Hello! Thank you in advance for any help!
I installed sapiens and its dependencies from the forked repository to ensure compatibility. But I got this error just for running the demo, using same pretrained checkpoints and inputs in keypoints17.sh
KeyError: 'Adafactor is already registered in optimizer at torch.optim', i
To solve this I downgraded torch to 2.4.1, and torchvision==0.19.1, then i got this Error: libcublasLt.so.11. Here is the full discription of the error.
Could not load library libcublasLt.so.11. Error: libcublasLt.so.11: cannot open shared object file: No such file or directory
Invalid handle. Cannot load symbol cublasLtCreate
./keypoints17.sh: line 87: 60511 Aborted (core dumped) CUDA_VISIBLE_DEVICES=${VALID_GPU_IDS[GPU_ID]} python ${RUN_FILE} ${DETECTION_CONFIG_FILE} ${DETECTION_CHECKPOINT} ${CONFIG_FILE} ${CHECKPOINT} --input "${INPUT}/imagepaths$((i+1)).txt" --output-root="${OUTPUT}" --save-predictions --radius ${RADIUS} --kpt-thr ${KPT_THRES} --thickness ${LINE_THICKNESS}
How can I fix any of these issues?
And this is my nvidia-smi
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.127.05 Driver Version: 550.127.05 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA RTX A2000 12GB Off | 00000000:17:00.0 Off | Off |
| 30% 26C P8 4W / 70W | 12MiB / 12282MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA RTX A2000 12GB Off | 00000000:73:00.0 Off | Off |
| 30% 29C P8 6W / 70W | 79MiB / 12282MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
| 2 NVIDIA RTX A2000 12GB Off | 00000000:A6:00.0 Off | Off |
| 30% 28C P8 4W / 70W | 12MiB / 12282MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 1886 G /usr/lib/xorg/Xorg 4MiB |
| 1 N/A N/A 1886 G /usr/lib/xorg/Xorg 64MiB |
| 1 N/A N/A 2002 G /usr/bin/gnome-shell 5MiB |
| 2 N/A N/A 1886 G /usr/lib/xorg/Xorg 4MiB |
+-----------------------------------------------------------------------------------------+
Hello! Thank you in advance for any help! I installed sapiens and its dependencies from the forked repository to ensure compatibility. But I got this error just for running the demo, using same pretrained checkpoints and inputs in keypoints17.sh KeyError: 'Adafactor is already registered in optimizer at torch.optim', i
To solve this I downgraded torch to 2.4.1, and torchvision==0.19.1, then i got this Error: libcublasLt.so.11. Here is the full discription of the error.
Could not load library libcublasLt.so.11. Error: libcublasLt.so.11: cannot open shared object file: No such file or directory Invalid handle. Cannot load symbol cublasLtCreate ./keypoints17.sh: line 87: 60511 Aborted (core dumped) CUDA_VISIBLE_DEVICES=${VALID_GPU_IDS[GPU_ID]} python ${RUN_FILE} ${DETECTION_CONFIG_FILE} ${DETECTION_CHECKPOINT} ${CONFIG_FILE} ${CHECKPOINT} --input "${INPUT}/imagepaths$((i+1)).txt" --output-root="${OUTPUT}" --save-predictions --radius ${RADIUS} --kpt-thr ${KPT_THRES} --thickness ${LINE_THICKNESS}
How can I fix any of these issues? And this is my nvidia-smi