commit message

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 80
+extend-ignore = E203,E501,E402
+exclude = .git,__pycache__,build,.venv/,third_party

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,28 @@
+build/
+# lib
+bin/
+cmake_modules/
+cmake-build-debug/
+.idea/
+.vscode/
+*.pyc
+flagged
+.ipynb_checkpoints
+__pycache__
+Untitled*
+experiments
+third_party/REKD
+hloc/matchers/dedode.py
+gradio_cached_examples
+*.mp4
+hloc/matchers/quadtree.py
+third_party/QuadTreeAttention
+desktop.ini
+*.egg-info
+output.pkl
+log.txt
+experiments*
+gen_example.py
+datasets/lines/terrace0.JPG
+datasets/lines/terrace1.JPG
+datasets/South-Building*

Dockerfile

@@ -0,0 +1,27 @@
+# Use an official conda-based Python image as a parent image
+FROM pytorch/pytorch:2.4.0-cuda12.1-cudnn9-runtime
+LABEL maintainer vincentqyw
+ARG PYTHON_VERSION=3.10.10
+
+# Set the working directory to /code
+WORKDIR /code
+
+# Install Git and Git LFS
+RUN apt-get update && apt-get install -y git-lfs
+RUN git lfs install
+
+# Clone the Git repository
+RUN git clone https://huggingface.co/spaces/Realcat/image-matching-webui /code
+
+RUN conda create -n imw python=${PYTHON_VERSION}
+RUN echo "source activate imw" > ~/.bashrc
+ENV PATH /opt/conda/envs/imw/bin:$PATH
+
+# Make RUN commands use the new environment
+SHELL ["conda", "run", "-n", "imw", "/bin/bash", "-c"]
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+RUN apt-get update && apt-get install ffmpeg libsm6 libxext6 -y
+
+# Export port
+EXPOSE 7860

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,13 @@
+---
+title: MINIMA
+emoji: 📈
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: 5.9.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

api/__init__.py

@@ -0,0 +1,42 @@
+import sys
+from typing import List
+from pydantic import BaseModel
+import base64
+import io
+import numpy as np
+from fastapi.exceptions import HTTPException
+from PIL import Image
+from pathlib import Path
+
+sys.path.append(str(Path(__file__).parents[1]))
+from hloc import logger
+
+
+class ImagesInput(BaseModel):
+    data: List[str] = []
+    max_keypoints: List[int] = []
+    timestamps: List[str] = []
+    grayscale: bool = False
+    image_hw: List[List[int]] = [[], []]
+    feature_type: int = 0
+    rotates: List[float] = []
+    scales: List[float] = []
+    reference_points: List[List[float]] = []
+    binarize: bool = False
+
+
+def decode_base64_to_image(encoding):
+    if encoding.startswith("data:image/"):
+        encoding = encoding.split(";")[1].split(",")[1]
+    try:
+        image = Image.open(io.BytesIO(base64.b64decode(encoding)))
+        return image
+    except Exception as e:
+        logger.warning(f"API cannot decode image: {e}")
+        raise HTTPException(
+            status_code=500, detail="Invalid encoded image"
+        ) from e
+
+
+def to_base64_nparray(encoding: str) -> np.ndarray:
+    return np.array(decode_base64_to_image(encoding)).astype("uint8")

