-
While testing the new Sagemaker endpoints and bulk upload workflow, I ran into an issue with the AWS SDK for JS' SagemakerRuntime InvokeEndpoint command while trying to upload a zip file of 50 images …
-
Once you've done the Colab version, try installing everything locally. They have a docker container version or you can also install all the dependencies directly in your global environment. If you're …
-
We ran into an issue where separate_detections_into_folders.py was crashing when run with the --render_boxes flag. The error was essentially that you could not use quality=keep when original image is…
-
Hi Dan,
thank you for your quick reply! (Issue #290 )
after running the pipeline:
* find_repeat_detections.py
* manually removing false posittives
* remove_repeat_detections.py
I end up with a…
-
What do you think about changing the separate_images() function to call the [megadetector separate_detections_into_folders.py ](https://github.com/microsoft/CameraTraps/blob/main/api/batch_processing/…
-
I had a quick question about the [`data_management`](https://github.com/microsoft/CameraTraps/tree/main/data_management) folder. A few of the scripts at the root in that folder mention that they are "…
-
Hi Peter,
I'm having similar issues as to Rolland from before where deploying the model leads to an error with lines 1100 and 951 in the EcoAssist_GUI.py. I've updated my Git and completely uninsta…
-
I'm working on a Linux machine. When preparing the "cameratraps-detector" environment from the environment-detector.yml file, I kept getting a series of errors regarding the ipython_genutils module:
…
-
## User story
We need to understand the cost of running the current architecture inference on large archives (25 Gb) of imagery. In terms of both time (does it take a week with retries? 2 days?) an…
-
### 🐛 Describe the bug
I am getting slightly but significantly different results when running inference with Torchserve vs locally, due to the image input being slightly modified somewhere within t…