RVT与RVT2项目复现环境配置
·
目录
2. 驱动版本，nvcc，安装python包版本，直接使用pip install直接安装pytorch3d
1. 参考资料
参考资料如下:
RVT: Robotic View Transformer for 3D Object Manipulation
Ankit Goyal, Jie Xu, Yijie Guo, Valts Blukis, Yu-Wei Chao, Dieter Fox
NVIDIA
RVT-2: Learning Precise Manipulation from Few Demonstrations
Ankit Goyal, Valts Blukis, Jie Xu, Yijie Guo, Yu-Wei Chao, Dieter Fox
NVIDIA
仓库链接：
模型文件下载链接，原项目下载慢，可以使用如下资源，下载更方便：
https://huggingface.co/ankgoyal/rvt/tree/main/rvt2
数据集下载链接，原项目下载慢，可以使用如下资源，下载更方便：
https://huggingface.co/datasets/hqfang/rlbench-18-tasks/tree/main
执行pip freeze > requirements.txt指令后输出为：
absl-py==2.3.1
aiohappyeyeballs @ file:///croot/aiohappyeyeballs_1725434011349/work
aiohttp @ file:///croot/aiohttp_1725527756643/work
aiosignal @ file:///tmp/build/80754af9/aiosignal_1637843061372/work
antlr4-python3-runtime==4.9.3
astunparse==1.6.3
async-timeout @ file:///croot/async-timeout_1703096998144/work
attrs @ file:///croot/attrs_1729089401488/work
bitsandbytes==0.38.1
Bottleneck @ file:///croot/bottleneck_1707864210935/work
Brotli @ file:///croot/brotli-split_1714483155106/work
cachetools==5.5.2
certifi @ file:///croot/certifi_1725551672989/work/certifi
cffi==1.17.1
charset-normalizer @ file:///croot/charset-normalizer_1721748349566/work
clip==1.0
contourpy==1.1.1
cycler==0.12.1
datasets @ file:///croot/datasets_1716911606380/work
decorator==4.4.2
dill @ file:///croot/dill_1715094664823/work
einops==0.8.1
filelock==3.16.1
flatbuffers==25.12.19
fonttools==4.57.0
freetype-py==2.5.1
frozenlist @ file:///croot/frozenlist_1698702560391/work
fsspec==2025.3.0
ftfy==6.2.3
fvcore==0.1.5.post20210915
gast==0.4.0
google-auth==2.45.0
google-auth-oauthlib==1.0.0
google-pasta==0.2.0
grpcio==1.70.0
h5py==3.11.0
hf-xet==1.2.0
huggingface-hub==0.36.0
hydra-core==1.3.2
idna @ file:///croot/idna_1714398848350/work
imageio==2.35.1
imageio-ffmpeg==0.5.1
importlib_metadata==8.5.0
importlib_resources==6.4.5
iopath==0.1.10
keras==2.13.1
kiwisolver==1.4.7
lazy_loader==0.4
libclang==18.1.1
Markdown==3.7
MarkupSafe==2.1.5
matplotlib==3.7.5
mkl-fft @ file:///croot/mkl_fft_1695058164594/work
mkl-random @ file:///croot/mkl_random_1695059800811/work
mkl-service==2.4.0
moviepy==2.0.0.dev2
multidict @ file:///croot/multidict_1701096859099/work
multiprocess @ file:///croot/multiprocess_1692294385131/work
natsort==8.4.0
networkx==3.1
numexpr @ file:///croot/numexpr_1683221822650/work
numpy==1.24.4
omegaconf==2.3.0
opencv-python==4.12.0.88
opt_einsum==3.4.0
packaging==25.0
pandas==2.0.3
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=peract_colab&subdirectory=rvt/libs/peract_colab
pillow==10.4.0
ply==3.11
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=point_renderer&subdirectory=rvt/libs/point-renderer
portalocker @ file:///home/conda/feedstock_root/build_artifacts/portalocker_1720928545232/work
proglog==0.1.12
protobuf==4.25.8