api/client.py

@@ -0,0 +1,218 @@
+import argparse
+import base64
+import os
+import pickle
+import time
+from typing import Dict, List
+
+import cv2
+import numpy as np
+import requests
+
+ENDPOINT = "http://127.0.0.1:8000"
+if "REMOTE_URL_RAILWAY" in os.environ:
+    ENDPOINT = os.environ["REMOTE_URL_RAILWAY"]
+
+print(f"API ENDPOINT: {ENDPOINT}")
+
+API_VERSION = f"{ENDPOINT}/version"
+API_URL_MATCH = f"{ENDPOINT}/v1/match"
+API_URL_EXTRACT = f"{ENDPOINT}/v1/extract"
+
+
+def read_image(path: str) -> str:
+    """
+    Read an image from a file, encode it as a JPEG and then as a base64 string.
+    Args:
+        path (str): The path to the image to read.
+    Returns:
+        str: The base64 encoded image.
+    """
+    # Read the image from the file
+    img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
+
+    # Encode the image as a png, NO COMPRESSION!!!
+    retval, buffer = cv2.imencode(".png", img)
+
+    # Encode the JPEG as a base64 string
+    b64img = base64.b64encode(buffer).decode("utf-8")
+
+    return b64img
+
+
+def do_api_requests(url=API_URL_EXTRACT, **kwargs):
+    """
+    Helper function to send an API request to the image matching service.
+    Args:
+        url (str): The URL of the API endpoint to use. Defaults to the
+            feature extraction endpoint.
+        **kwargs: Additional keyword arguments to pass to the API.
+    Returns:
+        List[Dict[str, np.ndarray]]: A list of dictionaries containing the
+            extracted features. The keys are "keypoints", "descriptors", and
+            "scores", and the values are ndarrays of shape (N, 2), (N, ?),
+            and (N,), respectively.
+    """
+    # Set up the request body
+    reqbody = {
+        # List of image data base64 encoded
+        "data": [],
+        # List of maximum number of keypoints to extract from each image
+        "max_keypoints": [100, 100],
+        # List of timestamps for each image (not used?)
+        "timestamps": ["0", "1"],
+        # Whether to convert the images to grayscale
+        "grayscale": 0,
+        # List of image height and width
+        "image_hw": [[640, 480], [320, 240]],
+        # Type of feature to extract
+        "feature_type": 0,
+        # List of rotation angles for each image
+        "rotates": [0.0, 0.0],
+        # List of scale factors for each image
+        "scales": [1.0, 1.0],
+        # List of reference points for each image (not used)
+        "reference_points": [[640, 480], [320, 240]],
+        # Whether to binarize the descriptors
+        "binarize": True,
+    }
+    # Update the request body with the additional keyword arguments
+    reqbody.update(kwargs)
+    try:
+        # Send the request
+        r = requests.post(url, json=reqbody)
+        if r.status_code == 200:
+            # Return the response
+            return r.json()
+        else:
+            # Print an error message if the response code is not 200
+            print(f"Error: Response code {r.status_code} - {r.text}")
+    except Exception as e:
+        # Print an error message if an exception occurs
+        print(f"An error occurred: {e}")
+
+
+def send_request_match(path0: str, path1: str) -> Dict[str, np.ndarray]:
+    """
+    Send a request to the API to generate a match between two images.
+    Args:
+        path0 (str): The path to the first image.
+        path1 (str): The path to the second image.
+    Returns:
+        Dict[str, np.ndarray]: A dictionary containing the generated matches.
+            The keys are "keypoints0", "keypoints1", "matches0", and "matches1",
+            and the values are ndarrays of shape (N, 2), (N, 2), (N, 2), and
+            (N, 2), respectively.
+    """
+    files = {"image0": open(path0, "rb"), "image1": open(path1, "rb")}
+    try:
+        # TODO: replace files with post json
+        response = requests.post(API_URL_MATCH, files=files)
+        pred = {}
+        if response.status_code == 200:
+            pred = response.json()
+            for key in list(pred.keys()):
+                pred[key] = np.array(pred[key])
+        else:
+            print(
+                f"Error: Response code {response.status_code} - {response.text}"
+            )
+    finally:
+        files["image0"].close()
+        files["image1"].close()
+    return pred
+
+
+def send_request_extract(
+    input_images: str, viz: bool = False
+) -> List[Dict[str, np.ndarray]]:
+    """
+    Send a request to the API to extract features from an image.
+    Args:
+        input_images (str): The path to the image.
+    Returns:
+        List[Dict[str, np.ndarray]]: A list of dictionaries containing the
+            extracted features. The keys are "keypoints", "descriptors", and
+            "scores", and the values are ndarrays of shape (N, 2), (N, 128),
+            and (N,), respectively.
+    """
+    image_data = read_image(input_images)
+    inputs = {
+        "data": [image_data],
+    }
+    response = do_api_requests(
+        url=API_URL_EXTRACT,
+        **inputs,
+    )
+    # breakpoint()
+    # print("Keypoints detected: {}".format(len(response[0]["keypoints"])))
+
+    # draw matching, debug only
+    if viz:
+        from hloc.utils.viz import plot_keypoints
+        from ui.viz import fig2im, plot_images
+
+        kpts = np.array(response[0]["keypoints_orig"])
+        if "image_orig" in response[0].keys():
+            img_orig = np.array(["image_orig"])
+
+            output_keypoints = plot_images([img_orig], titles="titles", dpi=300)
+            plot_keypoints([kpts])
+            output_keypoints = fig2im(output_keypoints)
+            cv2.imwrite(
+                "demo_match.jpg",
+                output_keypoints[:, :, ::-1].copy(),  # RGB -> BGR
+            )
+    return response
+
+
+def get_api_version():
+    try:
+        response = requests.get(API_VERSION).json()
+        print("API VERSION: {}".format(response["version"]))
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Send text to stable audio server and receive generated audio."
+    )
+    parser.add_argument(
+        "--image0",
+        required=False,
+        help="Path for the file's melody",
+        default="datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg",
+    )
+    parser.add_argument(
+        "--image1",
+        required=False,
+        help="Path for the file's melody",
+        default="datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot90.jpg",
+    )
+    args = parser.parse_args()
+
+    # get api version
+    get_api_version()
+
+    # request match
+    # for i in range(10):
+    #     t1 = time.time()
+    #     preds = send_request_match(args.image0, args.image1)
+    #     t2 = time.time()
+    #     print(
+    #         "Time cost1: {} seconds, matched: {}".format(
+    #             (t2 - t1), len(preds["mmkeypoints0_orig"])
+    #         )
+    #     )
+
+    # request extract
+    for i in range(1000):
+        t1 = time.time()
+        preds = send_request_extract(args.image0)
+        t2 = time.time()
+        print(f"Time cost2: {(t2 - t1)} seconds")
+
+    # dump preds
+    with open("preds.pkl", "wb") as f:
+        pickle.dump(preds, f)

