Changelog¶
0.15: February 16, 2021¶
Changed:
Can choose to run inference on GPU for individual modules using
EnableGPU
configuration option.Changed
identification.cpp
,identification.py
, andidentification_live_streaming.py
sample code to demonstrate usage of new collection metadata functions.
Added:
createCollection
,loadCollection
, anddeleteCollection
API functions. CallingcreateCollection
then subsequentlyloadCollection
is equivalent to callingcreateLoadCollection
.getCollectionNames
API function returns a list of the names of all the collections in the database.getCollectionMetadata
API function returns the metadata for the specified collection in the database, loaded or unloaded.getCollectionIdentities
API function returns a map of identities and UUIDs for the specified collection in the database, loaded or unloaded.CollectionMetadata
API struct, returned bygetCollectionMetadata
.
0.14: January 25, 2021¶
Changed:
Default value of
ConfigurationOptions::smallestFaceHeight
has been increased from 20px to 40px.Downloadable model file formats have changed. You will need to re-run the model download scripts if upgrading from an older SDK version.
Changed sample app images.
Fixed:
Fixed bug which impacted Faceprint feature vector integrity with calls to
jsonToFaceprint
andfaceprintToJson
whenConfigurationOptions::frVectorCompression
was set to true. The format of serialized Faceprint feature vectors (generated with frVectorCompression = true) has changed and therefore old serialized Faceprints which were generated and saved cannot be used with new versions of the SDK.MXNET_CUDNN_AUTOTUNE_DEFAULT
environment variable is now properly read by the GPU SDK.MXNET_CUDNN_AUTOTUNE_DEFAULT=0
should be set when variable-sized input images are used.
0.13: January 15, 2021¶
Removed:
Removed functions which were marked as deprecated in release 0.11.
Fixed:
Fixed bug in python bindings function
identify_top_candidates
.
0.12: January 4, 2021¶
Added:
Added Windows SDK to downloads page.
Fixed:
Cap
similarityMeasure
at 1.f, previously could sometimes exceed 1 due to rounding errors.Improved 1 to N identification sample apps, better demonstrate how to select high quality enrollment images. Improved 1 to N identification documentation.
Fixed
getFaceFeatureVectors
function when running GPU SDK withenableGPU
set to false.
0.11: December 23, 2020¶
Changed:
Function prototype changed for
removeByIdentity
. Now returns the number of Faceprints which were deleted from the collection.enrollTemplate
has been deprecated, useenrollFaceprint
instead.getLargestFaceFeatureVector(Faceprint&)
has been deprecated, usegetLargestFaceFeatureVector(Faceprint&, bool&)
instead.
Fixed:
Fixed bug with logger.
0.10: December 11, 2020¶
New features and enhancements:
Face recognition template generation speed improvements on x86 CPU (both LITE and FULL model template generation nearly twice as fast). The RAM usage has also increased, the FULL model now using 2Gb RAM (previously 1.1Gb), and the LITE model using 55Mb RAM (previously 35Mb).
Changed:
SDK now supports CPUs which have AVX instruction set and don’t have AVX2 instruction set (previously our SDK required AVX2 CPUs). SDK uses runtime dispatching and will run significantly faster on CPUs supporting AVX2.
faceprintToJson
no longer adds newline to json elements.
0.9: November 20, 2020¶
New features and enhancements:
Python3.7 bindings for AArch64 and Arm32 SDK (previously only python3.6).
Added
setImage
overload which accepts buffer to encoded JPG, PNG, or TIFF image
Changed:
Changed scripts for downloading runtime model files. They are now located in the download_models directory.
Function prototype changed for
isLicensed
function. Now returns how many days are remaining for the license token.
Fixed:
Fixed bug with GPU face detector where
smallestFaceHeight
parameter was not being used.Bug in spoof code which was producing incorrect results. Spoof function prototype has also been changed, must provided the
FaceBoxAndLandmarks
of the face to be analyzed.
0.8: November 9, 2020¶
New features and enhancements:
All Python classes have a __repr__ method.
Python bindings for AArch64 and Arm32 SDK.
Log number of days remaining for license.
Can use images residing in CUDA memory for face detection and recognition.
Added PostgreSQL DatabaseManagementSystem support.
Added
faceprintToJson
andjsonToFaceprint
functions for deserializing / serializing Faceprint objects as strings.Improved sample apps.
Environment variable for setting log level.
Improved documentation.
Changed:
Version number can be obtained from python bindings using
tfsdk.SDK.get_version()
0.7: August 14, 2020¶
New features and enhancements:
Added
detectGlasses
API for detecting eye glassesAdded
detectMask
API function for detecting face masksAdded glasses detection sample codes (C++ and python).
Added mask detection sample apps (C++ and python).
Spoof model improvements.
Reduce SDK size.
No longer need to register all the GPUs in a machine in order to use one GPU with the SDK.
Changed:
Changed TRUEFACE_LICENSE to TRUEFACE_TOKEN in python bindings sample apps.
Spoof score has been inverted, 1 indicates real, 0 indicates fake.
detectMask
now takes 1 additional parameter,maskScore
.
0.6: July 7, 2020¶
New features and enhancements:
Face mask detection (currently on the CUDA engine only).
Setting
smallestFaceHeight
to -1 adjusts the face detection scale range from image-height/32 to image-height.Read license token from environment variable in python sample apps.
Method signature changes:
Renamed
createCollection
tocreateLoadCollection
.