geekyutao / inpaint-anything Goto Github PK
View Code? Open in Web Editor NEWInpaint anything using Segment Anything and inpainting models.
License: Apache License 2.0
Inpaint anything using Segment Anything and inpainting models.
License: Apache License 2.0
When I run your demo remove_anything.py, it returns error that
ImportError: cannot import name 'SamPredictor' from 'segment_anything' (unknown location)
This error is in from segment_anything import SamPredictor, sam_model_registry
I find the SamPredictor class is in predictor.py not segment_anything.py. Does anyone has this problem?
My run order is
python ./remove_anything.py --input_img ./example/remove-anything/dog.jpg --point_coords 200 450 --point_labels 1 --dilate_kernel_size 15 --output_dir ./results --sam_model_type "vit_h" --sam_ckpt ./sam_vit_h_4b8939.pth --lama_config ./lama/configs/prediction/default.yaml --lama_ckpt ./pretrained_models/big-lama
I would like to make a tutorial video on my channel SECourses but I don't see gradio interface or such as in your examples
If you don't have can you release the interface you used to generate those examples images you put in main page?
That shows masked / segmented content after clicking
File "F:\Inpaint-Anything\fill_anything.py", line 126, in
img_filled = fill_img_with_sd(
File "F:\Inpaint-Anything\stable_diffusion_inpaint.py", line 21, in fill_img_with_sd
pipe = StableDiffusionInpaintPipeline.from_pretrained(
File "F:\miniConda\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1008, in from_pretrained
loaded_sub_model = load_sub_model(
File "F:\miniConda\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 444, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
File "F:\miniConda\lib\site-packages\diffusers\models\modeling_utils.py", line 491, in from_pretrained
config, unused_kwargs, commit_hash = cls.load_config(
File "F:\miniConda\lib\site-packages\diffusers\configuration_utils.py", line 349, in load_config
raise EnvironmentError(
OSError: Error no file named config.json found in directory C:\Users\zhou.cache\huggingface\hub\models--stabilityai--stable-diffusion-2-inpainting\snapshots\781cb3e2113c1932245692810716dfd27e355ab6\vae.
[Unit]
Description=inpaint_anything_service
After=network.target syslog.target
Wants=network.target
[Service]
Type=simple
Restart=on-failure
RestartSec=5s
#Environment="PATH=/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/opt/mambaforge/envs/anything/bin:/opt/Inpaint-Anything/Inpaint-Anything"
ExecStart=/opt/mambaforge/envs/anything/bin/python /opt/Inpaint-Anything/Inpaint-Anything/app/app.py
ExecReload=/opt/mambaforge/envs/anything/bin/python /opt/Inpaint-Anything/Inpaint-Anything/app/app.py
ExecStop=/bin/kill $MAINPID
User=root
Group=root
OS: RedHat 9.1 x64
Of course, running "python app.py" under the app folder can run the Web UI normally.
I still have the same problem with the installation of the software. Tried what you suggested. Same error:
D:\Inpaint-Anything>python -m pip install -e segment_anything
Defaulting to user installation because normal site-packages is not writeable
ERROR: segment_anything is not a valid editable requirement. It should either be a path to a local project or a VCS URL (beginning with bzr+http, bzr+https, bzr+ssh, bzr+sftp, bzr+ftp, bzr+lp, bzr+file, git+http, git+https, git+ssh, git+git, git+file, hg+file, hg+http, hg+https, hg+ssh, hg+static-http, svn+ssh, svn+http, svn+https, svn+svn, svn+file).
D:\Inpaint-Anything>
i have an tourist img, i use the Inpaint-Anything to remove one tourister,
it can remove well, but leaving with shadow,
could you please tell me how to erase the shadow, so it looks like the lady take a picture by herself?
The pictures are all from the Internet If there is infringement, please contact to delete Thank you
你好,謝謝你們偉大的作品
想請問,如果想要自動消除某個物件,例如移除車子
可以下一個指令,例如 remove car 就把所有車子都移除掉
目前你的版本是手動點擊,不知道能否做到自動化的方式
謝謝
It seemed that Grounding SAM and many other projects can do better? Inpainting, editing and so on.
Hi, I have a question, how to enter multiple coordinates?
python remove_anything.py \
--input_img ~/input/test1.png \ --point_coords 58 127 778 127 58 366 778 366 \ --point_labels 4 \ --dilate_kernel_size 15 \ --output_dir ~/output \ --sam_model_type "vit_h" \ --sam_ckpt ~/sam/sam_vit_h_4b8939.pth \ --lama_config ./lama/configs/prediction/default.yaml \ --lama_ckpt big-lama
Traceback (most recent call last):
File "/root/Inpaint-Anything/remove_anything.py", line 75, in
masks, _, _ = predict_masks_with_sam(
File "/root/Inpaint-Anything/sam_segment.py", line 28, in predict_masks_with_sam
masks, scores, logits = predictor.predict(
File "/root/Inpaint-Anything/segment_anything/segment_anything/predictor.py", line 154, in predict
masks, iou_predictions, low_res_masks = self.predict_torch(
File "/root/miniconda3/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
return func(*args, **kwargs)
File "/root/Inpaint-Anything/segment_anything/segment_anything/predictor.py", line 222, in predict_torch
sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
File "/root/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/Inpaint-Anything/segment_anything/segment_anything/modeling/prompt_encoder.py", line 155, in forward
point_embeddings = self._embed_points(coords, labels, pad=(boxes is None))
File "/root/Inpaint-Anything/segment_anything/segment_anything/modeling/prompt_encoder.py", line 84, in _embed_points
points = torch.cat([points, padding_point], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 8 but got size 2 for tensor number 1 in the list.
ImportError: cannot import name 'SamplePadding' from 'kornia'
(/root/miniconda3/lib/python3.10/site-packages/kornia/init.py)
so, what's wrong?
想用自己的数据进行inpaint,怎么获取要去掉物体--point_coords这个参数?
运行的时候没有SAM那个交互式的界面,这是正常的吗?怎么开启SAM交互式界面获得--point_coords?
谢谢!!
ENV:
windows 11
python 3.11.3
log:
C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\app>python app.py --lama_config ./lama/configs/prediction/default.yaml --lama_ckpt ./pretrained_models/big-lama --sam_ckpt ./pretrained_models/sam_vit_h_4b8939.pth
Traceback (most recent call last):
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\app\app.py", line 13, in <module>
from lama_inpaint import inpaint_img_with_lama, build_lama_model, inpaint_img_with_builded_lama
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\lama_inpaint.py", line 19, in <module>
from saicinpainting.evaluation.utils import move_to_device
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\lama\saicinpainting\evaluation\__init__.py", line 6, in <module>
from saicinpainting.evaluation.losses.base_loss import SSIMScore, LPIPSScore, FIDScore
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\lama\saicinpainting\evaluation\losses\base_loss.py", line 15, in <module>
from .lpips import PerceptualLoss
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\lama\saicinpainting\evaluation\losses\lpips.py", line 15, in <module>
from saicinpainting.utils import get_shape
File "C:\Users\Jarvis\Desktop\Project\AI\Inpaint-Anything\lama\saicinpainting\utils.py", line 12, in <module>
from pytorch_lightning import seed_everything
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\__init__.py", line 28, in <module>
from pytorch_lightning import metrics # noqa: E402
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.classification import ( # noqa: F401
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.classification.accuracy import Accuracy # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\accuracy.py", line 18, in <module>
from pytorch_lightning.metrics.functional.accuracy import _accuracy_compute, _accuracy_update
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\functional\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.functional.accuracy import accuracy # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\functional\accuracy.py", line 18, in <module>
from pytorch_lightning.metrics.classification.helpers import _input_format_classification, DataType
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\helpers.py", line 19, in <module>
from pytorch_lightning.metrics.utils import select_topk, to_onehot
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\metrics\utils.py", line 18, in <module>
from pytorch_lightning.utilities import rank_zero_warn
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\utilities\__init__.py", line 18, in <module>
from pytorch_lightning.utilities.apply_func import move_data_to_device # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\utilities\apply_func.py", line 25, in <module>
from pytorch_lightning.utilities.imports import _compare_version, _TORCHTEXT_AVAILABLE
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\utilities\imports.py", line 76, in <module>
_HYDRA_EXPERIMENTAL_AVAILABLE = _module_available("hydra.experimental")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\pytorch_lightning\utilities\imports.py", line 35, in _module_available
return find_spec(module_path) is not None
^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib.util>", line 94, in find_spec
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\__init__.py", line 5, in <module>
from hydra import utils
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\utils.py", line 8, in <module>
import hydra._internal.instantiate._instantiate2
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 11, in <module>
from hydra._internal.utils import _locate
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\_internal\utils.py", line 17, in <module>
from hydra.core.utils import get_valid_filename, validate_config_path
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\core\utils.py", line 19, in <module>
from hydra.core.hydra_config import HydraConfig
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\core\hydra_config.py", line 6, in <module>
from hydra.conf import HydraConf
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\conf\__init__.py", line 45, in <module>
class JobConf:
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\site-packages\hydra\conf\__init__.py", line 70, in JobConf
@dataclass
^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\dataclasses.py", line 1223, in dataclass
return wrap(cls)
^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\dataclasses.py", line 1213, in wrap
return _process_class(cls, init, repr, eq, order, unsafe_hash,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\dataclasses.py", line 958, in _process_class
cls_fields.append(_get_field(cls, name, type, kw_only))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Jarvis\AppData\Local\Programs\Python\Python311\Lib\dataclasses.py", line 815, in _get_field
raise ValueError(f'mutable default {type(f.default)} for field '
ValueError: mutable default <class 'hydra.conf.JobConf.JobConfig.OverrideDirname'> for field override_dirname is not allowed: use default_factory
Good Morning
Thank you for your contribution. I was wondering why you used only Lama for "Remove Anything". Did you find it better suited than Stable Diffusion inpainting?
hello, I don't understand why rm lama refine ?
hi, i am so surprised by your latest feature, the local web ui, so i quickly run the app.py for a test, however i get an error like this: cannot import name 'build_lama_model' from 'lama_inpaint'
please help me solve the problem, or give me more information about this, thanks!
python app.py \
> --lama_config /home/lcc/github.com/Inpaint-Anything/pretrained_models/big-lama/config.yaml \
> --lama_ckpt /home/lcc/github.com/Inpaint-Anything/pretrained_models/big-lama/models/best.ckpt \
> --sam_ckpt /home/lcc/github.com/Inpaint-Anything/pretrained_models/sam_vit_h_4b8939.pth
Detectron v2 is not installed
Traceback (most recent call last):
File "/home/lcc/github.com/Inpaint-Anything/app/app.py", line 13, in <module>
from lama_inpaint import inpaint_img_with_lama, build_lama_model, inpaint_img_with_builded_lama
ImportError: cannot import name 'build_lama_model' from 'lama_inpaint' (/home/lcc/github.com/Inpaint-Anything/lama_inpaint.py)
centos7
GCC9.5
python3.9
cuda 11.3
torch 1.12.1
I am curious about your difference with Grounding-SAM.
I get the message and the program is pause. I cannot see any process to continue. I wonder how I can run the code?
It is an awesome segment project. I try your new web ui, but I see the wrong result in the web ui.
First I load the baseball image, I click the image and obtain the result. Then I reset the web ui and I load the dog image.When I click the dog image and click the predict mask using sam. The segment result is last image not the current image.
python -m pip install lama_requirements_windows.txt
ERROR: Could not find a version that satisfies the requirement lama_requirements_windows.txt (from versions: none)
ERROR: No matching distribution found for lama_requirements_windows.txt
I wonder if numpy version matters (mine is 1.22.4). I got a bug about np.bool before, after I change numpy's version, it turns into bus error.
Although remove_anything.py works fine for me, when I try other features such as fill_anything.py or replace_anything.py
I`m stuck with the error below:
malloc(): invalid next->prev_inuse (unsorted)
Aborted (core dumped)
apparently it is generally displayed when running C++ codes.
When I run the command:
python3 -m pip install -r lama/requirements.txt
the system displays an error message saying that
the clang compiler does not support '-march=native'.
Does Inpaint-Anything not support MacBook Pro with Intel CPU? My MacBook Pro CPU is intel Core i5 Quad 2GHz, MacOS version is 13.1.
I tried running the remove_anything command as mentioned in the README and it ended up taking 4m 30s to finish. I ran this on Colab without GPU. Is this the expected timeframe or am I doing something wrong?
Thanks
when i test fill_anything i get :
1、vae\diffusion_pytorch_model.safetensors not found
2、text_encoder\model.safetensors not found
i want to know all the models download URL for the features:
[Remove Anything]
[Fill Anything]
[Replace Anything]
[Remove Anything 3D]
[Remove Anything Video]
thank you !
方便调用
Please help with the version number of python you are using. My installation with python=3.10.6 always fails
as the title
An issue inside my extension redirected me here. Many people might be excited about this work, but have no good user interface. If you use A1111 SD-WebUI, my SAM extension + Mikubill ControlNet extension are all you need to try inpaint-anything inside a good and easy-to-use UI. Check README and this tutorial for how to use. You do not need to download whatever huge annoying general-purposed inpaint model. A base model + lllyasviel ControlNet inpainting model + SAM are all you need.
I am trying to do a Fill any thing and get an execution error like this Please help me with a solution.
Traceback (most recent call last):
File "fill_anything.py", line 79, in
masks, _, _ = predict_masks_with_sam(
File "/home/haga/Inpaint-Anything/sam_segment.py", line 23, in predict_masks_with_sam
sam = sam_model_registrymodel_type
File "/home/haga/Inpaint-Anything/segment_anything/segment_anything/build_sam.py", line 15, in build_sam_vit_h
return _build_sam(
File "/home/haga/Inpaint-Anything/segment_anything/segment_anything/build_sam.py", line 104, in _build_sam
with open(checkpoint, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'sam_vit_h_4b8939.pth'
你好,我这出现一个问题,我按照readme一步步安装成功,最后执行remove_anything.py文件时报错:
Detectron v2 is not installed
Traceback (most recent call last):
File "D:\AI\Inpaint-Anything\remove_anything.py", line 75, in
masks, _, _ = predict_masks_with_sam(
File "D:\AI\Inpaint-Anything\sam_segment.py", line 24, in predict_masks_with_sam
sam.to(device=device)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 1145, in to
return self._apply(convert)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 820, in apply
param_applied = fn(param)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "C:\Users\xxx\PycharmProjects\pythonProject2\venv\lib\site-packages\torch\cuda_init.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
When i run this code following: python remove_anything.py --input_img ./example/remove-anything/dog.jpg --point_coords 200 450 --point_labels 1 --dilate_kernel_size 15 --output_dir ./results --sam_model_type "vit_h" --sam_ckpt ./pretrained_models/sam_vit_h_4b8939.pth --lama_config ./lama/configs/prediction/default.yaml --lama_ckpt ./pretrained_models/big-lama, there have:
i keep following as the Installation and usage instruation, but i can't know what happend to get the "Detectron v2 is not installed" error?
Here is the error message:
ERROR: segment_anything is not a valid editable requirement. It should either be a path to a local project or a VCS URL (beginning with bzr+http, bzr+https, bzr+ssh, bzr+sftp, bzr+ftp, bzr+lp, bzr+file, git+http, git+https, git+ssh, git+git, git+file, hg+file, hg+http, hg+https, hg+ssh, hg+static-http, svn+ssh, svn+http, svn+https, svn+svn, svn+file).
I must be doing something wrong. Please tell me what it is. Thank you.
is there a hugging face for this?
Huggingface space for this project shows Runtime error
Hello! Great work this lib is amazing so far!
I am wondering how can we crop the area segmented by SAM, inpaint it with SD and expose that as an image on its own; The output Im trying to get is a mask of a point selection inpainted and everything else on the image as transparent or black
Would anyone know how to do that? Maybe Im missing something and SAM already exposes the mask as black/white images? I feel like everything is there to do that and its just a matter of piping things together properly, any help would be appreciated!
I am getting an error when I try to run the first example:
python remove_anything.py --input_img ./example/remove-anything/dog.jpg --point_coords 200 450 --point_labels 1 --dilate_kernel_size 15 --output_dir ./results --sam_model_type "vit_h" --sam_ckpt ./pretrained_models/sam_vit_h_4b8939.pth --lama_config ./lama/configs/prediction/default.yaml --lama_ckpt ./pretrained_models/big-lama
I am running on Windows 10 - 64 with Python 3.11
I had to update the lama requirements to use the current version of scikit-image ( 0.20.0 ) as the version called for ( 0.17.2 ) would not compile whereas the current version compiles just fine.
Here is the full error output:
Traceback (most recent call last):
File "F:\ai\Inpaint-Anything\remove_anything.py", line 9, in <module>
from lama_inpaint import inpaint_img_with_lama
File "F:\ai\Inpaint-Anything\lama_inpaint.py", line 19, in <module>
from saicinpainting.evaluation.utils import move_to_device
File "F:\ai\Inpaint-Anything\lama\saicinpainting\evaluation\__init__.py", line 6, in <module>
from saicinpainting.evaluation.losses.base_loss import SSIMScore, LPIPSScore, FIDScore
File "F:\ai\Inpaint-Anything\lama\saicinpainting\evaluation\losses\base_loss.py", line 15, in <module>
from .lpips import PerceptualLoss
File "F:\ai\Inpaint-Anything\lama\saicinpainting\evaluation\losses\lpips.py", line 15, in <module>
from saicinpainting.utils import get_shape
File "F:\ai\Inpaint-Anything\lama\saicinpainting\utils.py", line 12, in <module>
from pytorch_lightning import seed_everything
File "C:\Python311\Lib\site-packages\pytorch_lightning\__init__.py", line 28, in <module>
from pytorch_lightning import metrics # noqa: E402
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.classification import ( # noqa: F401
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.classification.accuracy import Accuracy # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\accuracy.py", line 18, in <module>
from pytorch_lightning.metrics.functional.accuracy import _accuracy_compute, _accuracy_update
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\functional\__init__.py", line 14, in <module>
from pytorch_lightning.metrics.functional.accuracy import accuracy # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\functional\accuracy.py", line 18, in <module>
from pytorch_lightning.metrics.classification.helpers import _input_format_classification, DataType
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\classification\helpers.py", line 19, in <module>
from pytorch_lightning.metrics.utils import select_topk, to_onehot
File "C:\Python311\Lib\site-packages\pytorch_lightning\metrics\utils.py", line 18, in <module>
from pytorch_lightning.utilities import rank_zero_warn
File "C:\Python311\Lib\site-packages\pytorch_lightning\utilities\__init__.py", line 18, in <module>
from pytorch_lightning.utilities.apply_func import move_data_to_device # noqa: F401
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\pytorch_lightning\utilities\apply_func.py", line 25, in <module>
from pytorch_lightning.utilities.imports import _compare_version, _TORCHTEXT_AVAILABLE
File "C:\Python311\Lib\site-packages\pytorch_lightning\utilities\imports.py", line 76, in <module>
_HYDRA_EXPERIMENTAL_AVAILABLE = _module_available("hydra.experimental")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\site-packages\pytorch_lightning\utilities\imports.py", line 35, in _module_available
return find_spec(module_path) is not None
^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib.util>", line 94, in find_spec
File "C:\Python311\Lib\site-packages\hydra\__init__.py", line 5, in <module>
from hydra import utils
File "C:\Python311\Lib\site-packages\hydra\utils.py", line 8, in <module>
import hydra._internal.instantiate._instantiate2
File "C:\Python311\Lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 11, in <module>
from hydra._internal.utils import _locate
File "C:\Python311\Lib\site-packages\hydra\_internal\utils.py", line 17, in <module>
from hydra.core.utils import get_valid_filename, validate_config_path
File "C:\Python311\Lib\site-packages\hydra\core\utils.py", line 19, in <module>
from hydra.core.hydra_config import HydraConfig
File "C:\Python311\Lib\site-packages\hydra\core\hydra_config.py", line 6, in <module>
from hydra.conf import HydraConf
File "C:\Python311\Lib\site-packages\hydra\conf\__init__.py", line 45, in <module>
class JobConf:
File "C:\Python311\Lib\site-packages\hydra\conf\__init__.py", line 70, in JobConf
@dataclass
^^^^^^^^^
File "C:\Python311\Lib\dataclasses.py", line 1223, in dataclass
return wrap(cls)
^^^^^^^^^
File "C:\Python311\Lib\dataclasses.py", line 1213, in wrap
return _process_class(cls, init, repr, eq, order, unsafe_hash,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\dataclasses.py", line 958, in _process_class
cls_fields.append(_get_field(cls, name, type, kw_only))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Python311\Lib\dataclasses.py", line 815, in _get_field
raise ValueError(f'mutable default {type(f.default)} for field '
ValueError: mutable default <class 'hydra.conf.JobConf.JobConfig.OverrideDirname'> for field override_dirname is not allowed: use default_factory
您在手册中的演示代码均取point_labels为1,是目标和背景的区分吗?
2023-04-19 14:17:53.241788: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0
.
2023-04-19 14:17:53.291639: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-04-19 14:17:54.054049: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Traceback (most recent call last):
File "replace_anything.py", line 77, in
masks, _, _ = predict_masks_with_sam(
File "/home/Inpaint-Anything/sam_segment.py", line 23, in predict_masks_with_sam
sam = sam_model_registrymodel_type
File "/home/Inpaint-Anything/segment_anything/segment_anything/build_sam.py", line 15, in build_sam_vit_h
return _build_sam(
File "/home/Inpaint-Anything/segment_anything/segment_anything/build_sam.py", line 105, in _build_sam
state_dict = torch.load(f)
File "/opt/miniconda3/envs/Inpainting/lib/python3.8/site-packages/torch/serialization.py", line 809, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/opt/miniconda3/envs/Inpainting/lib/python3.8/site-packages/torch/serialization.py", line 1172, in _load
result = unpickler.load()
File "/opt/miniconda3/envs/Inpainting/lib/python3.8/site-packages/torch/serialization.py", line 1142, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "/opt/miniconda3/envs/Inpainting/lib/python3.8/site-packages/torch/serialization.py", line 1112, in load_tensor
storage = zip_file.get_storage_from_record(name, numel, torch.UntypedStorage)._typed_storage()._untyped_storage
RuntimeError: PytorchStreamReader failed reading file data/11: invalid header or archive is corrupted
应该如何解决?还有一个问题,那个big-lama是把链接里面两个文件都放在pretrained_models里面吗?
This is not an error, more a question; is it somehow possible to segment any object in the image + fill the hole and save the segmentations as separate pngs?
I have two nvidia P4000 gpu (8GB RAM per). The memory of one gpu will overflow when run “python remove ....” or "python fill...." if I run a web UI app in the background.
Based on past experience, torch can specify the index of the GPU used. So can we specify the index of the GPU used? If possible, can a parameter setting be added?
Thanks
Hi, Thank you for the good paper and project.
I saw the issue of prompts in the research paper. How about developing a model that logically explains complex sentences by dividing them, or using it like Visual ChatGPT?
Specifically, it can solve by decomposing like Visual ChatGPT. This method of breaking complex sentences into shorter sentences and processing them in order.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.