search

dusty-nv / ros_deep_learning

Deep learning inference nodes for ROS / ROS2 with support for NVIDIA Jetson and TensorRT
879 stars 257 forks source link

Jetson-nano #15

Closed knoob-noob closed 4 years ago

knoob-noob commented 5 years ago

Would this work with jetson nano? Jetpack and jetson inference provide support for nano. If after installing them, I try to build ros_deep_learning package on jetson nano, would it work?

dusty-nv commented 5 years ago

Yes, install the L4T-R32.1 branch of jetson-inference and it should work

From: knoob-noob notifications@github.com Sent: Wednesday, July 31, 2019 7:02:02 AM To: dusty-nv/ros_deep_learning ros_deep_learning@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [dusty-nv/ros_deep_learning] Jetson-nano (#15)

Would this work with jetson nano? Jetpack and jetson inference provide support for nano. If after installing them, I try to build ros_deep_learning package on jetson nano, would it work?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/dusty-nv/ros_deep_learning/issues/15?email_source=notifications&email_token=ADVEGK4KGRFPVS6H4UJCCKTQCFWKVA5CNFSM4IIFN3LKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HCRDQXA, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ADVEGK4C2JGXPX2IYTA5WQLQCFWKVANCNFSM4IIFN3LA.

This email message is for the sole use of the intended recipient(s) and may contain confidential information. Any unauthorized review, use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.

knoob-noob commented 5 years ago

Hey! Thanks for the reply. These are the steps I followed- First I installed jetpack on jetson nano. Then, I cloned the master repo and followed the appropriate steps. After this, I was able to use jetson inference to do image recognition and object detection. Then, I tried building the ros_deep_learning package but got an error while doing catkin_make.

Then, I found out that I'm supposed to be installing the L4t-R32.1 branch, so I deleted the jetson-inference folder and installed the L4T-R32.1 branch, and after this, I couldn't do image recognition or detection. Getting the following errors (after running **./imagenet-console --network=googlenet orange_0.jpg output_0.jpg) : imageNet -- failed to initialize. imagenet-console: failed to initialize imageNet**

Can you please tell how to resolve these issues?

Thanks.

knoob-noob commented 5 years ago

Also, can you please tell me whether I should clone L4TR32.1 branch using this command - git clone -b L4T-R32.1 https://github.com/dusty-nv/jetson-inference or is this not the proper way to clone here?

Because after following the steps mentioned at https://github.com/dusty-nv/ros_deep_learning, (but using the above command to clone the repo), when I run cmake ../ and sudo make install,it's not downloading the models on it's own, and when the make is complete, the model downloader file (download-models.sh) along with some other files is missing from the tools directory.

How do I fix these issues?

dusty-nv commented 4 years ago

The ros_deep_learning repo has now been updated for JetPack 4.2 and to build against jetson-inference master. Let me know if you have any more problems building it.