-
@AlexeyAB Hey, I tried int8 version for tiny yolo2 but it only localizes the object but does not classify the class of the object. does this code only localize the objects and not classify ?
Thank…
-
I follow the instructions to put the PB and txt files in the assets folder. After the app opens, it will flash back. I am training the yolo2 to do face detection. The output is 30=5*6. What is the rea…
-
Dear all:
I have been training this network thousands of iterations, but I nearly cannot find any change about the loss value. So what's wrong? Does anyone have validated its validity?
![yolo](h…
-
Hello,
I'm looking for some help with custom anchors. When I use the custom anchors methodology provided in the repo, the model has about 5% lower MAP compared to when using the default anchors. He…
-
When I run gen_anchors.py or train.py, it occurs :
Traceback (most recent call last):
File "gen_anchors.py", line 5, in
from preprocessing import parse_annotation
File "/home/liuweihuang/…
-
First thanks you for the great tutorial. Second, I have a problem when I want to train Yolo2, I did everything you said from converting the txt files correctly, through creating the 3 cfg files, and a…
-
Hello, everyone
I get the 'model.ckpt' from yolo-voc.weights, using parse_darknet_yolo2.py.
Then, I want to check the 'model.ckpt'. I get a trouble 'Tensor had NaN values' when I run detect.py with…
-
https://github.com/experiencor/keras-yolo2/blob/4e8c85ce02435f136d4f4cfe930b4ccb759fbaf8/gen_anchors.py#L103
Very minor but I guess this should be args? code works because args are global. Not big …
-
I'm sorry to bother you, but I'm running the program according to your steps, using Pycharm, tensorflow1.1, opencv3.0, which is wrong and can't be done. Please answer it.
File "darkflow/cython_util…
-
Hi,
When I read the code, I found something hard to understand:
1. In the code train.py, you randomly chose a scale index for training image every cfg.disp_interval. (https://github.com/longcw/yo…