-
# Swish/SiLU
Do you have any plans to implement the Swish Op in ONNX?
### Describe the operator
Swish is a popular Activation fuction. Its mathematical definition could be found at https://en.wik…
-
Hiii...
I am using darkflow for object detection and deep-sort for tracking. But when I am running this with tiny-yolo weights and FLAG.gpu=0.3 it uses 35 - 45% CPU. I have installed tensor…
-
**Error**: **ValueError: Invalid layer: Functional**
(coreml) (base) MacBook-Pro-78:Convert michaelt$ python coreml.py
WARNING:root:TensorFlow version 1.15.0 detected. Last version known to be ful…
-
I have a question about **anchor free**.
In data.py, the boxes are assigned to different branches for regression.
**However, where are the thresholds( 30 and 90 ) derived?**
Welcome any explanati…
-
Hi @AlexeyAB,
I'm trying to find a repo to convert the weights that I'd trained using your repo, with a custom config based on yolov3.cfg file. After some researches, these are the repos that I've tr…
-
When I ran the prediction method, this line
out_scores, out_boxes, out_classes = sess.run([scores, boxes, classes], feed_dict={yolo_model.input: image_data, K.learning_phase(): 0})
gives me the fol…
-
Hi, I follow exactly the instructions in GitHub and I have installed all the necessary software. The only difference is I use Anaconda to run the code. I got the following error after I run `python ru…
-
Hi, thanks a lot for sharing your code. I tried implementing it with standard yolov3.weights and compare to darknet output, just out of interest. Unfortunately, I do get (slightly) odd results where t…
-
-
In YOLO V3 paper, they use multi-scale training, lots of data augmentation.
I don't know exactly whether they manually multiply original dataset through multi-scale training and data augmentation b…