-
Hello guys, as you know tensorflow has several methods for model quantization after finish training in order to reduce size with a bit of accuracy trade off. I am wondering is there any similar featur…
-
To reduce anchorboxes from five to one, i tried editing config file, but training is throwing error. Also i am not able to load back end weights alone, when given backend weight file name in config, i…
-
Since they framed detection as a YOLO problem, I assume they have weights and biases. (eg. the classic equation for regression: y = xW + b, where W is the weights and b is the bias). Does this just me…
-
Hi,
has anyone ever tried to use more or less anchors than the default (=9)?
Even though "gen_anchors.py" allows for more anchors to be computed, "yolo.py" seems to be hard coded to exactly 9 an…
-
Traceback (most recent call last):
File "demo.py", line 37, in
net_utils.load_net(trained_model, net)
File "/home/pcrane/yolo2-pytorch/utils/network.py", line 66, in load_net
param = …
-
**after running `python demo.py`, an error occur.**
**I install all the packages in anaconda's `pytorch` env. my opencv is 2.4.10( conda install opencv=2.4.10)**
```
OpenCV Error: Unspecified e…
-
## **Environment info**
```
----------Python Info----------
('Version :', '2.7.12')
('Compiler :', 'GCC 4.4.7 20120313 (Red Hat 4.4.7-1)')
('Build :', ('default', 'Jul 2 2016 1…
-
I wanna ask if it is possible to use 1 channel images data to train and test
I already finish the training part, but when I run the predict.py it always problem
I only changed yolo.py line 232 from
…
-
I follow procedure with no problem until:
make
./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg
if I excecute 'make'
I get: '*** No targets specified and no makerfile found. Stop.'
if…
-
I got the following issue no matter I turn on GPU flag or not.
./src/additionally.c: At top level:
./src/additionally.c:416:6: error: conflicting types for ‘transpose_bin’
void transpose_bin(uin…