Hello, I want to train an yolo_V4 on a custom dataset. I made a post TAO augmentation question , but I need more info now. So if I set in the training config the following: output_width: 600 output_height: 600 output_channel: 3 And if I have images of size 320x340, 600x400, 800x800 (for example),…

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks After the images/labels are augmented accordingly, TAO yolov4 will use cv2 to resize to output_width and output_height. This is …

Tao input size yolo_V4

Accelerated Computing Intelligent Video Analytics TAO Toolkit

Morganh September 29, 2022, 2:16am 3

The augmentation method is mentioned in YOLOv4 - NVIDIA Docs

Yes, the TAO can modify the labels as well.

Topic		Replies	Views
TAO augmentation question TAO Toolkit	2	535	August 12, 2022
Questions regarding the preparation of images for training yolo_v4 model on TAO toolkit TAO Toolkit	5	634	January 17, 2024
TLT yolo_v4 image resizer during evaluation TAO Toolkit	2	417	October 12, 2021
Yolov4 for different input size, pretrained model weights for the different sizes TAO Toolkit	31	4582	February 24, 2022
ERROR: Input to reshape is a tensor with 2108 values, but the requested shape has 2074 TAO Toolkit	2	659	April 17, 2023
Preprocessing Images TAO Toolkit	2	445	October 12, 2021
YOLO V4 TLT general questions on dataset TAO Toolkit	2	628	October 12, 2021
Tuning of Parameters TAO Toolkit	13	687	November 24, 2021
TAO input image resizing TAO Toolkit	9	1257	April 18, 2022
Relationship between training dataset size and inference data size TAO Toolkit	12	812	February 22, 2022

Tao input size yolo_V4

Related topics