pyarrow @ file:///croot/pyarrow_1721664224170/work/python
pyasn1==0.6.1
pyasn1_modules==0.4.2
pycparser==2.23
pyglet==2.1.11
PyOpenGL==3.1.0
pyparsing==3.1.4
PyQt5-sip==12.11.0
pyquaternion==0.9.9
pyrender==0.1.45
-e git+https://github.com/stepjam/PyRep.git@231a1ac6b0a179cff53c1d403d379260b9f05f2f#egg=PyRep&subdirectory=../../../rvt/libs/PyRep
PySocks @ file:///tmp/build/80754af9/pysocks_1605305779399/work
python-dateutil==2.9.0.post0
-e git+https://github.com/facebookresearch/pytorch3d.git@f5f6b78e70e0a1b70f3be9a09b5b001e9b3a7a03#egg=pytorch3d
pytz==2025.2
PyWavelets==1.4.1
PyYAML @ file:///croot/pyyaml_1728657952215/work
regex==2024.11.6
requests @ file:///croot/requests_1721410876868/work
requests-oauthlib==2.0.0
-e git+https://github.com/buttomnutstoast/RLBench.git@587a6a0e6dc8cd36612a208724eb275fe8cb4470#egg=rlbench&subdirectory=../../../rvt/libs/RLBench
rsa==4.9.1
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=rvt
safetensors==0.5.3
scikit-image==0.21.0
scipy==1.10.1
sip @ file:///tmp/abs_44cd77b_pu/croots/recipe/sip_1659012365470/work
six @ file:///tmp/build/80754af9/six_1644875935023/work
tabulate @ file:///home/conda/feedstock_root/build_artifacts/tabulate_1665138452165/work
tensorboard==2.13.0
tensorboard-data-server==0.7.2
tensorflow==2.13.1
tensorflow-estimator==2.13.0
tensorflow-io-gcs-filesystem==0.34.0
termcolor==2.4.0
tifffile==2023.7.10
timeout-decorator==0.5.0
tokenizers==0.20.3
toml @ file:///tmp/build/80754af9/toml_1616166611790/work
torch==1.12.1+cu113
torchaudio==0.12.1+cu113
torchvision==0.13.1+cu113
tqdm==4.67.1
transformers==4.46.3
transforms3d==0.4.2
trimesh==4.10.1
typing_extensions==4.0.0
tzdata==2025.3
urllib3 @ file:///croot/urllib3_1727769808118/work
wcwidth==0.2.14
Werkzeug==3.0.6
wrapt==2.0.1
xxhash @ file:///croot/python-xxhash_1667919521615/work
yacs @ file:///tmp/build/80754af9/yacs_1634047592950/work
yarl @ file:///croot/yarl_1725976495189/work
-e git+https://github.com/NVlabs/YARR.git@f4aaeea183321e6b526166249119071e64252ad2#egg=yarr&subdirectory=../../../rvt/libs/YARR
zipp==3.20.22. 驱动版本，nvcc，安装python包版本，直接使用pip install直接安装pytorch3d
一键收集环境信息的 Shell 指令：
Driver Version: 570.133.07
Ubuntu 20.04.6 LTS (Focal Fossa)
Python 3.8.20
Cuda compilation tools, release 11.3, V11.3.109, Build cuda_11.3.r11.3/compiler.29920130_0
# 创建报告文件
REPORT_FILE="rvt_env_report_$(date +%Y%m%d_%H%M).txt"
# 开始写入信息
{
echo "========================"
echo "RVT/RVT2 环境配置报告"
echo "生成时间: $(date)"
echo "========================"
echo
# 1. 操作系统信息
echo "[1] 操作系统信息"
uname -a
if [ -f /etc/os-release ]; then
cat /etc/os-release
fi
echo
# 2. GPU 与 NVIDIA 驱动
echo "[2] NVIDIA 驱动与 GPU 信息"
if command -v nvidia-smi &> /dev/null; then
nvidia-smi
else
echo "nvidia-smi 未找到（可能无 GPU 或驱动未安装）"
fi
echo
# 3. CUDA 版本
echo "[3] CUDA 版本"
if command -v nvcc &> /dev/null; then
nvcc --version
elif [ -f /usr/local/cuda/version.txt ]; then
