-
I am trying to make your powerful library with an RTX 3070 Ti.
After creating a python 3.8 anaconda environment with CUDA 11.3.1 and cuDNN 8.2.1
The lowest tensorflow version that properly utilzes m…
-
I think the most contribution in segnet is the idx-maxpooling. you can use the F.max_unpool2d(idx, x) to replace the nn.upsample().
The original upsample can't fit the loss of location information.
-
If I use the SenNet, do I need to compute the classweighting mentioned in the paper?
-
How to solve this problem
ERROR: cannot launch node of type [segnet_ros/segnet_action_server]: Cannot locate node of type [segnet_action_server] in package [segnet_ros]. Make sure file exists i…
-
when i was run the segnet.py raised this error:
raise ValueError('Unsupported image shape: ', x.shape)
ValueError: ('Unsupported image shape: ', ())
i would be grateful if you could answer this qu…
-
An error occurred while I was compiling. Here is my error message
jetbot@jetson-4-3:~/workspace/catkin_ws$ catkin_make
Base path: /home/jetbot/workspace/catkin_ws
Source space: /home/jetbot/wor…
-
Recently, i have change to use GTX1080, so i install cuda8 and the respectively cudnn v5. how can i change the code for my computer?
Regards!
-
I'm trying to testing bayesian segnet. I use command in the tutorial for testing :
`python ./SegNet/Scripts/test_bayesian_segnet.py --model SegNet/Models/bayesian_segnet_inference.prototxt --weights…
-
Hi all,
Very interesting blog article and codebase, thank you.
I was interested in trying to compare the various segmentation strategies mentionned in the blog article, and realized that the overal…
-
Hi Alex, thanks for sharing the code. I have a question regarding Segnet architecture.
In Segnet, the architecture is as follows, what confuses me is that there are two convolutional layer followin…