api/config/api.yaml

@@ -0,0 +1,51 @@
+# This file was generated using the `serve build` command on Ray v2.38.0.
+
+proxy_location: EveryNode
+http_options:
+  host: 0.0.0.0
+  port: 8000
+
+grpc_options:
+  port: 9000
+  grpc_servicer_functions: []
+
+logging_config:
+  encoding: TEXT
+  log_level: INFO
+  logs_dir: null
+  enable_access_log: true
+
+applications:
+- name: app1
+  route_prefix: /
+  import_path: api.server:service
+  runtime_env: {}
+  deployments:
+  - name: ImageMatchingService
+    num_replicas: 4
+    ray_actor_options:
+      num_cpus: 2.0
+      num_gpus: 1.0
+
+api:
+  feature:
+    output: feats-superpoint-n4096-rmax1600
+    model:
+      name: superpoint
+      nms_radius: 3
+      max_keypoints: 4096
+      keypoint_threshold: 0.005
+    preprocessing:
+      grayscale: True
+      force_resize: True
+      resize_max: 1600
+      width: 640
+      height: 480
+      dfactor: 8
+  matcher:
+    output: matches-NN-mutual
+    model:
+      name: nearest_neighbor
+      do_mutual_check: True
+      match_threshold: 0.2
+  dense: False

