-
This is a fairly involved rearchitecting of `droidlet`, so I'll provide as much context as possible.
I've discussed this with @kavyasrinet and @aszlam who both approved this direction.
## Motivati…
-
Status:
Dockerfile built.
Docker Tested. Compiled
Next TODO: Fix error [#11](https://github.com/event-driven-robotics/event-driven-demos/issues/11)
-
Hey, thank you for your fast reply.
I tried to run the model for training data with 2 keypoints detection (not human pose estimation), but the loss of the keypoint mask branch is high, and the model …
ghost updated
5 years ago
-
Could you please share the npz files for SMPL-H model?
I get the following error:
```
[jalal@goku smplx]$ python examples/demo.py --model-folder /scratch3/3d_pose/humanpose/SMPL_models/models -…
-
Hello everyone, I have some problem when build and run Torchserve with ONNX model and GPU. This is my log:
```
WARNING: sun.reflect.Reflection.getCallerClass is not supported. This will impact pe…
-
I'm trying to run it on a local machine instead of the google collab demo
I have setup my local env, all required packages installed (and made sure to get a Pytorch+Pyvision version without CUDA) s…
-
### My Computer Specs
CPU: Ryzen 7 4800H
GPU: RTX 3050 Mobile GPU
RAM: 24GB
SSD: 512GB + 256GB
Run Docker with Windows Sub-System Linux Ubuntu 20.04 (WSL integration enabled)
### 🐛 Describe th…
-
Hi @waleedka : Thanks for the great work! Is it possible to train for keypoint detection? Sorry for the wrong title of the issue, I can't correct it.
-
Hi guys, I have a question: Can TorchServe run detect task in real-time? I developed a surveillance camera app written in Python with input are camera, inside the app, I send the frame from camera to …
-
**Describe the bug**
*Section: Prepare calibration datasets*
Code block:
```
import datasets
num_inference_steps = 20
subset_size = 200
dataset = datasets.load_dataset("jschoormans/humanpos…