An error occurred when running demo/track.py

[jihg88]

Hi,thans for your great work!I just want to test it on the video,but when running with the track.py on line 134 :Error in forward_face_index_map_1: no kernel image is available for execution on the device

        rend_depth = self.neural_renderer(
            pred_verts,
            face_tensor[None].expand(pred_verts.shape[0], -1, -1).int(),
            # textures=texture_atlas_rgb,
            mode="depth",
            K=K,
            R=R,
            t=t,
        )

Logs: [2024-03-20 11:15:01,774][pytorch_lightning.utilities.migration.utils][INFO] - Lightning automatically upgraded your loaded checkpoint from v1.8.1 to v2.2.1. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint ../../../../home/lyx/.cache/4DHumans/logs/train/multiruns/hmr2/0/checkpoints/epoch=35-step=1000000.ckpt [2024-03-20 11:15:01,780][torch.distributed.nn.jit.instantiator][INFO] - Created a temporary directory at /tmp/tmp0fqy2lvo [2024-03-20 11:15:01,780][torch.distributed.nn.jit.instantiator][INFO] - Writing /tmp/tmp0fqy2lvo/_remote_module_non_scriptable.py WARNING: You are using a SMPL model, with only 10 shape coefficients. [2024-03-20 11:15:04,210][phalp.trackers.PHALP][INFO] - Loading Predictor model... [2024-03-20 11:15:04,389][phalp.trackers.PHALP][INFO] - Loading Detection model... [2024-03-20 11:15:08,291][detectron2.checkpoint.detection_checkpoint][INFO] - [DetectionCheckpointer] Loading from https://dl.fbaipublicfiles.com/detectron2/ViTDet/COCO/cascade_mask_rcnn_vitdet_h/f328730692/model_final_f05665.pkl ... [2024-03-20 11:15:10,244][detectron2.checkpoint.detection_checkpoint][INFO] - [DetectionCheckpointer] Loading from https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x/139653917/model_final_2d9806.pkl ... [2024-03-20 11:15:10,357][phalp.trackers.PHALP][INFO] - Setting up Visualizer... [2024-03-20 11:15:10,704][phalp.trackers.PHALP][INFO] - Setting up DeepSort... [2024-03-20 11:15:10,705][phalp.trackers.PHALP][INFO] - Saving tracks at : demo_out/videos/phalp_out/breakdancing/results/breakdancing [2024-03-20 11:15:14,537][pyscenedetect][INFO] - Downscale factor set to 7, effective resolution: 274 x 154 [2024-03-20 11:15:14,538][pyscenedetect][INFO] - Detecting scenes... [2024-03-20 11:15:14,841][phalp.trackers.PHALP][INFO] - Detected shot change at frame: Tracking : breakdancing 🚶 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0% eta : -:--:-- time elapsed : 0:00:02Error in forward_face_index_map_1: no kernel image is available for execution on the device

my cuda version=11.7,so i installed pytorch with : conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia,i don't know how to fix the problem.

[statho]

It seems that the neural renderer package is not properly installed.

You can use the PHALP_Prime_HMR2 tracker by removing the comment in this line instead of the default one.

[jihg88]

Thank you for your reply,it works now！