cat /usr/local/cuda/version.txt
elif [ -f /usr/local/cuda/version.json ]; then
cat /usr/local/cuda/version.json
else
echo "CUDA 未检测到"
fi
echo
# 4. cuDNN 版本（常见路径）
echo "[4] cuDNN 版本"
CUDNN_H="/usr/local/cuda/include/cudnn_version.h"
if [ -f "$CUDNN_H" ]; then
grep "#define CUDNN_MAJOR\|CUDNN_MINOR\|CUDNN_PATCHLEVEL" "$CUDNN_H"
else
echo "cuDNN 头文件未找到（可能未安装或路径不同）"
fi
echo
# 5. Python 环境
echo "[5] Python 信息"
python3 --version 2>&1
which python3
echo
# 6. pip 包列表（包括 PyTorch 等）
echo "[6] Python 包列表 (pip freeze)"
pip3 freeze
echo
# 7. Conda 环境（如果使用）
if command -v conda &> /dev/null; then
echo "[7] Conda 环境信息"
conda info
echo
echo "[7b] Conda 包列表"
conda list
echo
fi
# 8. GCC / 编译器版本
echo "[8] GCC 版本"
gcc --version 2>&1 || echo "GCC 未安装"
echo
# 9. 当前项目 Git 信息（建议在 RVT 项目根目录运行）
if [ -d .git ]; then
echo "[9] 当前 Git 仓库信息"
git remote -v
git rev-parse HEAD
git branch --show-current
echo
fi
# 10. Docker 信息（可选）
echo "[10] Docker 信息（若使用容器）"
if command -v docker &> /dev/null; then
docker --version
# 可选：列出最近使用的镜像
# docker images --format "table {{.Repository}}\t{{.Tag}}\t{{.CreatedAt}}" | head -n 6
else
echo "Docker 未安装或未使用"
fi
} > "$REPORT_FILE"
echo "✅ 环境报告已保存至: $REPORT_FILE"打印信息如下：
========================
RVT/RVT2 环境配置报告
生成时间: 2026年 01月 09日 星期五 11:13:16 CST
========================
[1] 操作系统信息
Linux gdp 5.15.0-139-generic #149~20.04.1-Ubuntu SMP Wed Apr 16 08:29:56 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
NAME="Ubuntu"
VERSION="20.04.6 LTS (Focal Fossa)"
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME="Ubuntu 20.04.6 LTS"
VERSION_ID="20.04"
HOME_URL="https://www.ubuntu.com/"
SUPPORT_URL="https://help.ubuntu.com/"
BUG_REPORT_URL="https://bugs.launchpad.net/ubuntu/"
PRIVACY_POLICY_URL="https://www.ubuntu.com/legal/terms-and-policies/privacy-policy"
VERSION_CODENAME=focal
UBUNTU_CODENAME=focal
[2] NVIDIA 驱动与 GPU 信息
Fri Jan 9 11:13:16 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.133.07 Driver Version: 570.133.07 CUDA Version: 12.8 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA RTX 6000 Ada Gene... Off | 00000000:01:00.0 On | Off |
| 30% 43C P8 31W / 300W | 1045MiB / 49140MiB | 4% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
[3] CUDA 版本
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Mon_May__3_19:15:13_PDT_2021
Cuda compilation tools, release 11.3, V11.3.109
Build cuda_11.3.r11.3/compiler.29920130_0
[4] cuDNN 版本
cuDNN 头文件未找到（可能未安装或路径不同）
[5] Python 信息
Python 3.8.20
/home/gdp/miniconda3/envs/rvt/bin/python3
[6] Python 包列表 (pip freeze)
absl-py==2.3.1
aiohappyeyeballs @ file:///croot/aiohappyeyeballs_1725434011349/work
aiohttp @ file:///croot/aiohttp_1725527756643/work
aiosignal @ file:///tmp/build/80754af9/aiosignal_1637843061372/work
antlr4-python3-runtime==4.9.3
astunparse==1.6.3
async-timeout @ file:///croot/async-timeout_1703096998144/work
