meaten / FlowChain-ICCV2023

Trajectory prediction method using a stacked normalizing flow for fast and accurate density estimation.
48 stars 2 forks source link

Can't reproduce the similiar results #4

Closed mulplue closed 9 months ago

mulplue commented 10 months ago

Hi, I've tried to reproduce results on ETH/UCY dataset,but get some different results:

ETH: 0.55/0.99 -> 0.541/0.980
HOTEL: 0.20/0.35 -> 0.266/0.508
UNIV: 0.29/0.54 -> 0.232/0.431
ZARA1: 0.22/0.40 -> 0.267/0.516
ZARA2: 0.20/0.34 -> 0.276/0.526

I think that may due to the environment, can you offer your python version and the specific version of packages?

meaten commented 10 months ago

Hi @mulplue,

Thanks for trying out my code. My Python version is 3.8.10. I also specified the versions of the Python packages I used below. There should be some unused packages but I showed them as is for sure.

I would much appreciate it if you tell me the details about your settings. such as model weights (retrained or not), and hyperparameters.

click here

```js absl-py==1.0.0 aiofiles==23.1.0 aiohttp==3.8.4 aiosignal==1.3.1 albumentations==1.3.0 alembic==1.9.3 altair==4.2.2 antlr4-python3-runtime==4.9.3 anyio==3.6.2 astunparse==1.6.3 async-timeout==4.0.2 attrdict==2.0.1 attrs==22.2.0 cachetools==5.0.0 certifi==2021.10.8 charset-normalizer==2.0.12 click==8.0.4 cmaes==0.9.1 colorlog==6.7.0 comet-ml==3.32.2 configobj==5.0.8 cycler==0.11.0 dill==0.3.6 docker-pycreds==0.4.0 docstring-parser==0.15 dulwich==0.21.3 easydict==1.10 einops==0.6.0 entrypoints==0.4 everett==3.1.0 fastapi==0.92.0 ffmpy==0.3.0 flatbuffers==2.0 fonttools==4.30.0 frozenlist==1.3.3 fsspec==2023.1.0 gast==0.5.3 gitdb==4.0.9 GitPython==3.1.27 google-auth==2.6.0 google-auth-oauthlib==0.4.6 google-pasta==0.2.0 gradio==3.19.1 greenlet==2.0.2 grpcio==1.44.0 h11==0.14.0 h5py==3.6.0 httpcore==0.16.3 httpx==0.23.3 idna==3.3 imageio==2.16.1 imgaug==0.4.0 importlib-metadata==4.11.2 importlib-resources==5.10.2 Jinja2==3.1.2 joblib==1.1.0 jsonargparse==4.20.0 jsonschema==4.17.3 keopscore==2.1.1 keras==2.8.0 Keras-Preprocessing==1.1.2 kiwisolver==1.3.2 kornia==0.6.10 libclang==13.0.0 linkify-it-py==2.0.0 lpips==0.1.4 Mako==1.2.4 Markdown==3.3.6 markdown-it-py==2.2.0 MarkupSafe==2.1.2 matplotlib==3.5.1 mdit-py-plugins==0.3.3 mdurl==0.1.2 multidict==6.0.4 ncls==0.0.66 networkx==2.7.1 numpy==1.22.3 nvidia-cublas-cu11==11.10.3.66 nvidia-cuda-nvrtc-cu11==11.7.99 nvidia-cuda-runtime-cu11==11.7.99 nvidia-cudnn-cu11==8.5.0.96 oauthlib==3.2.0 omegaconf==2.3.0 opencv-python==4.5.5.64 opencv-python-headless==4.7.0.72 opt-einsum==3.3.0 optuna==3.1.0 orjson==3.8.6 packaging==21.3 pandas==1.5.3 pathtools==0.1.2 Pillow==9.0.1 pkgutil_resolve_name==1.3.10 POT==0.8.2 progressbar2==4.0.0 promise==2.3 protobuf==3.19.4 psutil==5.9.0 pyasn1==0.4.8 pyasn1-modules==0.2.8 pybind11==2.10.3 pycryptodome==3.17 pydantic==1.10.5 pyDeprecate==0.3.2 pydub==0.25.1 pyparsing==3.0.7 pyrsistent==0.19.3 python-box==6.1.0 python-dateutil==2.8.2 python-multipart==0.0.5 python-utils==3.1.0 pytorch-lightning==1.6.5 pytz==2022.7.1 PyWavelets==1.2.0 PyYAML==6.0 qudida==0.0.4 requests==2.27.1 requests-oauthlib==1.3.1 requests-toolbelt==0.10.1 rfc3986==1.5.0 rsa==4.8 scikit-image==0.19.2 scikit-learn==1.0.2 scipy==1.8.0 seaborn==0.12.2 semantic-version==2.10.0 sentry-sdk==1.5.7 setproctitle==1.2.2 shapely==2.0.1 shortuuid==1.0.8 simplejson==3.18.3 six==1.16.0 smmap==5.0.0 sniffio==1.3.0 SQLAlchemy==2.0.3 starlette==0.25.0 tensorboard==2.8.0 tensorboard-data-server==0.6.1 tensorboard-plugin-wit==1.8.1 tensorboardX==2.5.1 tensorflow==2.8.0 tensorflow-io-gcs-filesystem==0.24.0 termcolor==1.1.0 tf-estimator-nightly==2.8.0.dev2021122109 threadpoolctl==3.1.0 tifffile==2022.2.9 timm==0.5.4 toolz==0.12.0 torch==1.13.1 torchaudio==0.13.1 torchfile==0.1.0 torchmetrics==0.9.3 torchvision==0.14.1 tqdm==4.63.0 typeshed-client==2.2.0 typing_extensions==4.5.0 uc-micro-py==1.0.1 urllib3==1.26.8 uvicorn==0.20.0 wandb==0.12.17 websocket-client==1.3.3 websockets==10.4 Werkzeug==2.0.3 wrapt==1.14.0 wurlitzer==3.0.3 yacs==0.1.8 yarl==1.8.2 yaspin==2.1.0 zipp==3.7.0 ```

mulplue commented 9 months ago

I’sorry for misusing val set as test set, so the results above is on the val set. I tried your environment and test on test set, get the similiar results:

ETH: 0.55/0.99 -> 0.536/0.941
HOTEL: 0.20/0.35 -> 0.201/0.370
UNIV: 0.29/0.54 -> 0.288/0.548
ZARA1: 0.22/0.40 -> 0.226/0.421
ZARA2: 0.20/0.34 -> 0.207/0.395

Apologize again and thank you for your detailed reply.