Release Notes
This page features release notes for previous PySDK releases. You may download PySDK versions listed here from PyPI.
Last updated
Was this helpful?
This page features release notes for previous PySDK releases. You may download PySDK versions listed here from PyPI.
Last updated
Was this helpful?
AI accelerators are initially supported for Linux OS. The runtime/device designator for these devices is "DEEPX/M1A"
.
NOTE: due to current limitations of DeepX runtime the number of supported devices is limited to one.
Error handling is improved for Hailo runtime agent: now all errors reported by HailoRT runtime are treated as critical.
TensorRT runtime agent performance is improved due to implementation of asynchronous pipelined inference.
Hailo runtime agent is supported on Windows 10/11 OS.
postprocess_type
keyword argument is added to degirum.zoo_manager.ZooManager.list_models
method. It allows filtering models by post-processor type.
Possible values for this argument are: "Classification"
, "Detection"
, "Segmentation"
etc. They correspond to OutputPostprocessType
model parameter values.
Oriented bounding box post-processor incorrectly interpreted rotation angle tensors for certain OBB models, which led to the error message "Execution failed. Condition '<N1> == <N2>' is not met"
.
Oriented bounding box renderer now shows labels at the corner of rotated box.
More stringent security checks are implemented when running Python post-processors in AI server.
Segmentation renderer works incorrectly for models with non-square (rectangular) inputs.
ORCA USB performance improvements are implemented.
ORCA USB stability improvements are implemented.
The post-processor for YOLOV8 Oriented Bounding Box (OBB) detection models is implemented. The post-processor tag is "DetectionYoloV8OBB"
. This complements the release of OBB model results drawing made in version 0.15.1.
DLA_FALLBACK
device type for TENSORRT
runtime is renamed to DLA
. Former DLA
device type is deprecated and removed. Now DLA
device type refers to an inference mode where the inference is conducted mainly on Deep Learning Accelerator (DLA) hardware with GPU fallback enabled.
The following error message appears when making simultaneous inference of two or more models using Hailo Runtime: "HailoRT Runtime Agent: Failed to configure infer model, status = HAILO_INVALID_OPERATION"
.
PySDK cloud inference now performs automatic reconnection to the cloud inference server in case of critical errors. This greatly improves robustness of cloud inference in case of inference node failures: after reconnection the cloud inference server assigns another healthy node for the inference, while PySDK retries the inference of not yet processed frames on that new node.
YOLO Detection postprocessor now supports models with no grid tensors and separate detection heads.
image_overlay
method of PySDK detection post-processor now supports drawing of oriented bounding box (OBB) model results. OBB detection results have additional "angle
" key in the result dictionary for each detected object, which specifies the bounding box rotation angle in radians in clockwise direction.
The error message "The input shape parameter InputShape for input #0 must have 4 elements, while it has <N>"
is produced for models with tensor input type.
degirum.list_models
and degirum.zoo_manager.ZooManager.list_models
methods did not filter out models not compatible with the connected inference engine for cloud model zoos when invoked with empty device
, runitime
or device_type
arguments.
Multiple fixes for Hailo runtime agent:
added support for additional tensor format orders introduced in HailoRT 4.20: models with NMS layers caused crashes in the previous release;
Hailo multi-process_service is used for inferences by default if it is running, otherwise local inference mode is used;
default page alignment for data buffers is changed from 4KB to 16KB to avoid errors on systems with 4KB PCI page settings.
Multiple fixes for Brainchip Akida runtime agent:
updated device names to uppercase (e.g., NSoC_v1 → NSOC_V1);
implemented validation of input/output dimensions during model loading to provide clear error reporting.
Starting from this version, PySDK is not supported for Python 3.8.
Device selection by device index is implemented for Hailo runtime agent. Now you can Hailo device(s) to be used for inference regular way by assigning degirum.model.Model.devices_selected
property of your model object.
ONNX runtime agent now supports ONNX runtime version 1.19.0 and prints the version in degirum sys-info
command output.
RKNN runtime agent now supports RKNN runtime version 2.3.0.
OPENVINO runtime agent now supports OPENVINO runtime version 2024.6.0.
HAILO runtime agent now supports HAILORT runtime version 4.20.
The post-processor for YOLOV8 license place detection models is implemented. The post-processor tag is "DetectionYoloV8Plates"
.
Error messages generated by Python post-processors now include the filename and line number where the error occurs. This should simplify debugging of Python post-processor code.
degirum.connect
performance is greatly improved for large cloud zoos. In the previous versions the whole content of the cloud zoo with all model parameters is downloaded from the cloud server. With 1000+ models public model zoo this process may take few seconds with slow Internet connection. Now the model parameters are downloaded on-demand, and degirum.connect
downloads only model names.
Added support of OpenVINO version 2024.6.0.
Added support of Intel Arc GPUs on Windows for OpenVINO runtime.