attrs @ file:///croot/attrs_1729089401488/work
bitsandbytes==0.38.1
Bottleneck @ file:///croot/bottleneck_1707864210935/work
Brotli @ file:///croot/brotli-split_1714483155106/work
cachetools==5.5.2
certifi @ file:///croot/certifi_1725551672989/work/certifi
cffi==1.17.1
charset-normalizer @ file:///croot/charset-normalizer_1721748349566/work
clip==1.0
contourpy==1.1.1
cycler==0.12.1
datasets @ file:///croot/datasets_1716911606380/work
decorator==4.4.2
dill @ file:///croot/dill_1715094664823/work
einops==0.8.1
filelock==3.16.1
flatbuffers==25.12.19
fonttools==4.57.0
freetype-py==2.5.1
frozenlist @ file:///croot/frozenlist_1698702560391/work
fsspec==2025.3.0
ftfy==6.2.3
fvcore==0.1.5.post20210915
gast==0.4.0
google-auth==2.45.0
google-auth-oauthlib==1.0.0
google-pasta==0.2.0
grpcio==1.70.0
h5py==3.11.0
hf-xet==1.2.0
huggingface-hub==0.36.0
hydra-core==1.3.2
idna @ file:///croot/idna_1714398848350/work
imageio==2.35.1
imageio-ffmpeg==0.5.1
importlib_metadata==8.5.0
importlib_resources==6.4.5
iopath==0.1.10
keras==2.13.1
kiwisolver==1.4.7
lazy_loader==0.4
libclang==18.1.1
Markdown==3.7
MarkupSafe==2.1.5
matplotlib==3.7.5
mkl-fft @ file:///croot/mkl_fft_1695058164594/work
mkl-random @ file:///croot/mkl_random_1695059800811/work
mkl-service==2.4.0
moviepy==2.0.0.dev2
multidict @ file:///croot/multidict_1701096859099/work
multiprocess @ file:///croot/multiprocess_1692294385131/work
natsort==8.4.0
networkx==3.1
numexpr @ file:///croot/numexpr_1683221822650/work
numpy==1.24.4
omegaconf==2.3.0
opencv-python==4.12.0.88
opt_einsum==3.4.0
packaging==25.0
pandas==2.0.3
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=peract_colab&subdirectory=rvt/libs/peract_colab
pillow==10.4.0
ply==3.11
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=point_renderer&subdirectory=rvt/libs/point-renderer
portalocker @ file:///home/conda/feedstock_root/build_artifacts/portalocker_1720928545232/work
proglog==0.1.12
protobuf==4.25.8
pyarrow @ file:///croot/pyarrow_1721664224170/work/python
pyasn1==0.6.1
pyasn1_modules==0.4.2
pycparser==2.23
pyglet==2.1.11
PyOpenGL==3.1.0
pyparsing==3.1.4
PyQt5-sip==12.11.0
pyquaternion==0.9.9
pyrender==0.1.45
-e git+https://github.com/stepjam/PyRep.git@231a1ac6b0a179cff53c1d403d379260b9f05f2f#egg=PyRep&subdirectory=../../../rvt/libs/PyRep
PySocks @ file:///tmp/build/80754af9/pysocks_1605305779399/work
python-dateutil==2.9.0.post0
-e git+https://github.com/facebookresearch/pytorch3d.git@f5f6b78e70e0a1b70f3be9a09b5b001e9b3a7a03#egg=pytorch3d
pytz==2025.2
PyWavelets==1.4.1
PyYAML @ file:///croot/pyyaml_1728657952215/work
regex==2024.11.6
requests @ file:///croot/requests_1721410876868/work
requests-oauthlib==2.0.0
-e git+https://github.com/buttomnutstoast/RLBench.git@587a6a0e6dc8cd36612a208724eb275fe8cb4470#egg=rlbench&subdirectory=../../../rvt/libs/RLBench
rsa==4.9.1
