Files
modelscope/requirements/cv.txt

74 lines
1.0 KiB
Plaintext
Raw Permalink Normal View History

accelerate
albumentations>=1.0.3
av>=9.2.0
bmt_clipit>=1.0
chumpy
clip>=1.0
control_ldm
ddpm_guided_diffusion
diffusers
easydict
easyrobust
edit_distance
face_alignment>=1.3.5
fairscale>=0.4.1
fastai>=1.0.51
ffmpeg>=1.4
ffmpeg-python>=0.2.0
ftfy
fvcore
healpy
imageio>=2.9.0
imageio-ffmpeg>=0.4.2
imgaug>=0.4.0
kornia>=0.5.0
lap
lmdb
lpips
ml_collections
mmcls>=0.21.0
mmdet>=2.25.0,<=2.28.2
# mmdet3d-1.0.0rc6 remove networkx and numba version restriction
mmdet3d==1.0.0a1
mmsegmentation<=0.30.0
moviepy>=1.0.3
nerfacc==0.2.2
networkx
numba
omegaconf
onnx
onnxruntime>=1.10
onnxsim
open-clip-torch>=2.7.0
opencv-python
paint_ldm
pandas
panopticapi
plyfile>=0.7.4
psutil
pyclipper
PyMCubes
pytorch-lightning
regex
# <0.20.0 for compatible python3.7 python3.8
scikit-image>=0.19.3,<0.20.0
scikit-learn>=0.20.1
shapely
shotdetect_scenedetect_lgss>=0.0.4
smplx
tensorflow-estimator>=1.15.1
tf_slim
thop
timm>=0.4.9
torch-scatter
torchmetrics>=0.6.2
torchsummary>=1.5.1
torchvision
add text-to-360pano-image pipeline, mod cv requirements 7月份计划上线的360全景图生成模型,自研 模型权重文件地址https://www.modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary #### 依赖项说明 ##### 由于要使用xformers,torch版本最好使用1.13.1 ``` pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116 ``` ##### 对应的diffusers和xformers版本如下 ``` pip install -U diffusers==0.18.0 pip install xformers==0.0.16 pip install triton, accelerate, transformers ``` ##### ModelScope Library 需要使用cv ``` pip install modelscope pip install "modelscope[cv]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html ``` ##### 此外,还需要安装第三方的一个库,Real-ESRGAN, 安装方法如下 ``` # Install basicsr - https://github.com/xinntao/BasicSR # We use BasicSR for both training and inference pip install basicsr # facexlib and gfpgan are for face enhancement pip install facexlib pip install gfpgan pip install Pillow pip install tqdm pip install realesrgan==0.3.0 ``` Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/13346430 * add text-to-360pano-image pipeline * add text-to-360pano-image pipeline, mod cv requirements * rm redundant files and cv requirements; add standard input and output definations * fix diffusers==0.18.0 and run test * fix diffusers==0.18.0 in multi-modal and run test again * add model_revision='v1.0.0' * fix yapf * add trycatch for enabling xformers * fix key error * add install xformers in test/setup * skip highres.fix in ci * feat: Fix conflict, auto commit by WebIDE
2023-07-27 11:33:39 +08:00
tqdm
transformers>=4.26.0
trimesh
ujson
utils
videofeatures_clipit>=1.0
yacs