dnth/yolov5-deepsparse-blogpost
By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using on
Jupyter Notebook
Issues
- 6
export.py error
#5 opened by lucheng07082221 - 6
- 0
No inerence
#21 opened by TDBTECHNO - 1
- 2
Convert ONNX model to Other Formats
#9 opened by sharoseali - 2
export.py error
#19 opened by dani3l125 - 1
- 0
Why is there no significant change in model size after pruning and quantization?
#17 opened by Pass-O-Guava - 2
- 0
Failed to load the checkpoint after completion of model training in Google Colab
#15 opened by abirsince92 - 0
Error in change epoic count
#13 opened by VYRION-Ai - 0
- 0
- 5
- 4
Export pytorch lite model
#7 opened by abdelaziz-mahdy - 1
unable resume training
#6 opened by chillum-codeX - 0
export.py error
#4 opened by lucheng07082221 - 4
how to do resume of training? should i need to train for 300 epoch to get quantised ,model?
#3 opened by akashAD98 - 7
Error with training and export
#2 opened by santoshmedisetty - 1
Colab notebook
#1 opened by dnth