-
@roytseng-tw Hi,
I run the inference based on your `infer_simple.py` successfully .
At same environment (one gpu, same machine, same folder path), i use it in Jupyter for inference, but give me er…
-
(densepose2) wag@wag-SYS-7049GP-TRT:/home/ssl/ssl/detectron2/projects/DensePose$ python apply_net.py show configs/densepose_rcnn_R_50_FPN_s1x.yaml densepose_rcnn_R_50_FPN_s1x.pkl image.jpg dp_contour,…
-
Hi,
I used trained from model on my input image and it generated output image with the following code.
`!python apply_net.py show configs/densepose_rcnn_R_50_FPN_s1x.yaml model_final_dd99d2.pkl…
-
Hello,
I'm running Densepose in Docker container with mounted data, first test runs OK
```
root@a182491c8d77:/densepose# python2 detectron/tests/test_batch_permutation_op.py
No handlers could be…
-
As is mentioned in the title above, how can I visualize the training net with net_drawer?
I just added several lines in the files "/home/liangu/densepose/densepose/detectron/utils/train.py", as foll…
-
## Instructions To Reproduce the 🐛 Bug:
1. installing the following using pip in collab notebook :
- torch==1.10.1+cu102 torchvision==0.11.2+cu102 torchaudio==0.10.1 -f https://download.pytorch.org/…
-
hi all,
I'm trying to use the detectrone2 - densepose to produce 3 channel IUV image.
My procedure description:
used build line (from Detectron2 install page):
```
python -m pip install det…
ghost updated
2 years ago
-
(Pose) jaskaran@jaskaran-pc:~/densepose$ python2 tools/infer_simple.py --cfg configs/DensePose_ResNet101_FPN_s1x-e2e.yaml --output-dir DensePoseData/infer_out/ --image-ext jpg --wts ht…
-
@vkhalidov I'm trying to use segmentation map for a dataset that I'm creating but I see some random dark spots in the segmentation map that is produced by the model I'm using the default configuration…
-
**Host System:**
-Ubuntu 18.04.1
-RTX 2080ti
- Cuda 10
- nvidia driver 410
- Cudnn 7.3.0
**Running Docker Image:**
densepose:c2-cuda9-cudnn7
root@4cf2a710d35b:/densepose# nvidia-smi…