantized
36 quantized uint8 values, the mapping between real and quantized uint8 values must
50 mean that the result of the quantized calculations do no longer readily provide
64 In order for such zero-padding to be feasible in a quantized implementation of
66 quantized form, i.e. that it correspond exactly to some quantized value, which
70 quantized value for padding, that does not exactly correspond to the real value
130 * `zero_point` is integral, more specifically is one of the possible quantized
139 to quantized values (typically uint8), we turn to applying this knowledge to
141 multiplication of matrices of quantized values.
[all …]
/external/tensorflow/tensorflow/contrib/lite/
Dinterpreter_test.cc338 TfLiteQuantizationParams quantized; in TEST() local
340 {3}, quantized), in TEST()
343 {3}, quantized), in TEST()
419 TfLiteQuantizationParams quantized; in TEST() local
423 quantized, data, 15), in TEST()
427 quantized), in TEST()
430 quantized), in TEST()
433 quantized), in TEST()
436 quantized), in TEST()
500 TfLiteQuantizationParams quantized; in TEST() local
[all …]

123