-
I have followed the instructions given for training on my own data set. I want to include more classes apart from the twenty for which the model is trained for. To start with, for testing purposes, I …
-
-
I have custom trained my model on 6 classes. I trained the 608*608 yolov3 and it works perfectly fine with model converting from darknet to caffe and then performing inference through Tensor-rt.
B…
-
Dear qqwwee and others,
1) Any hint how to change the code to use another number of anchors? (Especially only one anchor)
2) Any hint how to change the code to accept another neural network? (not …
-
I can not train to use random.
CFG:[yolo_v3_tiny_pan3_aa_ae_mixup_scale_giou.cfg.txt](https://github.com/AlexeyAB/darknet/files/4343162/yolo_v3_tiny_pan3_aa_ae_mixup_scale_giou.cfg.txt)
I use the…
-
Thank you for the great work.
I am trying to compile yolo v3 and yolo v3 spp to quantized tflite model but unable to do so.
I found out that, there are shortcut layers in yolo v3 and spp models wh…
-
First of all great work! I have many traffics sign images which has been categorized in folders of name of their type.I need to know how can I setup my images for training means:
1. How can I make a…
-
In yolov3_tiny network dimensions of the first yolo layer is `13 x 13 x 255` and dimensions of the second one is `26 x 26 x 255`. However, if we use a network configuration in which unlike yolov3_tiny…
-
Please could the docs be updated for more modern yolo versions like v3? Preferably v3/v3 -tiny?
Yolo v3 tiny has 2 outputs rather than 1, the structure of the model is quite different so this tut…
-
[net]
# Testing
batch=64
subdivisions=64
# Training
# batch=64
# subdivisions=64
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1…
yrc08 updated
3 years ago