You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
PHALP with dancing2.mp4 work
PHALP with dancing3.mp4 throws an error as following
(phalp2) :~/3dhuman/PHALP$ python scripts/demo.py video.source=assets/videos/dancing3.mp4 video.output_dir='outputs7'
[03/17 01:12:51] INFO No OpenGL_accelerate module loaded: No module named acceleratesupport.py:17
'OpenGL_accelerate'
[2024-03-17 01:12:53,960][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 ../../../../.cache/4DHumans/logs/train/multiruns/hmr2/0/checkpoints/epoch=35-step=1000000.ckpt`
[2024-03-17 01:12:53,964][torch.distributed.nn.jit.instantiator][INFO] - Created a temporary directory at /tmp/tmpqwevip08
[2024-03-17 01:12:53,964][torch.distributed.nn.jit.instantiator][INFO] - Writing /tmp/tmpqwevip08/_remote_module_non_scriptable.py
WARNING: You are using a SMPL model, with only 10 shape coefficients.
[2024-03-17 01:12:56,972][phalp.trackers.PHALP][INFO] - Loading Predictor model...
[2024-03-17 01:12:57,111][phalp.trackers.PHALP][INFO] - Loading Detection model...
[2024-03-17 01:13:01,881][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 ...
[2024-03-17 01:13:03,885][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 ...
[2024-03-17 01:13:03,984][phalp.trackers.PHALP][INFO] - Setting up Visualizer...
[2024-03-17 01:13:04,293][phalp.utils.io][INFO] - Number of frames: 115
[2024-03-17 01:13:05,283][phalp.trackers.PHALP][INFO] - Setting up DeepSort...
[2024-03-17 01:13:05,283][phalp.trackers.PHALP][INFO] - Saving tracks at : outputs7/results/dancing3
Tracking : dancing3 🚶 ━╸━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4% eta : 0:01:11 time elapsed : 0:00:04
GLError(
err = 12289,
baseOperation = eglMakeCurrent,
cArguments = (
<OpenGL._opaque.EGLDisplay_pointer object at 0x7fe0559b1940>,
<OpenGL._opaque.EGLSurface_pointer object at 0x7fe05c8f4f40>,
<OpenGL._opaque.EGLSurface_pointer object at 0x7fe05c8f4f40>,
<OpenGL._opaque.EGLContext_pointer object at 0x7fe0559b25c0>,
),
result = 0
)
Traceback (most recent call last):
File "/home/zhangyupeng/w/3drecon/3dhuman/PHALP/phalp/trackers/PHALP.py", line 252, in track
rendered_, f_size = self.visualizer.render_video(final_visuals_dic[frame_key])
File "/home/zhangyupeng/w/3drecon/3dhuman/PHALP/phalp/visualize/visualizer.py", line 359, in render_video
rendered_image_final, valid_mask = self.render_single_frame(
File "/home/zhangyupeng/w/3drecon/3dhuman/PHALP/phalp/visualize/visualizer.py", line 77, in render_single_frame
rgb_from_pred, validmask = self.render.visualize_all(pred_vertices.numpy(), pred_cam_t_bs.cpu().numpy(), color, image, use_image=use_image)
File "/home/zhangyupeng/w/3drecon/3dhuman/PHALP/phalp/visualize/py_renderer.py", line 115, in visualize_all
color = self.__call__(verts, focal_length=fl, baseColorFactors=baseColorFactors)
File "/home/zhangyupeng/w/3drecon/3dhuman/PHALP/phalp/visualize/py_renderer.py", line 152, in __call__
color, rend_depth = self.renderer.render(scene, flags=pyrender.RenderFlags.RGBA)
File "/home/zhangyupeng/miniconda3/envs/phalp2/lib/python3.10/site-packages/pyrender/offscreen.py", line 86, in render
self._platform.make_current()
File "/home/zhangyupeng/miniconda3/envs/phalp2/lib/python3.10/site-packages/pyrender/platforms/egl.py", line 196, in make_current
assert eglMakeCurrent(
File "/home/zhangyupeng/miniconda3/envs/phalp2/lib/python3.10/site-packages/OpenGL/error.py", line 228, in glCheckError
raise GLError(
OpenGL.error.GLError: GLError(
err = 12289,
baseOperation = eglMakeCurrent,
cArguments = (
<OpenGL._opaque.EGLDisplay_pointer object at 0x7fe0559b1940>,
<OpenGL._opaque.EGLSurface_pointer object at 0x7fe05c8f4f40>,
<OpenGL._opaque.EGLSurface_pointer object at 0x7fe05c8f4f40>,
<OpenGL._opaque.EGLContext_pointer object at 0x7fe0559b25c0>,
),
result = 0
)
The text was updated successfully, but these errors were encountered:
Same error here. I resolved it by reencoding all my videos using the latest version of FFMPEG. Installing FFMPEG from apt results in an older ffmpeg installation. I compiled it from source. Afterwards, I reencoded using:
I cut two shot video (dancing2.mp4, dancing3.mp4) from a same long video.
dancing2.mp4: https://github.com/brjathu/PHALP/assets/1321005/6867121d-3f85-46f5-b351-68aa871a7a1f
dancing3.mp4: https://github.com/brjathu/PHALP/assets/1321005/8a2cef07-f936-48d6-9df2-3cb84fdb55aa
PHALP with dancing2.mp4 work
PHALP with dancing3.mp4 throws an error as following
The text was updated successfully, but these errors were encountered: