Jacinto 7 TIDL Release Notes
Version: 08.05.00, Date: Dec 09, 2022
Contents
- Introduction
- Licensing
- What's New
- Documentation
- Upgrade and Compatibility Information
- Device Support
- Validation Information
- Fixed Issues
- Known Issues
- Change Request
- Technical Support
- Package Versioning
Introduction
This package contains Texas Instrument's Deep learning solution for J721E SoCs from the Jacinto 7 family
Licensing
The licensing information of this product, as well as any third-party components included which are made available under a number of other open-source licenses are enumerated as part of the manifest. Note : Below Links would work only after installing the package
Documentation
1 | User's Guide | [HTML] |
2 | Software Manifest | [HTML] |
What's New
Here are a few of the new features supported in this release:
- Optimization of DDR footprint for inference of a network with multiple resolutions
- APIs to query/collect layer level performance statistics
- Support for Scatter ND layer
Upgrade and Compatibility Information
This release is interface compatible with previous release. Note : Model's imported/compiled with previous release versions will not work with this release. User is expected to re-import/re-compile models with this release before using it
Device Support
Target SoC | Target Plaform | Build environment (OS) | Target environment (OS) |
J721E EVM | x86_64 Linux PC | x86_64 (Linux) | NA |
Validation Information
This release was built and validated using the following tools:
Dependencies (included in Processor SDK RTOS):
- ivision - 01_00
- MMALIB - 02_05_00_07
- PDK - CORE SDK 08.05.00
- C7x CGT - ti-cgt-c7000_3.0.0.STS
Dependencies (NOT included in Processor SDK RTOS):
- GCC version 5.4.0 (In Ubuntu 18.04)
- OpenCV: 4.1.0 (for Test bench Only)
- Protobuf: 3.11.3 (for Import tool only)
- Flatbuffers : 1.12.0 (for Import tool only)
Fixed Issues
ID | Description | Module | Affected Versions | Affected Platforms |
---|---|---|---|---|
[TIDL-2856] | ONNX import of MaxPool returns error on absence of optional op attributes | TOOL | 08.04.00, 08.02.00, 08.01.00, 08.00.01, 08.00.00, 02.00.00, 01.04.00, 01.03.00, 01.02.00, 01.01.00, 01.00.00 | J721E |
[TIDL-2783] | OSRT : Models with post processing not optimized for C7x not identified as OD and result in incorrect layer delegation to C7x/MMA instead of ARM | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00/td> | J721E |
[TIDL-2523] | Functional issue for tflite efficientdet model with data convert layer enabled | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2515] | Tflite/Tensorflow flatten layer with input width != 1 and height != 1 gives functionally incorrect output | COMPUTE | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2847] | edgeai-tidl-tools tidlrt example failing | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2885] | Tflite runtime : Compilation can result in memory corruption if input height != input width | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2886] | ONNX runtime : Reshape-Transpose-Reshape combination of layers delegated to C7x even when not supported | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2584] | Multi instances of TIDL on a single core may not work without enabling preemption feature | COMPUTE | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
[TIDL-2603] | Poor accuracy for Inner product and Global Average pool layers with Clip activation | TOOL | 08.04.00, 08.02.00, 08.01.00,08.00.01, 08.00.00, 02.00.00 | J721E |
Known Issues
ID | Description | Module | Reported in Release | Affected Platforms | Occurrence | Workaround in this release |
---|---|---|---|---|---|---|
TIDL-1197 | Model execution order for a branch is not optimal | COMPUTE | 01.02.00 | J721E | Rare | No fucntional issue, Only Performance drop would be obsrved |
TIDL-1530 | Processing on EVM gets stuck in case of "GEMM" layer in onnx model | OSRT | 02.00.00 | J721E | Rare | set reservedCtrl=1 of TIDL_CreateParams |
TIDL-1872 | Import failure for deeplabv3 (mobilenetv2 backbone) based OD+SEG Model | COMPUTE | 08.01.00 | J721E | Rare | |
TIDL-2593 | OSRT : Softmax layer with non-flattened input gets delegated to C7X-MMA instead of ARM | OSRT | 08.02.00 | J721E | Rare | Introduce a flatten layer before softmax or set softmax layer in deny_list runtime option |
TIDL-2888 | Network with more than 16 subgraphs cannot be run using ONNX runtime | OSRT | 08.04.00 | J721E | Rare | NA |
TIDL-2878 | OSRT : Optimized OD post processing results in crash in case all convolution heads are not part of same subgraph | OSRT | 08.04.00 | J721E | Rare | NA |
TIDL-2822 | TFLite Runtime : Pre quantized object detection model has accuracy issue | OSRT | 08.04.00 | J721E | Rare | NA |
TIDL-2821 | 16-bit convolution with pad = 0 results in hang | OSRT | 08.04.00 | J721E | Rare | NA |
For latest status of the issues and any new issues found post this release, please refer TI External software Incident Report. Issues on this product can be filtered with search query as project = EXT_EP AND issuetype in (Bug, Enhancement) AND Product ~ "TI Deep Learning Library"
Change Request
ID | Description | Original Fix Version | New Fix Version |
---|---|---|---|
JACINTOREQ-5006 | TIDL: Descope of 8.5 Requirements related to performance optimization | 08.05.00 | 09.00.00 |
JACINTOREQ-5007 | TIDL: Descope of 8.5 Requirements related to improving allowlisting and preprocessing | 08.05.00 | 08.06.00 |
Technical Support
For technical support, please post your questions on TI E2E Forum for Processors.
For additional assistance, contact local TI Field Application Engineer
Package Versioning
Each package version is composed of 4 period-delimited numbers - represented here by the letters M, m, p and b [M.m.p.b]
. The table below provides a descriptive reference regarding package version numbering.
Digit | Meaning | Description |
---|---|---|
1 (M=Major) | Major revision | Incremented when the new version is substantially different from the previous For example, a new module added or an existing module's algorithm significantly altered. |
2 (m=minor) | Minor revision | Incremented when the new version has changed but not in a major way. For example, some minor changes in the API or feature set. |
3 (p=patch) | Patch number | Incremented for all other source code changes. This include any packaging support code. |
4 (b=build) | Build number | Incremented for each release delivery to CM. Reset for any change to M, m or p |
© Copyright 1995-2021, Texas Instruments Incorporated. All rights reserved.
Trademarks | Privacy policy | Terms of use | Terms of sale