-
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…
-
[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
-
If you want to report a bug - provide:
* description of a bug: **Failed to build yolo_v3_tiny_pan_lstm from issue 3114**
* what command do you use? `darknet detector train data/self_driving.…
-
first of all. thanks for your cool work.
I run the darknet_video.py . and it give me inference time about 14s I change darknet_video.py to print time not fps. one frame. Is this normal?
*…
-
I have 4-channel RGBA png image. I wanted to train a tiny-yolo model from scratch.
I made channels = 4 in my cfg file. But when I run the training it crashes after 1st iteration itself.
Crash log:…