-e git+https://gitee.com/hanszhu918/rvt.git@17e4da2077e8e3ab8e4195bc1936e87b1416de52#egg=rvt
safetensors==0.5.3
scikit-image==0.21.0
scipy==1.10.1
sip @ file:///tmp/abs_44cd77b_pu/croots/recipe/sip_1659012365470/work
six @ file:///tmp/build/80754af9/six_1644875935023/work
tabulate @ file:///home/conda/feedstock_root/build_artifacts/tabulate_1665138452165/work
tensorboard==2.13.0
tensorboard-data-server==0.7.2
tensorflow==2.13.1
tensorflow-estimator==2.13.0
tensorflow-io-gcs-filesystem==0.34.0
termcolor==2.4.0
tifffile==2023.7.10
timeout-decorator==0.5.0
tokenizers==0.20.3
toml @ file:///tmp/build/80754af9/toml_1616166611790/work
torch==1.12.1+cu113
torchaudio==0.12.1+cu113
torchvision==0.13.1+cu113
tqdm==4.67.1
transformers==4.46.3
transforms3d==0.4.2
trimesh==4.10.1
typing_extensions==4.0.0
tzdata==2025.3
urllib3 @ file:///croot/urllib3_1727769808118/work
wcwidth==0.2.14
Werkzeug==3.0.6
wrapt==2.0.1
xxhash @ file:///croot/python-xxhash_1667919521615/work
yacs @ file:///tmp/build/80754af9/yacs_1634047592950/work
yarl @ file:///croot/yarl_1725976495189/work
-e git+https://github.com/NVlabs/YARR.git@f4aaeea183321e6b526166249119071e64252ad2#egg=yarr&subdirectory=../../../rvt/libs/YARR
zipp==3.20.2
[7] Conda 环境信息
active environment : rvt
active env location : /home/gdp/miniconda3/envs/rvt
shell level : 2
user config file : /home/gdp/.condarc
populated config files : /home/gdp/miniconda3/.condarc
/home/gdp/miniconda3/condarc.d/anaconda-auth.yml
/home/gdp/.condarc
conda version : 25.11.1
conda-build version : not installed
python version : 3.13.11.final.0
solver : libmamba (default)
virtual packages : __archspec=1=skylake
__conda=25.11.1=0
__cuda=12.8=0
__glibc=2.31=0
__linux=5.15.0=0
__unix=0=0
base environment : /home/gdp/miniconda3 (writable)
conda av data dir : /home/gdp/miniconda3/etc/conda
conda av metadata url : None
channel URLs : https://conda.anaconda.org/conda-forge/linux-64
https://conda.anaconda.org/conda-forge/noarch
https://repo.anaconda.com/pkgs/main/linux-64
https://repo.anaconda.com/pkgs/main/noarch
https://repo.anaconda.com/pkgs/r/linux-64
https://repo.anaconda.com/pkgs/r/noarch
package cache : /home/gdp/miniconda3/pkgs
/home/gdp/.conda/pkgs
envs directories : /home/gdp/miniconda3/envs
/home/gdp/.conda/envs
platform : linux-64
user-agent : conda/25.11.1 requests/2.32.5 CPython/3.13.11 Linux/5.15.0-139-generic ubuntu/20.04.6 glibc/2.31 solver/libmamba conda-libmamba-solver/25.11.0 libmambapy/2.3.2 aau/0.7.5 c/. s/. e/.
UID:GID : 1000:1000
netrc file : None
offline mode : False
[7b] Conda 包列表
# packages in environment at /home/gdp/miniconda3/envs/rvt:
#
# Name Version Build Channel
_libgcc_mutex 0.1 main
_openmp_mutex 5.1 1_gnu
aiohappyeyeballs 2.4.0 py38h06a4308_0
aiohttp 3.10.5 py38h5eee18b_0
aiosignal 1.2.0 pyhd3eb1b0_0
aom 3.12.1 h7934f7d_0
arrow-cpp 16.1.0 hc1eb8f0_0
async-timeout 4.0.3 py38h06a4308_0
attrs 24.2.0 py38h06a4308_0
aws-c-auth 0.6.19 h5eee18b_0
aws-c-cal 0.5.20 hdbd6064_0
aws-c-common 0.8.5 h5eee18b_0
aws-c-compression 0.2.16 h5eee18b_0
aws-c-event-stream 0.2.15 h6a678d5_0
aws-c-http 0.6.25 h5eee18b_0
aws-c-io 0.13.10 h5eee18b_0
aws-c-mqtt 0.7.13 h5eee18b_0
aws-c-s3 0.1.51 hdbd6064_0
aws-c-sdkutils 0.1.6 h5eee18b_0
aws-checksums 0.1.13 h5eee18b_0
aws-crt-cpp 0.18.16 h6a678d5_0
aws-sdk-cpp 1.10.55 h721c034_0
blas 1.0 mkl
bottleneck 1.3.7 py38ha9d4c09_0
brotli-python 1.0.9 py38h6a678d5_8
bzip2 1.0.8 h5eee18b_6
c-ares 1.34.5 hef5626c_0
ca-certificates 2025.12.2 h06a4308_0
cairo 1.18.4 h44eff21_0
certifi 2024.8.30 py38h06a4308_0
charset-normalizer 3.3.2 pyhd3eb1b0_0
cudatoolkit 11.3.1 h2bc3f7f_2
cyrus-sasl 2.1.28 h1110e0f_3 anaconda
datasets 2.19.1 py38h06a4308_0
dav1d 1.2.1 h5eee18b_0
dbus 1.16.2 h5bd4931_0 anaconda
dill 0.3.8 py38h06a4308_0
expat 2.7.3 h7354ed3_4
ffmpeg 4.4.0 hca11adc_0 conda-forge
filelock 3.13.1 py38h06a4308_0
fontconfig 2.14.1 h4c34cd2_2
freetype 2.13.3 h4a9f257_0
frozenlist 1.4.0 py38h5eee18b_0
fsspec 2024.3.1 py38h06a4308_0
fvcore 0.1.5.post20210915 py38 fvcore
gettext 0.21.0 h39681ba_1 anaconda
gflags 2.2.2 h6a678d5_1
giflib 5.2.2 h5eee18b_0
glib 2.84.4 h5bdd934_0 anaconda
glib-tools 2.84.4 h8875d55_0 anaconda
glog 0.5.0 h6a678d5_1
gmp 6.3.0 h6a678d5_0 anaconda
gnutls 3.6.13 h85f3911_1 conda-forge
graphite2 1.3.14 h295c915_1
gst-plugins-base 1.14.1 h6a678d5_1
gstreamer 1.14.1 h5eee18b_1 anaconda
harfbuzz 4.3.0 hf52aaf7_1 anaconda
huggingface_hub 0.24.6 py38h06a4308_0
icu 58.2 he6710b0_3 anaconda
idna 3.7 py38h06a4308_0
intel-openmp 2023.0.0 h9e868ea_25371
iopath 0.1.10 pypi_0 pypi
jansson 2.14 h5eee18b_1
jpeg 9f h5ce9db8_0
krb5 1.20.1 h143b758_1 anaconda
lame 3.100 h7b6447c_0
lazy-loader 0.4 pypi_0 pypi
lcms2 2.16 hb9589c4_0
ld_impl_linux-64 2.44 h153f514_2
leptonica 1.82.0 h42c8aad_2
lerc 4.0.0 h6a678d5_0
libabseil 20240116.2 cxx17_h6a678d5_0
libarchive 3.6.2 h3d51595_0 conda-forge
libbrotlicommon 1.0.9 h5eee18b_9
libbrotlidec 1.0.9 h5eee18b_9
libbrotlienc 1.0.9 h5eee18b_9
libclang 14.0.6 default_h7634d5b_1 conda-forge
libclang13 14.0.6 default_h9986a30_1 conda-forge
libcups 2.4.15 hbe4054b_0 anaconda
libcurl 8.16.0 heebcbe5_0 anaconda
libdeflate 1.22 h5eee18b_0
libedit 3.1.20230828 h5eee18b_0 anaconda
libev 4.33 h7f8727e_1
libevent 2.1.12 hdbd6064_1
libexpat 2.7.3 h7354ed3_4
libffi 3.4.4 h6a678d5_1
libgcc 15.2.0 h69a1729_7
libgcc-ng 15.2.0 h166f726_7
libglib 2.84.4 h77a78f3_0
libgomp 15.2.0 h4751f2c_7
libgrpc 1.62.2 h2d74bed_0
libiconv 1.16 h5eee18b_3
libidn2 2.3.8 hf80d704_0
libkrb5 1.21.3 h520c7b4_4 anaconda
libllvm14 14.0.6 hcd5def8_4 conda-forge
libnghttp2 1.67.0 had1ee68_0 conda-forge
libogg 1.3.5 h27cfd23_1
libopus 1.3.1 h5eee18b_1
libpng 1.6.50 h2ed474d_0
libpq 12.20 hdbd6064_0 anaconda
libprotobuf 4.25.3 he621ea3_0
libssh2 1.11.1 h251f7ec_0
libstdcxx 15.2.0 h39759b7_7
