ynjiun
ynjiun
Hi, Do we know is there a pytorch implementation of demon? Please point me to the github link if there is. Thanks a lot.
Hi, I have a question more related to SSD fundamental than any specific implementation: if my goal is to recognize all "foreground" objects and bbox them and not too much...
I run run_ssd_batch.py and found there are a lot of overlapped bounding boxes output with different confidence level. I assume that nms should remove the lower confidence overlapped bounding boxes...
Could anyone give an example command line on how to run prune_alexnet.py? Can we use prune_alexnet.py to extend to prune_sq_ssd_lite.py to prune sq_ssd_lite? What is a typical after pruning performance...
Hi, this is a great repository I am look for! Thanks a lot for your contribution. I am trying to do a transfer learning from your sq-ssd-lite to learn only...
Hi, I am able to run: docker run --gpus all -d -p 8888:5000 -v /data:/data nvcr.io/nvidia/digits:20.03-tensorflow-py3 and I would like to load my ssdlite-mobilenet-v3-kitti model trained by tensorflow-gpu==1.15 as my...
I tried to run the inference using a stereo images captured by my stereo camera using pretrained models. But none of them showing reasonable depth prediction. However, if I use...
Hi, I am impressed by your work and tried to run prediction on kitti dataset. It looks good. But when I tried to run prediction on a monochrome dataset captured...
Hi, I am developing an occupancy networks for road scene. I wonder how to generate an occupancy ground truth for an image captured from Carla. The idea is to generate...
Hi, I am loading and building a tensorflow model middlebury_d400.pb and encounter the following error message: ``` --> config model done --> Loading tensorflow model W:tensorflow:From /home/paul/rknn2/lib/python3.6/site-packages/tensorflow/python/tools/strip_unused_lib.py:86: extract_sub_graph (from tensorflow.python.framework.graph_util_impl)...