Dropped support for OpenVINO versions 2022.1.1, 2023.2.0.
InputShape
model configuration parameter is supported for models with "Image"
input type. Now you may specify input tensor shape in one line "InputShape": [<N>, <H>>, <W>, <C>]
instead of providing four lines with four InputN/H/W/C
individual parameters.
Default values for the following model configuration parameters are changed:
OutputConfThreshold
0.1
0.3
MaxDetections
20
100
MaxClassesPerDetection
30
1
Maximum supported model parameters configuration version is increased from 9 to 10.
Separate output for pose keypoint heads is supported in pose detection post-processor.
YOLOv8 instance segmentation post-processor is integrated.
Numerous critical bugs have been fixed in Hailo runtime plugin.
Note: For Hailo plugin users it is strongly recommended to upgrade PySDK to version 0.14.3
The following error may appear intermittently on systems NOT equipped with ORCA USB: "libusb: error [cache_config_descriptors] could not access configuration descriptor 0 (actual) for 'USB\VID_0627&PID_0001***': [995] The I/O operation has been aborted because of either a thread exit or an application request."
AI Server configured with HTTP protocol may crash intermittently with Access-Violation/SEGFAULT error when model inference with erroneous configuration is requested.
TensorRT runtime agent changes:
supported TensorRT version is updated from 8.5 to 10.6;
added support for x86-64 architecture.
ORCA1 firmware version 1.1.22 is included in this release. It contains numerous bug fixes targeted to improve reliability of ORCA1 USB operation.
Pose detection postprocessor now supports models with multiple classes.
Various bug fixes related to ORCA1 USB device operation.
AI server memory monitoring of Python postprocessor execution sometimes gives false-positives and prevents normal execution of Python postprocessors.
ORCA1 firmware version 1.1.21 is included in this release. It contains numerous bug fixes targeted to improve reliability of ORCA1 USB operations.
Object blurring option is implemented in PySDK object detection results renderer. To control blurring you use degirum.model.Model.overlay_blur
property of the Model
class.
Assign None
to disable blurring (this is the default value): model.overlay_blur = None
.
To enable blurring of all detected bounding boxes, assign "all"
string : model.overlay_blur = "all"
.
To enable blurring of bounding boxes belonging to a particular class, assign that class label string: : model.overlay_blur = "car"
.
To enable blurring of bounding boxes belonging to particular class list, assign a list of class label strings: model.overlay_blur = ["car", "person"]
.
YOLOv8 postprocessor now supports both normalized and regular bounding boxes. It automatically infers that the boxes are normalized or not, and if they are normalized to unity, the boxes are adjusted to the images size. Note that the box outputs are typically normalized for TFLite models, while ONNX models usually do not provide normalization.
The error message similar to this "Shape of tensor passed as the input #0 does not match to model parameters. Expected tensor shape is (1, 0, 0, 77)"
appears when performing AI server inference of a model with Tensor input type of fewer than 4 dimensions, when those dimensions are specified using InputN/InputW/InputH/InputC
model parameters, for example, InputN: 1, InputC: 77
. The error does not appear when dimensions are specified using InputShape
model parameter.
ORCA1 firmware version 1.1.19 is included in this release. It contains numerous bug fixes targeted to improve reliability of ORCA1 operation.
Robust and secure Python postprocessor execution framework is implemented for AI server. Now all Python postprocessor code is executed in separate process pool in sandboxed environments as opposed to in-process execution in previous PySDK versions.
Device validation is implemented when you try to load a model from a cloud model zoo and the inference device requested by that model is not available. In such case the following exception is raised: "Model '{model}' does not have any supported runtime/device combinations that will work on this system."
timing
attribute is added to the inference result base class degirum.postprocessor.InferenceResults
. This attribute is populated with the inference timing information when degirum.model.Model.measure_time
property is set to True. The inference timing information is represented as a dictionary with the same keys as returned by degirum.model.Model.time_stats()
method.
degirum.model.Model.output_class_set
class label filtering is not applied when any degirum_tools
analyzers are attached to the model object by degirum_tools.attach_analyzers()
.
Significant (100x) performance drop of TFLITE/CPU
model inference when more than one virtual CPU device is selected for the inference (which is default condition).
AMD Vitis NPU is initially supported for Windows OS. The runtime/device designator for this device is "ONNX/VITIS_NPU"
.
Variable number of landmarks is supported in pose detection postprocessor. This is needed to support new face keypoints recognition models.
AI server ASIO protocol is improved to disconnect client in case of aborted inference without waiting for inference timeout.
ORCA1 firmware version 1.1.18 is included in this release. This firmware improves the mechanism of detection of DDR4 external memory link failures.
The error handling of critical ORCA hardware errors is improved: when such error is diagnosed during the inference, ORCA firmware is reloaded, ORCA is reinitialized, and the inference is retried once. If such retry succeeds, the error is not reported.
