When I run this command, the programme errors out. "python -m sample.generate --model_path ./save/humanml_trans_enc_512/model000200000.pt --num_samples 10 --num_repetitions 3"

[imustwangxin]

(wangxin_mdm) [phdcv@localhost motion-diffusion-model]$ python -m sample.generate --model_path ./save/humanml_trans_enc_512/model000200000.pt --num_samples 10 --num_repetitions 3
Loading dataset...
Reading ././dataset/humanml_opt.txt
Loading dataset t2m ...
100%|████████████████████████████████████████████| 4384/4384 [00:00<00:00, 18551.49it/s]
Creating model and diffusion...
TRANS_ENC init
EMBED TEXT
Loading CLIP...
Loading checkpoints from [./save/humanml_trans_enc_512/model000200000.pt]...

Sampling [repetitions #0]

100%|███████████████████████████████████████████████| 1000/1000 [01:54<00:00, 8.70it/s]
created 10 samples

Sampling [repetitions #1]

100%|███████████████████████████████████████████████| 1000/1000 [01:45<00:00, 9.44it/s]
created 20 samples

Sampling [repetitions #2]

100%|███████████████████████████████████████████████| 1000/1000 [01:48<00:00, 9.18it/s]
created 30 samples
saving results file to [./save/humanml_trans_enc_512/samples_humanml_trans_enc_512_000200000_seed10/results.npy]
saving visualizations to [./save/humanml_trans_enc_512/samples_humanml_trans_enc_512_000200000_seed10]...
["a person remained sitting down." (00) | Rep #00 | -> sample00_rep00.mp4]
MovieWriter stderr:
[libopenh264 @ 0x5623a54cd380] Incorrect library version loaded
Error initializing output stream 0:0 -- Error while opening encoder for output stream #0:0 - maybe incorrect parameters such as bit_rate, rate, width or height

Traceback (most recent call last):
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 230, in saving
yield self
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 1156, in save
writer.grab_frame(**savefig_kwargs)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 384, in grab_frame
dpi=self.dpi, **savefig_kwargs)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/figure.py", line 2180, in savefig
self.canvas.print_figure(fname, **kwargs)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/backend_bases.py", line 2091, in print_figure
**kwargs)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/backends/backend_agg.py", line 446, in print_raw
fh.write(renderer._renderer.buffer_rgba())
BrokenPipeError: [Errno 32] Broken pipe

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/phdcv/wangxin/motion-diffusion-model/sample/generate.py", line 269, in
main()
File "/home/phdcv/wangxin/motion-diffusion-model/sample/generate.py", line 201, in main
plot_3d_motion(animation_save_path, skeleton, motion, dataset=args.dataset, title=caption, fps=fps)
File "/home/phdcv/wangxin/motion-diffusion-model/data_loaders/humanml/utils/plot_script.py", line 128, in plot_3d_motion
ani.save(save_path, fps=fps)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 1156, in save
writer.grab_frame(**savefig_kwargs)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/contextlib.py", line 130, in exit
self.gen.throw(type, value, traceback)
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 232, in saving
self.finish()
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 367, in finish
self.cleanup()
File "/home/phdcv/phdcvssd1/anaconda3/envs/wangxin_mdm/lib/python3.7/site-packages/matplotlib/animation.py", line 411, in cleanup
self._proc.returncode, self._proc.args, out, err)
subprocess.CalledProcessError: Command '['ffmpeg', '-f', 'rawvideo', '-vcodec', 'rawvideo', '-s', '300x300', '-pix_fmt', 'rgba', '-r', '20', '-loglevel', 'error', '-i', 'pipe:', '-vcodec', 'h264', '-pix_fmt', 'yuv420p', '-y', './save/humanml_trans_enc_512/samples_humanml_trans_enc_512_000200000_seed10/sample00_rep00.mp4']' returned non-zero exit status 1.

[GuyTevet]

seems you have an ffmpeg issue

MovieWriter stderr:
[libopenh264 @ 0x5623a54cd380] Incorrect library version loaded
Error initializing output stream 0:0 -- Error while opening encoder for output stream #0:0 - maybe incorrect parameters such as bit_rate, rate, width or height

[shawkontzu]

This is due to incompatible ffmpeg version in your conda env, your conda env has a default ffmpeg, you might installed another ffmpeg outside your conda env (on ubuntu it's at '/user/bin/ffmpeg'). Just check which ffmpeg you are running in your conda env by running
which ffmpeg
I have ffmpeg version 4.3 Copyright (c) 2000-2020 the FFmpeg developers built with gcc 7.3.0 (crosstool-NG 1.23.0.449-a04d0) in my conda env and
ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers built with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1) system wise.

solution:
inside "motion-diffusion-model/data_loaders/humanml/utils/plot_script.py" add
plt.rcParams['animation.ffmpeg_path'] = '/usr/bin/ffmpeg' right after you import matplotlib, forcing matplotlib to use system-wise ffmpeg fixed this issue for me.