Michael Nielsen

Changing weight parameter in loss function and how to use weighted_binary_cross_entropy

1

Hi, So far getting good results on image segmentation with cntk, and I tried different loss functions to tweak the desired result. Using fixed class weights is simple enough, (unless...

I train in python, and included evaluation of models in a c++ mfc singledoc/view program that was always very fast to open. After including cntk it is slow to open...

Pretrained models

3

Hi, using download_model.py in cntk-2.7\PretrainedModels gives error: HTTP Error 403: Site Disabled https://github.com/microsoft/CNTK/blob/master/PretrainedModels/Image.md

Tiny YOLOv3 , Yolov3 in ONNXRuntime C API vs Python

1

These two models have unknown dimensions, so the input and output shapes have -1 in them in C api. and in python yolov3 has variable names in their place. I...

I am trying to connect two alvium 1500 cameras on jetson nano B01 with two Mipi CSI connectors. I tried the preinstalled 4.2.2 SD image from Allied Vision webpage, and...

Where is the Dataloader for OBB data

9

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question In the original repo for yolov5 v 5-6 it...

I have to comment out the chat_history append for it to work. if the conversation is added to the history, only the first question I ask will receive an answer....

cls loss detection with 1 class / changes in general

6

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question In yolov5 5.0-6.2 cls loss with one class was...