Viet-Hoang Tran

Results 23 comments of Viet-Hoang Tran

Hi, I have a same question as comment above. I want to use PVTv2 as the backbone for tracking model. I tried to connect tensors of four stages and apply...

> @hoangtv2000 Hello, did you divide PVT2 into 4 stages or using an iteration method? I have some confusion I just concatenate 4 tensors by shape[1] and apply zero padding...

After following the installation requirements, I restarted the kernel and solved this issue.

In my case, I downgrade the Python to 3.7 and Install Tensorflow==1.13.1 and the model works fine.

Hi @sandeep1404, I am getting an error at Batchnorm same as yours. Have you solve this bug yet? If yes, please guide me how to solve it.

> I think one of the best ways to do NMS is to use the OpenCV function `cv2.dnn.NMSBoxes` > > Here is my impplemntion for Yolov8 from A to Z...

> So AIMET does not support Qoperator format in ONNX, right? > > Is there any method which could convert QDQ to Qoperator in ONNX? Hi @JiliangNi, have you found...

Hi @peterjc123, Thanks for your reply, I had some experiments and I realized that I have to run model_rewrite() to train my model. Models that do not use this method...

Thanks @zk1998, Here is my script ```python import sys, os, argparse, random sys.path.append(os.getcwd()) RANK = int(os.getenv("RANK", -1)) import torch import torch.nn as nn import torch.optim as optim import torch.quantization as...

I saved the rewritten model and load it with ```QATQuantizer()``` with the setting ```'rewrite_graph': False, 'force_overwrite': False```. But It takes me 20 epochs to achieve 0.04 mAPs 😃. Although the...