libstdcxx-ng 15.2.0 hc03a8fd_7
libtheora 1.2.0 h32ad74f_1
libthrift 0.15.0 hd8eb582_4
libtiff 4.5.1 hffd6297_1
libunistring 1.3 hb25bd0a_0
libuuid 1.41.5 h5eee18b_0
libvorbis 1.3.7 h7b6447c_0
libvpx 1.15.2 h4cb591d_0
libwebp 1.3.2 h11a3e52_0
libwebp-base 1.3.2 h5eee18b_1
libxcb 1.17.0 h9b100fa_0
libxkbcommon 1.0.1 h5eee18b_1 anaconda
libxml2 2.10.4 hcbfbd50_0
libxslt 1.1.37 h2085143_0 anaconda
libzlib 1.3.1 hb25bd0a_0
lmdb 0.9.31 hb25bd0a_0 anaconda
lz4-c 1.9.4 h6a678d5_1
lzo 2.10 h7b6447c_2 anaconda
mkl 2023.1.0 h213fc3f_46344
mkl-service 2.4.0 py38h5eee18b_1
mkl_fft 1.3.8 py38h5eee18b_0
mkl_random 1.2.4 py38hdb19cb5_0
multidict 6.0.4 py38h5eee18b_0
multiprocess 0.70.15 py38h06a4308_0
mysql 5.7.24 h721c034_2 anaconda
ncurses 6.5 h7934f7d_0
nettle 3.6 he412f7d_0 conda-forge
ninja 1.13.2 h171cf75_0 conda-forge
numexpr 2.8.4 py38hc78ab66_1
numpy 1.24.3 py38hf6e8229_1
numpy-base 1.24.3 py38h060ed82_1
openh264 2.1.1 h4ff587b_0 anaconda
openjpeg 2.5.2 he7f1fd0_0
openssl 3.6.0 h26f9b46_0 conda-forge
orc 2.0.1 h2d29ad5_0
packaging 24.1 py38h06a4308_0
pandas 2.0.3 py38h1128e8f_0
pcre2 10.46 hf426167_0
pillow 10.4.0 py38h5eee18b_0
pip 24.3.1 pyh8b19718_0 conda-forge
pixman 0.46.4 h7934f7d_0
ply 3.11 py38_0 anaconda
portalocker 3.0.0 pypi_0 pypi
pthread-stubs 0.3 h0ce48e5_1
pyarrow 16.1.0 py38h1128e8f_0
pyqt 5.15.7 py38h6a678d5_1 anaconda
pyqt5-sip 12.11.0 py38h6a678d5_1 anaconda
pysocks 1.7.1 py38h06a4308_0
python 3.8.20 he870216_0
python-dateutil 2.9.0post0 py38h06a4308_2
python-tzdata 2025.2 pyhd3eb1b0_0
python-xxhash 2.0.2 py38h5eee18b_1
python_abi 3.8 2_cp38 conda-forge
pytorch 1.12.1 py3.8_cuda11.3_cudnn8.3.2_0 pytorch
pytorch-mutex 1.0 cuda pytorch
pytorch3d 0.7.9 dev_0 <develop>
pytz 2024.1 py38h06a4308_0
pywavelets 1.4.1 pypi_0 pypi
pyyaml 6.0.3 pypi_0 pypi
qt-main 5.15.2 h7358343_9
qt-webengine 5.15.9 hbbf29b9_6 anaconda
qtwebkit 5.212 h3fafdc1_5
re2 2022.04.01 h295c915_0
readline 8.3 hc2a1206_0
regex 2024.9.11 py38h5eee18b_0
requests 2.32.3 py38h06a4308_0
s2n 1.3.27 hdbd6064_0
safetensors 0.4.5 py38ha89cbab_0
scikit-image 0.21.0 pypi_0 pypi
setuptools 75.1.0 py38h06a4308_0
sip 6.6.2 py38h6a678d5_0 anaconda
six 1.16.0 pyhd3eb1b0_1
snappy 1.2.1 h6a678d5_0
sqlite 3.51.0 h2a70700_0
tabulate 0.9.0 pyhd8ed1ab_1 conda-forge
tbb 2021.8.0 hdb19cb5_0
termcolor 2.4.0 pyhd8ed1ab_0 conda-forge
tesseract 5.2.0 h6a678d5_0 anaconda
tifffile 2023.7.10 pypi_0 pypi
tk 8.6.15 h54e0aa7_0
tokenizers 0.20.1 py38h7d74088_0
toml 0.10.2 pyhd3eb1b0_0 anaconda
torchaudio 0.12.1 py38_cu113 pytorch
torchvision 0.13.1 py38_cu113 pytorch
tqdm 4.67.1 pypi_0 pypi
transformers 4.45.2 py38h06a4308_0
typing-extensions 4.11.0 py38h06a4308_0
typing_extensions 4.11.0 py38h06a4308_0
tzdata 2025b h04d1e81_0
urllib3 2.2.3 py38h06a4308_0
utf8proc 2.6.1 h5eee18b_1
wheel 0.44.0 py38h06a4308_0
x264 1!161.3030 h7f98852_1 conda-forge
