Home
last modified time | relevance | path

Searched refs:quantization (Results 1 – 12 of 12) sorted by relevance

/aosp12/frameworks/av/media/codecs/amrwb/enc/inc/
H A Dq_gain2.tab25 * during quantization of gains. *
28 #define nb_qua_gain6b 64 /* Number of quantization level */
29 #define nb_qua_gain7b 128 /* Number of quantization level */
/aosp12/bionic/libc/kernel/uapi/linux/
H A Dv4l2-mediabus.h35 __u16 quantization; member
H A Dvideodev2.h208 __u32 quantization; member
1237 __u8 quantization; member
H A Dv4l2-controls.h1189 __u32 quantization; member
/aosp12/packages/modules/NeuralNetworks/tools/api/
H A DNeuralNetworksTypes.t644 * The quantization scale.
653 * The quantization zero point.
H A Dtypes.spec4272 * * Quantized with symmetric per channel quantization for the filter:
4279 * * Quantized signed with filter symmetric per channel quantization
4970 * A version of quantized LSTM, using 16 bit quantization for internal
4979 * cell. Tensor is quantized with a fixed quantization range of
5052 * quantization range of [-2^4, 2^4 * 32767/32768] (scale = 2^4 /
5057 * quantization range of [-1, 127/128] (scale = 1/128, zeroPoint =
5064 * the current time step. Tensor is quantized using a quantization
5069 * Tensor is quantized with a fixed quantization range of [-1, 127/128]
5698 * * Quantized with symmetric per channel quantization for the filter:
5711 * * Quantized signed with filter symmetric per channel quantization
[all …]
/aosp12/hardware/interfaces/neuralnetworks/1.3/
H A Dtypes.hal304 * * Quantized with symmetric per channel quantization for the filter:
316 * * Quantized signed with filter symmetric per channel quantization
471 * * Quantized with symmetric per channel quantization for the filter:
483 * * Quantized signed with filter symmetric per channel quantization
3355 * * Quantized with symmetric per channel quantization for the filter:
3361 * * Quantized signed with filter symmetric per channel quantization
3965 * A version of quantized LSTM, using 16 bit quantization for internal
3974 * cell. Tensor is quantized with a fixed quantization range of
4047 * quantization range of [-2^4, 2^4 * 32767/32768] (scale = 2^4 /
4611 * * Quantized with symmetric per channel quantization for the filter:
[all …]
/aosp12/hardware/interfaces/neuralnetworks/1.2/
H A Dtypes.hal353 * * Quantized with symmetric per channel quantization for the filter:
505 * * Quantized with symmetric per channel quantization for the filter:
3163 * * Quantized with symmetric per channel quantization for the filter:
3738 * A version of quantized LSTM, using 16 bit quantization for internal
3747 * cell. Tensor is quantized with a fixed quantization range of
3820 * quantization range of [-2^4, 2^4 * 32767/32768] (scale = 2^4 /
3825 * quantization range of [-1, 127/128] (scale = 1/128, zeroPoint =
3832 * the current time step. Tensor is quantized using a quantization
3837 * Tensor is quantized with a fixed quantization range of [-1, 127/128]
4365 * * Quantized with symmetric per channel quantization for the filter:
[all …]
/aosp12/hardware/interfaces/sensors/1.0/
H A Dtypes.hal1064 * quantization unit
/aosp12/packages/apps/Dialer/java/com/android/dialer/about/res/raw/
H A Dthird_party_licenses11000 NEUQUANT Neural-Net quantization algorithm by Anthony Dekker, 1994. See
11001 "Kohonen neural networks for optimal colour quantization" in "Network:
/aosp12/packages/inputmethods/LatinIME/dictionaries/
H A Den_US_wordlist.combined.gz1dictionary=main:en_us,locale=en_US,description=English (US),date ...
H A Den_wordlist.combined.gz1dictionary=main:en,locale=en,description=English,date=1414726273, ...