Compatibilities of Deep Learning Steps¶
This section clarifies compatibilities of Steps related to deep learning.
Instance Segmentation¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
Compatible Mech-DLK Version |
Model and Configuration File Extension(s) |
1.4.0 |
1.4.0 |
Instance Segmentation * |
1.4.0 |
.pth/.py |
1.5.x |
2.0.0/2.1.0 |
1.4.0 |
.pth/.py |
|
2.0.0/2.1.0 |
.dlkmp/.dlkcfg |
|||
1.6.0 |
2.0.0/2.1.0 |
1.4.0 |
||
2.0.0/2.1.0 |
||||
Environment not required |
Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) |
2.2.0 |
||
1.6.1 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
1.6.2 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
* Please start the deep learning server for the Step.
Image Classification¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
Compatible Mech-DLK Version |
Model and Configuration File Extension(s) |
1.4.0 |
1.4.0 |
Image Classification * |
1.4.0 |
.pth/.json |
1.5.x |
2.0.0/2.1.0 |
Image Classification * |
1.4.0 |
.pth/.json |
Deep Learning Inference |
2.0.0/2.1.0 |
.dlkpack |
||
1.6.0 |
2.0.0/2.1.0 |
Image Classification * |
1.4.0 |
|
Environment not required |
Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) |
2.0.0/2.1.0 |
||
Deep Learning Model Package Inference (Mech-DLK 2.2.0+) |
2.2.0 |
|||
1.6.1 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
1.6.2 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
* Please start the deep learning server for the Step.
Object Detection¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
Compatible Mech-DLK Version |
Model and Configuration File Extension(s) |
1.4.0 |
1.4.0 |
Object Detection * |
1.4.0 |
.pth/.py |
1.5.x |
2.0.0/2.1.0 |
Object Detection * |
1.4.0 |
.pth/.py |
Deep Learning Inference |
2.0.0/2.1.0 |
.dlkpack |
||
1.6.0 |
2.0.0/2.1.0 |
Object Detection * |
1.4.0 |
|
Environment not required |
Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) |
2.0.0/2.1.0 |
||
Deep Learning Model Package Inference (Mech-DLK 2.2.0+) |
2.2.0 |
|||
1.6.1 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
1.6.2 |
Environment not required |
Deep Learning Model Package CPU Inference/ Deep Learning Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpackC/.dlkpack |
* Please start the deep learning server for the Step.
Defect Detection¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
Compatible Mech-DLK Version |
Model and Configuration File Extension(s) |
1.4.0 |
1.4.0 |
Defect Detection * |
1.4.0 |
.pth/.py |
1.5.x |
2.0.0/2.1.0 |
Deep Learning Inference |
2.0.0/2.1.0 |
.dlkpack |
1.6.0 |
Environment not required |
Deep Learning Inference (Mech-DLK 2.1.0/2.0.0) |
2.0.0/2.1.0 |
.dlkpack |
Deep Learning Model Package Inference (Mech-DLK 2.2.0+) |
2.2.0 |
|||
1.6.1 |
Environment not required |
Deep Learning Model Package Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpack |
1.6.2 |
Environment not required |
Deep Learning Model Package Inference (Mech-DLK 2.2.0+) |
2.2.1 |
.dlkpack |
* Please start the deep learning server for the Step.
Predict Pick Points (Any Object)¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
1.6.1 |
Environment not required |
Grasp Pose Estimation |
1.6.2 |
Environment not required |
Predict Pick Points (Any Object) |
Predict Pick Points (Single Object Type)¶
Mech-Vision Version |
Mech-Mind Software Environment Version |
Mech-Vision Step |
Model and Configuration File Extension(s) |
1.6.2 |
Environment not required |
Predict Pick Points (Single Object Type) |
.onnx |
Note
Please contact Mech-Mind Technical Support for the model in ONNX format.