xorg-libx11 1.8.12 h9b100fa_1
xorg-libxau 1.0.12 h9b100fa_0
xorg-libxdmcp 1.1.5 h9b100fa_0
xorg-libxext 1.3.6 h9b100fa_0
xorg-libxrender 0.9.12 h9b100fa_0
xorg-xorgproto 2024.1 h5eee18b_1
xxhash 0.8.0 h7f8727e_3
xz 5.6.4 h5eee18b_1
yacs 0.1.6 pyhd3eb1b0_1
yaml 0.2.5 h7b6447c_0
yarl 1.11.0 py38h5eee18b_0
zlib 1.3.1 hb25bd0a_0
zstd 1.5.7 h11fc155_0
[8] GCC 版本
gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Copyright (C) 2019 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
[10] Docker 信息（若使用容器）
Docker 未安装或未使用3. ~/.bashrc设置依赖路径
在 ~/.bashrc中的配置,按需添加如下，不然会报一些依赖库路径相关的错误，比如CoppeliaSim以及QT等的库依赖错误：
# <<< conda initialize <<<
# export PATH=/usr/bin:$PATH
export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
export COPPELIASIM_ROOT=/home/gdp/CoppeliaSim_Player_V4_1_0_Ubuntu20_04
export LD_LIBRARY_PATH=$COPPELIASIM_ROOT:$LD_LIBRARY_PATH
export QT_QPA_PLATFORM_PLUGIN_PATH=$COPPELIASIM_ROOT
export DISPLAY=:1.0
export CUDA_HOME=/usr/local/cuda-11.3
export PATH=$PATH:$CUDA_HOME/bin
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CUDA_HOME/lib64
export QT_PLUGIN_PATH=/usr/lib/x86_64-linux-gnu/qt5/plugins
export PATH="/home/gdp/miniconda3/envs/rvt/bin:$PATH"
export PATH="/home/gdp/miniconda3/condabin:$PATH"
# 添加用户本地路径到PYTHONPATH
#export PYTHONPATH=$HOME/.local/lib/python3.8/site-packages:$PYTHONPATH
#export CUB_HOME=~/cub-1.10.0
#export PATH="$CUB_HOME/bin:$PATH"
# Qt插件路径
export QT_PLUGIN_PATH=/home/gdp/CoppeliaSim_Player_V4_1_0_Ubuntu20_04 #重要
export QT_QPA_PLATFORM_PLUGIN_PATH=$QT_PLUGIN_PATH/platforms
conda activate rvt
cd /home/gdp/github/RVT/rvt4. 修改后的自定义指令
# 可以运行
python train.py --exp_cfg_path configs/rvt2_zhhw.yaml --mvt_cfg_path mvt/configs/rvt2_zhhw.yaml \
--device 0 \
--with-eval \
--log-dir runs/train_zhhwtensorboard基础启动指令
tensorboard --logdir runs/train_zhhwtensorboard常用进阶参数,在远程服务器上运行，或者想指定端口，可以使用,--bind_all: 允许通过局域网 IP 访问（如果在远程服务器上这很有用）。
tensorboard --logdir runs/train_zhhw --port 6006 --bind_allzhhw_评估指令
python eval.py --model-folder runs/train_zhhw/rvt2 --eval-datafolder ./data/test --tasks put_item_in_drawer --eval-episodes 5 --log-name test/1 --device 0 --model-name model_last.pth \
--episode-length 30 \
--headless终止运行后执行清理：
Ctrl+C后彻底清理残留资源
#杀掉所有残留的 python 进程
ps aux | grep python | awk '{print $2}' | xargs kill -9 2>/dev/null
#清理共享内存（如果可能的话，非必须但推荐）
sudo rm -rf /dev/shm/* 2>/dev/null可选的任务列表：
RLBench:
task: put_item_in_drawer, reach_and_drag, turn_tap, slide_block_to_color_target, open_drawer, put_groceries_in_cupboard, place_shape_in_shape_sorter, put_money_in_safe, push_buttons, close_jar, stack_blocks, place_cups, place_wine_at_rack_location, light_bulb_in, sweep_to_dustpan_of_size, insert_onto_square_peg, meat_off_grill, stack_cups
条目总数目：18
DAMO开发者矩阵，由阿里巴巴达摩院和中国互联网协会联合发起，致力于探讨最前沿的技术趋势与应用成果，搭建高质量的交流与分享平台，推动技术创新与产业应用链接，围绕“人工智能与新型计算”构建开放共享的开发者生态。
更多推荐
24
0- 0
已为社区贡献2条内容
所有评论(0)