8000 Human Video Reenactment · Issue #14 · Yukun-Huang/DreamWaltz-G · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Human Video Reenactment #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
KolarDevGenAi opened this issue Jan 29, 2025 · 6 comments
Open

Human Video Reenactment #14

KolarDevGenAi opened this issue Jan 29, 2025 · 6 comments

Comments

@KolarDevGenAi
Copy link

i want to run Human Video Reenactment on my own input video so i didnt understand that how to create my own motion-x reenact dataset so kindly give guide about it.
Thanks.
@shayanjanjua
Copy link

I myself facing the same issue and not able to perform it. Kindly help me too.

@Yukun-Huang
Copy link
Owner

Hi guys, this part relys on the other repo: https://github.com/yufu-wang/tram to obtain camera and human pose parameters. You may follow their guidance to preprocess your own video and get the hps_track_0.npy and camera.npy the same as in our provided example. Then back to our repo and do the rest by inference_tram.sh.

@KolarDevGenAi
Copy link
Author

@Yukun-Huang but when i run this command !python scripts/estimate_camera.py --video "/content/kk111.mov" it get this error

21859
Exception in callback functools.partial(<bound method IOLoop.discard_future_result of <tornado.platform.asyncio.AsyncIOLoop object at 0xe671e30f7d0>>, <Future finished exception=TypeError("Redis.init_() got an unexpected keyword argument 'host'")>)
Traceback (most recent call last):
File "/usr/local/lib/python3.11/dist-packages/tornado/ioloop.py", line 738, in _run_callback
ret = callback()
^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/tornado/ioloop.py", line 762, in _discard_future_result
future.result()
File "/usr/local/lib/python3.11/dist-packages/tornado/gen.py", line 234, in wrapper
yielded = ctx_run(next, result)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/deva/sources.py", line 687, in process
self.redis = yield aioredis.Redis(host=self.redis_address, password=self.redis_password)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Redis.init() got an unexpected keyword argument 'host'
Traceback (most recent call last):
File "/content/tram/scripts/estimate_camera.py", line 11, in
from lib.pipeline import video2frames, detect_segment_track, visualize_tram
File "/content/tram/scripts/../lib/pipeline/init.py", line 1, in
from .tools import video2frames, detect_segment_track
File "/content/tram/scripts/../lib/pipeline/tools.py", line 12, in
from lib.pipeline.deva_track import get_deva_tracker, track_with_mask, flush_buffer
File "/content/tram/scripts/../lib/pipeline/deva_track.py", line 10, in
from deva.model.network import DEVA
File "/usr/local/lib/python3.11/dist-packages/deva/init.py", line 19, in
from .gpt import async_gpt,sync_gpt
File "/usr/local/lib/python3.11/dist-packages/deva/gpt.py", line 99, in
_gpt = GPT()
^^^^^
File "/usr/local/lib/python3.11/dist-packages/deva/gpt.py", line 18, in init
self.api_key = self.config['api_key']
~~~~~~~~~~~^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/deva/store.py", line 225, in getitem
return self.db.getitem(item)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/deva/utils/sqlitedict.py", line 255, in getitem
raise KeyError(key)
KeyError: 'api_key'
2025-01-29 10:54:49.727872 : exit
bye bye, 21859
2025-01-29 10:54:49.728066 : 'NoneType' object has no attribute 'close'

@shayanjanjua
Copy link

@Yukun-Huang
When i run the following command i face this error how to overcome this.

!python scripts/estimate_camera.py --video "/content/input.mov"

14658
Traceback (most recent call last):
File "/content/tram/scripts/estimate_camera.py", line 11, in
from lib.pipeline import video2frames, detect_segment_track, visualize_tram
File "/content/tram/scripts/../lib/pipeline/init.py", line 1, in
from .tools import video2frames, detect_segment_track
File "/content/tram/scripts/../lib/pipeline/tools.py", line 12, in
from lib.pipeline.deva_track import get_deva_tracker, track_with_mask, flush_buffer
File "/content/tram/scripts/../lib/pipeline/deva_track.py", line 10, in
from deva.model.network import DEVA
File "/usr/local/lib/python3.11/dist-packages/deva/init.py", line 6, in
from .sources import *
File "/usr/local/lib/python3.11/dist-packages/deva/sources.py", line 20, in
import aioredis
File "/usr/local/lib/python3.11/dist-packages/aioredis/init.py", line 1, in
from aioredis.client import Redis, StrictRedis
File "/usr/local/lib/python3.11/dist-packages/aioredis/client.py", line 32, in
from aioredis.connection import (
File "/usr/local/lib/python3.11/dist-packages/aioredis/connection.py", line 33, in
from .exceptions import (
File "/usr/local/lib/python3.11/dist-packages/aioredis/exceptions.py", line 14, in
class TimeoutError(asyncio.TimeoutError, builtins.TimeoutError, RedisError):
TypeError: duplicate base class TimeoutError

@Yukun-Huang
Copy link
Owner

@KolarDevGenAi @shayanjanjua Please follow tram's installation instruction strictly. It seems that the submodule Tracking-Anything-with-DEVA (deva) is not installed correctly.

@KolarDevGenAi
Copy link
Author

@Yukun-Huang but now when i run this command again !python scripts/estimate_camera.py --video "/content/kk111.mov"
its getting this below error

FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
Traceback (most recent call last):
File "/content/tram/scripts/estimate_camera.py", line 12, in
from lib.camera import run_metric_slam, calibrate_intrinsics
File "/content/tram/scripts/../lib/camera/init.py", line 1, in
from .masked_droid_slam import run_metric_slam, calibrate_intrinsics
File "/content/tram/scripts/../lib/camera/masked_droid_slam.py", line 13, in
from droid import Droid
File "/content/tram/thirdparty/DROID-SLAM/droid_slam/droid.py", line 2, in
import lietorch
File "/usr/local/lib/python3.11/dist-packages/lietorch/init.py", line 75, in
_init_backend()
File " 5F3E /usr/local/lib/python3.11/dist-packages/lietorch/init.py", line 55, in _init_backend
torch.ops.load_library(libpath)
File "/usr/local/lib/python3.11/dist-packages/torch/_ops.py", line 1350, in load_library
ctypes.CDLL(path)
File "/usr/lib/python3.11/ctypes/init.py", line 376, in init
self._handle = _dlopen(self._name, mode)
^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: libcudart.so.11.0: cannot open shared object file: No such file or directory

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Yukun-Huang @shayanjanjua @KolarDevGenAi
0