The performance of HWC -> CHW conversion in AI server pre-processor is improved. This affects inference speed of ONNX models with NCHW input tensor layouts.
The post-processor for YOLOv10 object detection models is implemented. The post-processor tag is "DetectionYoloV10"
.
cache-dump
subcommand is added to server
command of PySDK CLI. This subcommand queries the current state od AI server runtime agent cache. Usage example: degirum server cache-dump --host <hostname>
AI server tracing to stdout is implemented. To enable tracing, put __TraceToStdout=yes
trace configuration option into dg_trace.ini
trace configuration file. Traces will be printed to stdout in JSON format, compatible with log collection services such as DataDog, Loki/Grafana, and Elastic/Kibana. To enable tracing for all AI server events, additionally put AIServer=Detailed
trace configuration option into dg_trace.ini
trace configuration file.
When cloud server responds with cloud inference error details, the detailed message is not included into the text of the raised exception.
N2X runtime agent fails to load on Linux systems when /dev/bus/usb
device is not available. This leads to inability to use N2X/ORCA1
and N2X/CPU
inference devices on such systems. This problem affects PySDK installations running on virtual machines and inside Docker images started in non-privileged mode.
Added support of OpenVINO version 2024.2.0.
YOLO segmentation model postprocessing support is implemented in degirum.postprocessor.DetectionResults
class.
degirum version
command is added to PySDK CLI. Using this command you may obtain PySDK version.
degirum.zoo_manager.ZooManager.system_info()
method added. This method queries the system info dictionary of the attached inference engine. The format of this dictionary is the same as the output of degirum sys-info
command.
Now to access the DeGirum public cloud model zoo there is no need to use cloud API token. So, the following code will just work:
ORCA1 firmware version 1.1.15 is included in this release. This firmware implements measures to reinitialize DDR4 external memory link in case of failures. This reduces the probability of runtime errors such as "Timeout waiting for RPC EXEC completion"
.
ORCA1 firmware is now loaded on AI server startup only in case of version mismatch or previously detected critical hardware error. In previous AI server versions it was reloaded unconditionally on every start.
degirum.model.Model.device_type
property now can be assigned for single-device models (models for which SupportedDeviceTypes
model parameter is not defined). In previous PySDK versions such assignment always generated an error "Model does not support dynamic device type selection: model property SupportedDeviceTypes is not defined"
.
Google EdgeTPU AI accelerator support was broken in PySDK ver. 0.13.0. Now it is restored.
Plugin for RKNN runtime is initially supported. This plugin allows performing inferences of .rknn
AI models on RockChip AI accelerators, including:
TFLite plugin now supports the following inference delegates:
NXP VX
NXP Ethos-U
ArmNN
The device_type
keyword argument is added to degirum.zoo_manager.ZooManager.list_models
method. It specifies the filter for target runtime/device combinations: the string or list of strings of full device type names in "RUNTIME/DEVICE" format. For example, the following code will return the list of models for N2X/ORCA1 runtime/device pair:
New functions have been added to PySDK top-level API:
degirum.list_models()
degirum.load_model()
degirum.get_supported_devices()
These functions are intended to further simplify PySDK API.
The function degirum.list_models()
allows you to request the list of models without explicitly obtaining ZooManager
object via degirum.connect()
call. It combines the arguments of degirum.connect()
and degirum.zoo_manager.ZooManager.list_models()
which appear one after another, for example:
5. The post-processor for YOLOv8 pose detection models is implemented. The post-processor tag is `"PoseDetectionYoloV8"`. 6. Pre-processor letter-boxing implementation is changed to match Ultralytics implementation for better mAP match. 7. ORCA firmware loading time is reduced by 3 seconds.
"Timeout 10000 ms waiting for response from AI server"
error may happen intermittently at the inference start of a cloud model on AI server, when AI server has unreliable connection to the Internet due to incorrect timeouts on the client side.
Model filtering functionality of degirum.zoo_manager.ZooManager.list_models
method works incorrectly with multi-device models having device wildcards in SupportedDeviceTypes
. For example, if the model has SupportedDeviceTypes: "OPENVINO/*"
, then the call inference_manager.list_models(device="ORCA1")
returns such model despite "ORCA1" device is not supported by "OPENVINO" runtime.
AI accelerators are initially supported for Linux OS. The runtime/device designator for these devices is "MEMRYX/MX3"
. Please refer to for installation details.
AI accelerators are initially supported for Linux OS for Akida Runtime version 2.11.0. The runtime/device designators for these devices are "AKIDA/NSoC_v1"
, "AKIDA/NSoC_v2"
, "AKIDA/AKD1500_v1"
. Please refer to for installation details.
AI accelerators are initially supported for Linux OS. The runtime/device designator for these devices are "HAILORT/HAILO8"
and "HAILORT/HAILO8L"
. Please refer to for installation details.