You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to run the MMYOLO model by converting it to TFLite. Converted the YOLO v5 to onnx file as per the documentation. Then I used the TFLite converter to convert onnx to TFLite. Onnx detections were correctly classified, whereas the TFLite detections are empty. Will MMYOLO support only tensor RT engine or will the model structure support TFLite also?
Environment
sys.platform: win32
Python: 3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]
CUDA available: False
MUSA available: False
numpy_random_seed: 2147483648
MSVC: Microsoft (R) C/C++ Optimizing Compiler Version 19.40.33811 for x64
GCC: n/a
PyTorch: 2.0.0+cpu
PyTorch compiling details: PyTorch built with:
C++ Version: 199711
MSVC 193431937
Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
Prerequisite
💬 Describe the reimplementation questions
I am trying to run the MMYOLO model by converting it to TFLite. Converted the YOLO v5 to onnx file as per the documentation. Then I used the TFLite converter to convert onnx to TFLite. Onnx detections were correctly classified, whereas the TFLite detections are empty. Will MMYOLO support only tensor RT engine or will the model structure support TFLite also?
Environment
sys.platform: win32
Python: 3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]
CUDA available: False
MUSA available: False
numpy_random_seed: 2147483648
MSVC: Microsoft (R) C/C++ Optimizing Compiler Version 19.40.33811 for x64
GCC: n/a
PyTorch: 2.0.0+cpu
PyTorch compiling details: PyTorch built with:
OpenCV: 4.10.0
MMEngine: 0.10.4
MMCV: 2.0.1
MMDetection: 3.3.0
MMYOLO: 0.6.0+
Expected results
Additional information
I want TFLite also to give the same result as onnx while deploying MMYOLO.
The text was updated successfully, but these errors were encountered: