merge
This commit is contained in:
yadonglu
404
Dockerfile
404
Dockerfile
@@ -1,203 +1,201 @@
|
|||||||
# Dockerfile for OmniParser with GPU support and OpenGL libraries
|
# Dockerfile for OmniParser with GPU support and OpenGL libraries
|
||||||
#
|
#
|
||||||
# This Dockerfile is intended to create an environment with NVIDIA CUDA
|
# This Dockerfile is intended to create an environment with NVIDIA CUDA
|
||||||
# support and the necessary dependencies to run the OmniParser project.
|
# support and the necessary dependencies to run the OmniParser project.
|
||||||
# The configuration is designed to support applications that rely on
|
# The configuration is designed to support applications that rely on
|
||||||
# Python 3.12, OpenCV, Hugging Face transformers, and Gradio. Additionally,
|
# Python 3.12, OpenCV, Hugging Face transformers, and Gradio. Additionally,
|
||||||
# it includes steps to pull large files from Git LFS and a script to
|
# it includes steps to pull large files from Git LFS and a script to
|
||||||
# convert model weights from .safetensor to .pt format. The container
|
# convert model weights from .safetensor to .pt format. The container
|
||||||
# runs a Gradio server by default, exposed on port 7861.
|
# runs a Gradio server by default, exposed on port 7861.
|
||||||
#
|
#
|
||||||
# Base image: nvidia/cuda:12.3.1-devel-ubuntu22.04
|
# Base image: nvidia/cuda:12.3.1-devel-ubuntu22.04
|
||||||
#
|
#
|
||||||
# Key features:
|
# Key features:
|
||||||
# - System dependencies for OpenGL to support graphical libraries.
|
# - System dependencies for OpenGL to support graphical libraries.
|
||||||
# - Miniconda for Python 3.12, allowing for environment management.
|
# - Miniconda for Python 3.12, allowing for environment management.
|
||||||
# - Git Large File Storage (LFS) setup for handling large model files.
|
# - Git Large File Storage (LFS) setup for handling large model files.
|
||||||
# - Requirement file installation, including specific versions of
|
# - Requirement file installation, including specific versions of
|
||||||
# OpenCV and Hugging Face Hub.
|
# OpenCV and Hugging Face Hub.
|
||||||
# - Entrypoint script execution with Gradio server configuration for
|
# - Entrypoint script execution with Gradio server configuration for
|
||||||
# external access.
|
# external access.
|
||||||
|
|
||||||
# If it is gpu enviroment, use nvidia/cuda:12.3.1-devel-ubuntu22.04, otherwise use ubuntu:22.04
|
FROM nvidia/cuda:12.3.1-devel-ubuntu22.04
|
||||||
# FROM nvidia/cuda:12.3.1-devel-ubuntu22.04
|
|
||||||
FROM docker.io/ubuntu:22.04
|
# Install system dependencies with explicit OpenGL libraries
|
||||||
|
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
|
||||||
# Install system dependencies with explicit OpenGL libraries
|
git \
|
||||||
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
|
git-lfs \
|
||||||
git \
|
wget \
|
||||||
git-lfs \
|
libgl1 \
|
||||||
wget \
|
libglib2.0-0 \
|
||||||
libgl1 \
|
libsm6 \
|
||||||
libglib2.0-0 \
|
libxext6 \
|
||||||
libsm6 \
|
libxrender1 \
|
||||||
libxext6 \
|
libglu1-mesa \
|
||||||
libxrender1 \
|
libglib2.0-0 \
|
||||||
libglu1-mesa \
|
libsm6 \
|
||||||
libglib2.0-0 \
|
libxrender1 \
|
||||||
libsm6 \
|
libxext6 \
|
||||||
libxrender1 \
|
python3-opencv \
|
||||||
libxext6 \
|
&& apt-get clean \
|
||||||
python3-opencv \
|
&& rm -rf /var/lib/apt/lists/* \
|
||||||
&& apt-get clean \
|
&& git lfs install
|
||||||
&& rm -rf /var/lib/apt/lists/* \
|
|
||||||
&& git lfs install
|
# Install Miniconda for Python 3.12
|
||||||
|
RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
|
||||||
# Install Miniconda for Python 3.12
|
bash miniconda.sh -b -p /opt/conda && \
|
||||||
RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
|
rm miniconda.sh
|
||||||
bash miniconda.sh -b -p /opt/conda && \
|
ENV PATH="/opt/conda/bin:$PATH"
|
||||||
rm miniconda.sh
|
|
||||||
ENV PATH="/opt/conda/bin:$PATH"
|
# Create and activate Conda environment with Python 3.12, and set it as the default
|
||||||
|
RUN conda create -n omni python=3.12 && \
|
||||||
# Create and activate Conda environment with Python 3.12, and set it as the default
|
echo "source activate omni" > ~/.bashrc
|
||||||
RUN conda create -n omni python=3.12 && \
|
ENV CONDA_DEFAULT_ENV=omni
|
||||||
echo "source activate omni" > ~/.bashrc
|
ENV PATH="/opt/conda/envs/omni/bin:$PATH"
|
||||||
ENV CONDA_DEFAULT_ENV=omni
|
|
||||||
ENV PATH="/opt/conda/envs/omni/bin:$PATH"
|
# Set the working directory in the container
|
||||||
|
WORKDIR /usr/src/app
|
||||||
# Set the working directory in the container
|
|
||||||
WORKDIR /usr/src/app
|
# Copy project files and requirements
|
||||||
|
COPY . .
|
||||||
# Copy project files and requirements
|
COPY requirements.txt /usr/src/app/requirements.txt
|
||||||
COPY . .
|
|
||||||
COPY requirements.txt /usr/src/app/requirements.txt
|
# Initialize Git LFS and pull LFS files
|
||||||
|
RUN git lfs install && \
|
||||||
# Initialize Git LFS and pull LFS files
|
git lfs pull
|
||||||
RUN git lfs install && \
|
|
||||||
git lfs pull
|
# Install dependencies from requirements.txt with specific opencv-python-headless version
|
||||||
|
RUN . /opt/conda/etc/profile.d/conda.sh && conda activate omni && \
|
||||||
# Install dependencies from requirements.txt with specific opencv-python-headless version
|
pip uninstall -y opencv-python opencv-python-headless && \
|
||||||
RUN . /opt/conda/etc/profile.d/conda.sh && conda activate omni && \
|
pip install --no-cache-dir opencv-python-headless==4.8.1.78 && \
|
||||||
# pip uninstall -y opencv-python opencv-python-headless && \
|
pip install -r requirements.txt && \
|
||||||
# pip install --no-cache-dir opencv-python-headless==4.8.1.78 && \
|
pip install huggingface_hub
|
||||||
pip install -r requirements.txt && \
|
|
||||||
pip install huggingface_hub
|
# Run download.py to fetch model weights and convert safetensors to .pt format
|
||||||
|
# RUN . /opt/conda/etc/profile.d/conda.sh && conda activate omni && \
|
||||||
# Run download.py to fetch model weights and convert safetensors to .pt format
|
# python download.py && \
|
||||||
# RUN . /opt/conda/etc/profile.d/conda.sh && conda activate omni && \
|
# echo "Contents of weights directory:" && \
|
||||||
# python download.py && \
|
# ls -lR weights && \
|
||||||
# echo "Contents of weights directory:" && \
|
# python weights/convert_safetensor_to_pt.py
|
||||||
# ls -lR weights && \
|
|
||||||
# python weights/convert_safetensor_to_pt.py
|
# Expose the default Gradio port
|
||||||
|
EXPOSE 7861
|
||||||
# Expose the default Gradio port
|
|
||||||
EXPOSE 7861
|
# Configure Gradio to be accessible externally
|
||||||
|
ENV GRADIO_SERVER_NAME="0.0.0.0"
|
||||||
# Configure Gradio to be accessible externally
|
|
||||||
ENV GRADIO_SERVER_NAME="0.0.0.0"
|
# Copy and set permissions for entrypoint script
|
||||||
|
# COPY entrypoint.sh /usr/src/app/entrypoint.sh
|
||||||
# Copy and set permissions for entrypoint script
|
# RUN chmod +x /usr/src/app/entrypoint.sh
|
||||||
# COPY entrypoint.sh /usr/src/app/entrypoint.sh
|
|
||||||
# RUN chmod +x /usr/src/app/entrypoint.sh
|
# To debug, keep the container running
|
||||||
|
# CMD ["tail", "-f", "/dev/null"]
|
||||||
# To debug, keep the container running
|
|
||||||
# CMD ["tail", "-f", "/dev/null"]
|
################################################################################################
|
||||||
|
# virtual display related setup --> from anthropic-quickstarts/computer-use-demo/Dockerfile
|
||||||
################################################################################################
|
|
||||||
# virtual display related setup --> from anthropic-quickstarts/computer-use-demo/Dockerfile
|
ENV DEBIAN_FRONTEND=noninteractive
|
||||||
|
ENV DEBIAN_PRIORITY=high
|
||||||
ENV DEBIAN_FRONTEND=noninteractive
|
|
||||||
ENV DEBIAN_PRIORITY=high
|
RUN apt-get update && \
|
||||||
|
apt-get -y upgrade && \
|
||||||
RUN apt-get update && \
|
apt-get -y install \
|
||||||
apt-get -y upgrade && \
|
# UI Requirements
|
||||||
apt-get -y install \
|
xvfb \
|
||||||
# UI Requirements
|
xterm \
|
||||||
xvfb \
|
xdotool \
|
||||||
xterm \
|
scrot \
|
||||||
xdotool \
|
imagemagick \
|
||||||
scrot \
|
sudo \
|
||||||
imagemagick \
|
mutter \
|
||||||
sudo \
|
x11vnc \
|
||||||
mutter \
|
# Python/pyenv reqs
|
||||||
x11vnc \
|
build-essential \
|
||||||
# Python/pyenv reqs
|
libssl-dev \
|
||||||
build-essential \
|
zlib1g-dev \
|
||||||
libssl-dev \
|
libbz2-dev \
|
||||||
zlib1g-dev \
|
libreadline-dev \
|
||||||
libbz2-dev \
|
libsqlite3-dev \
|
||||||
libreadline-dev \
|
curl \
|
||||||
libsqlite3-dev \
|
git \
|
||||||
curl \
|
libncursesw5-dev \
|
||||||
git \
|
xz-utils \
|
||||||
libncursesw5-dev \
|
tk-dev \
|
||||||
xz-utils \
|
libxml2-dev \
|
||||||
tk-dev \
|
libxmlsec1-dev \
|
||||||
libxml2-dev \
|
libffi-dev \
|
||||||
libxmlsec1-dev \
|
liblzma-dev \
|
||||||
libffi-dev \
|
# Network tools
|
||||||
liblzma-dev \
|
net-tools \
|
||||||
# Network tools
|
netcat \
|
||||||
net-tools \
|
# PPA req
|
||||||
netcat \
|
software-properties-common && \
|
||||||
# PPA req
|
# Userland apps
|
||||||
software-properties-common && \
|
sudo add-apt-repository ppa:mozillateam/ppa && \
|
||||||
# Userland apps
|
sudo apt-get install -y --no-install-recommends \
|
||||||
sudo add-apt-repository ppa:mozillateam/ppa && \
|
libreoffice \
|
||||||
sudo apt-get install -y --no-install-recommends \
|
firefox-esr \
|
||||||
libreoffice \
|
x11-apps \
|
||||||
firefox-esr \
|
xpdf \
|
||||||
x11-apps \
|
gedit \
|
||||||
xpdf \
|
xpaint \
|
||||||
gedit \
|
tint2 \
|
||||||
xpaint \
|
galculator \
|
||||||
tint2 \
|
pcmanfm \
|
||||||
galculator \
|
unzip && \
|
||||||
pcmanfm \
|
apt-get clean
|
||||||
unzip && \
|
|
||||||
apt-get clean
|
# Install noVNC
|
||||||
|
RUN git clone --branch v1.5.0 https://github.com/novnc/noVNC.git /opt/noVNC && \
|
||||||
# Install noVNC
|
git clone --branch v0.12.0 https://github.com/novnc/websockify /opt/noVNC/utils/websockify && \
|
||||||
RUN git clone --branch v1.5.0 https://github.com/novnc/noVNC.git /opt/noVNC && \
|
ln -s /opt/noVNC/vnc.html /opt/noVNC/index.html
|
||||||
git clone --branch v0.12.0 https://github.com/novnc/websockify /opt/noVNC/utils/websockify && \
|
|
||||||
ln -s /opt/noVNC/vnc.html /opt/noVNC/index.html
|
# setup user
|
||||||
|
ENV USERNAME=computeruse
|
||||||
# setup user
|
ENV HOME=/home/$USERNAME
|
||||||
ENV USERNAME=computeruse
|
RUN useradd -m -s /bin/bash -d $HOME $USERNAME
|
||||||
ENV HOME=/home/$USERNAME
|
RUN echo "${USERNAME} ALL=(ALL) NOPASSWD: ALL" >> /etc/sudoers
|
||||||
RUN useradd -m -s /bin/bash -d $HOME $USERNAME
|
USER computeruse
|
||||||
RUN echo "${USERNAME} ALL=(ALL) NOPASSWD: ALL" >> /etc/sudoers
|
WORKDIR $HOME
|
||||||
USER computeruse
|
|
||||||
WORKDIR $HOME
|
# setup python
|
||||||
|
RUN git clone https://github.com/pyenv/pyenv.git ~/.pyenv && \
|
||||||
# setup python
|
cd ~/.pyenv && src/configure && make -C src && cd .. && \
|
||||||
RUN git clone https://github.com/pyenv/pyenv.git ~/.pyenv && \
|
echo 'export PYENV_ROOT="$HOME/.pyenv"' >> ~/.bashrc && \
|
||||||
cd ~/.pyenv && src/configure && make -C src && cd .. && \
|
echo 'command -v pyenv >/dev/null || export PATH="$PYENV_ROOT/bin:$PATH"' >> ~/.bashrc && \
|
||||||
echo 'export PYENV_ROOT="$HOME/.pyenv"' >> ~/.bashrc && \
|
echo 'eval "$(pyenv init -)"' >> ~/.bashrc
|
||||||
echo 'command -v pyenv >/dev/null || export PATH="$PYENV_ROOT/bin:$PATH"' >> ~/.bashrc && \
|
ENV PYENV_ROOT="$HOME/.pyenv"
|
||||||
echo 'eval "$(pyenv init -)"' >> ~/.bashrc
|
ENV PATH="$PYENV_ROOT/bin:$PATH"
|
||||||
ENV PYENV_ROOT="$HOME/.pyenv"
|
ENV PYENV_VERSION_MAJOR=3
|
||||||
ENV PATH="$PYENV_ROOT/bin:$PATH"
|
ENV PYENV_VERSION_MINOR=11
|
||||||
ENV PYENV_VERSION_MAJOR=3
|
ENV PYENV_VERSION_PATCH=6
|
||||||
ENV PYENV_VERSION_MINOR=11
|
ENV PYENV_VERSION=$PYENV_VERSION_MAJOR.$PYENV_VERSION_MINOR.$PYENV_VERSION_PATCH
|
||||||
ENV PYENV_VERSION_PATCH=6
|
RUN eval "$(pyenv init -)" && \
|
||||||
ENV PYENV_VERSION=$PYENV_VERSION_MAJOR.$PYENV_VERSION_MINOR.$PYENV_VERSION_PATCH
|
pyenv install $PYENV_VERSION && \
|
||||||
RUN eval "$(pyenv init -)" && \
|
pyenv global $PYENV_VERSION && \
|
||||||
pyenv install $PYENV_VERSION && \
|
pyenv rehash
|
||||||
pyenv global $PYENV_VERSION && \
|
|
||||||
pyenv rehash
|
ENV PATH="$HOME/.pyenv/shims:$HOME/.pyenv/bin:$PATH"
|
||||||
|
|
||||||
ENV PATH="$HOME/.pyenv/shims:$HOME/.pyenv/bin:$PATH"
|
RUN python -m pip install --upgrade pip==23.1.2 setuptools==58.0.4 wheel==0.40.0 && \
|
||||||
|
python -m pip config set global.disable-pip-version-check true
|
||||||
RUN python -m pip install --upgrade pip==23.1.2 setuptools==58.0.4 wheel==0.40.0 && \
|
|
||||||
python -m pip config set global.disable-pip-version-check true
|
# only reinstall if requirements.txt changes
|
||||||
|
# COPY --chown=$USERNAME:$USERNAME computer_use_demo/requirements.txt $HOME/computer_use_demo/requirements.txt
|
||||||
# only reinstall if requirements.txt changes
|
# RUN python -m pip install -r $HOME/computer_use_demo/requirements.txt
|
||||||
# COPY --chown=$USERNAME:$USERNAME computer_use_demo/requirements.txt $HOME/computer_use_demo/requirements.txt
|
|
||||||
# RUN python -m pip install -r $HOME/computer_use_demo/requirements.txt
|
# setup desktop env & app
|
||||||
|
# COPY --chown=$USERNAME:$USERNAME image/ $HOME
|
||||||
# setup desktop env & app
|
# COPY --chown=$USERNAME:$USERNAME computer_use_demo/ $HOME/computer_use_demo/
|
||||||
# COPY --chown=$USERNAME:$USERNAME image/ $HOME
|
|
||||||
# COPY --chown=$USERNAME:$USERNAME computer_use_demo/ $HOME/computer_use_demo/
|
ARG DISPLAY_NUM=1
|
||||||
|
ARG HEIGHT=768
|
||||||
ARG DISPLAY_NUM=1
|
ARG WIDTH=1024
|
||||||
ARG HEIGHT=768
|
ENV DISPLAY_NUM=$DISPLAY_NUM
|
||||||
ARG WIDTH=1024
|
ENV HEIGHT=$HEIGHT
|
||||||
ENV DISPLAY_NUM=$DISPLAY_NUM
|
ENV WIDTH=$WIDTH
|
||||||
ENV HEIGHT=$HEIGHT
|
|
||||||
ENV WIDTH=$WIDTH
|
# Set the entrypoint
|
||||||
|
# ENTRYPOINT ["/usr/src/app/entrypoint.sh"]
|
||||||
# Set the entrypoint
|
|
||||||
# ENTRYPOINT ["/usr/src/app/entrypoint.sh"]
|
# docker build . -t omniparser-x-demo:local # manually build the docker image (optional)
|
||||||
|
|
||||||
# sudo docker build . -t omniparser-x-demo:local # manually build the docker image (optional)
|
|
||||||
|
|||||||
Binary file not shown.
878
demo.ipynb
878
demo.ipynb
File diff suppressed because one or more lines are too long
Binary file not shown.
|
Before Width: | Height: | Size: 328 KiB After Width: | Height: | Size: 560 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 404 KiB After Width: | Height: | Size: 720 KiB |
120
omniparser.py
120
omniparser.py
@@ -1,60 +1,60 @@
|
|||||||
from utils import get_som_labeled_img, check_ocr_box, get_caption_model_processor, get_dino_model, get_yolo_model
|
from utils import get_som_labeled_img, check_ocr_box, get_yolo_model
|
||||||
import torch
|
import torch
|
||||||
from ultralytics import YOLO
|
from ultralytics import YOLO
|
||||||
from PIL import Image
|
from PIL import Image
|
||||||
from typing import Dict, Tuple, List
|
from typing import Dict, Tuple, List
|
||||||
import io
|
import io
|
||||||
import base64
|
import base64
|
||||||
|
|
||||||
|
|
||||||
config = {
|
config = {
|
||||||
'som_model_path': 'finetuned_icon_detect.pt',
|
'som_model_path': 'finetuned_icon_detect.pt',
|
||||||
'device': 'cpu',
|
'device': 'cpu',
|
||||||
'caption_model_path': 'Salesforce/blip2-opt-2.7b',
|
'caption_model_path': 'Salesforce/blip2-opt-2.7b',
|
||||||
'draw_bbox_config': {
|
'draw_bbox_config': {
|
||||||
'text_scale': 0.8,
|
'text_scale': 0.8,
|
||||||
'text_thickness': 2,
|
'text_thickness': 2,
|
||||||
'text_padding': 3,
|
'text_padding': 3,
|
||||||
'thickness': 3,
|
'thickness': 3,
|
||||||
},
|
},
|
||||||
'BOX_TRESHOLD': 0.05
|
'BOX_TRESHOLD': 0.05
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
class Omniparser(object):
|
class Omniparser(object):
|
||||||
def __init__(self, config: Dict):
|
def __init__(self, config: Dict):
|
||||||
self.config = config
|
self.config = config
|
||||||
|
|
||||||
self.som_model = get_yolo_model(model_path=config['som_model_path'])
|
self.som_model = get_yolo_model(model_path=config['som_model_path'])
|
||||||
# self.caption_model_processor = get_caption_model_processor(config['caption_model_path'], device=cofig['device'])
|
# self.caption_model_processor = get_caption_model_processor(config['caption_model_path'], device=cofig['device'])
|
||||||
# self.caption_model_processor['model'].to(torch.float32)
|
# self.caption_model_processor['model'].to(torch.float32)
|
||||||
|
|
||||||
def parse(self, image_path: str):
|
def parse(self, image_path: str):
|
||||||
print('Parsing image:', image_path)
|
print('Parsing image:', image_path)
|
||||||
ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9})
|
ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9})
|
||||||
text, ocr_bbox = ocr_bbox_rslt
|
text, ocr_bbox = ocr_bbox_rslt
|
||||||
|
|
||||||
draw_bbox_config = self.config['draw_bbox_config']
|
draw_bbox_config = self.config['draw_bbox_config']
|
||||||
BOX_TRESHOLD = self.config['BOX_TRESHOLD']
|
BOX_TRESHOLD = self.config['BOX_TRESHOLD']
|
||||||
dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_path, self.som_model, BOX_TRESHOLD = BOX_TRESHOLD, output_coord_in_ratio=False, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=None, ocr_text=text,use_local_semantics=False)
|
dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_path, self.som_model, BOX_TRESHOLD = BOX_TRESHOLD, output_coord_in_ratio=False, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=None, ocr_text=text,use_local_semantics=False)
|
||||||
|
|
||||||
image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
|
image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
|
||||||
# formating output
|
# formating output
|
||||||
return_list = [{'from': 'omniparser', 'shape': {'x':coord[0], 'y':coord[1], 'width':coord[2], 'height':coord[3]},
|
return_list = [{'from': 'omniparser', 'shape': {'x':coord[0], 'y':coord[1], 'width':coord[2], 'height':coord[3]},
|
||||||
'text': parsed_content_list[i].split(': ')[1], 'type':'text'} for i, (k, coord) in enumerate(label_coordinates.items()) if i < len(parsed_content_list)]
|
'text': parsed_content_list[i].split(': ')[1], 'type':'text'} for i, (k, coord) in enumerate(label_coordinates.items()) if i < len(parsed_content_list)]
|
||||||
return_list.extend(
|
return_list.extend(
|
||||||
[{'from': 'omniparser', 'shape': {'x':coord[0], 'y':coord[1], 'width':coord[2], 'height':coord[3]},
|
[{'from': 'omniparser', 'shape': {'x':coord[0], 'y':coord[1], 'width':coord[2], 'height':coord[3]},
|
||||||
'text': 'None', 'type':'icon'} for i, (k, coord) in enumerate(label_coordinates.items()) if i >= len(parsed_content_list)]
|
'text': 'None', 'type':'icon'} for i, (k, coord) in enumerate(label_coordinates.items()) if i >= len(parsed_content_list)]
|
||||||
)
|
)
|
||||||
|
|
||||||
return [image, return_list]
|
return [image, return_list]
|
||||||
|
|
||||||
parser = Omniparser(config)
|
parser = Omniparser(config)
|
||||||
image_path = 'examples/pc_1.png'
|
image_path = 'examples/pc_1.png'
|
||||||
|
|
||||||
# time the parser
|
# time the parser
|
||||||
import time
|
import time
|
||||||
s = time.time()
|
s = time.time()
|
||||||
image, parsed_content_list = parser.parse(image_path)
|
image, parsed_content_list = parser.parse(image_path)
|
||||||
device = config['device']
|
device = config['device']
|
||||||
print(f'Time taken for Omniparser on {device}:', time.time() - s)
|
print(f'Time taken for Omniparser on {device}:', time.time() - s)
|
||||||
|
|||||||
Reference in New Issue
Block a user