api/server.py

@@ -0,0 +1,472 @@
+# server.py
+import warnings
+from pathlib import Path
+from typing import Any, Dict, Optional, Union
+import yaml
+
+import ray
+from ray import serve
+
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+import torch
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import JSONResponse
+from PIL import Image
+
+from api import ImagesInput, to_base64_nparray
+from hloc import DEVICE, extract_features, logger, match_dense, match_features
+from hloc.utils.viz import add_text, plot_keypoints
+from ui import get_version
+from ui.utils import filter_matches, get_feature_model, get_model
+from ui.viz import display_matches, fig2im, plot_images
+
+warnings.simplefilter("ignore")
+app = FastAPI()
+if ray.is_initialized():
+    ray.shutdown()
+ray.init(
+    dashboard_port=8265,
+    ignore_reinit_error=True,
+)
+serve.start(
+    http_options={"host": "0.0.0.0", "port": 8000},
+)
+
+
+class ImageMatchingAPI(torch.nn.Module):
+    default_conf = {
+        "ransac": {
+            "enable": True,
+            "estimator": "poselib",
+            "geometry": "Fundamental",
+            "method": "RANSAC",
+            "reproj_threshold": 8,
+            "confidence": 0.99999,
+            "max_iter": 2000,
+        },
+    }
+
+    def __init__(
+        self,
+        conf: dict = {},
+        device: str = "cpu",
+        detect_threshold: float = 0.015,
+        max_keypoints: int = 1024,
+        match_threshold: float = 0.2,
+    ) -> None:
+        """
+        Initializes an instance of the ImageMatchingAPI class.
+        Args:
+            conf (dict): A dictionary containing the configuration parameters.
+            device (str, optional): The device to use for computation. Defaults to "cpu".
+            detect_threshold (float, optional): The threshold for detecting keypoints. Defaults to 0.015.
+            max_keypoints (int, optional): The maximum number of keypoints to extract. Defaults to 1024.
+            match_threshold (float, optional): The threshold for matching keypoints. Defaults to 0.2.
+        Returns:
+            None
+        """
+        super().__init__()
+        self.device = device
+        self.conf = {**self.default_conf, **conf}
+        self._updata_config(detect_threshold, max_keypoints, match_threshold)
+        self._init_models()
+        if device == "cuda":
+            memory_allocated = torch.cuda.memory_allocated(device)
+            memory_reserved = torch.cuda.memory_reserved(device)
+            logger.info(
+                f"GPU memory allocated: {memory_allocated / 1024**2:.3f} MB"
+            )
+            logger.info(
+                f"GPU memory reserved: {memory_reserved / 1024**2:.3f} MB"
+            )
+        self.pred = None
+
+    def parse_match_config(self, conf):
+        if conf["dense"]:
+            return {
+                **conf,
+                "matcher": match_dense.confs.get(
+                    conf["matcher"]["model"]["name"]
+                ),
+                "dense": True,
+            }
+        else:
+            return {
+                **conf,
+                "feature": extract_features.confs.get(
+                    conf["feature"]["model"]["name"]
+                ),
+                "matcher": match_features.confs.get(
+                    conf["matcher"]["model"]["name"]
+                ),
+                "dense": False,
+            }
+
+    def _updata_config(
+        self,
+        detect_threshold: float = 0.015,
+        max_keypoints: int = 1024,
+        match_threshold: float = 0.2,
+    ):
+        self.dense = self.conf["dense"]
+        if self.conf["dense"]:
+            try:
+                self.conf["matcher"]["model"][
+                    "match_threshold"
+                ] = match_threshold
+            except TypeError as e:
+                logger.error(e)
+        else:
+            self.conf["feature"]["model"]["max_keypoints"] = max_keypoints
+            self.conf["feature"]["model"][
+                "keypoint_threshold"
+            ] = detect_threshold
+            self.extract_conf = self.conf["feature"]
+
+        self.match_conf = self.conf["matcher"]
+
+    def _init_models(self):
+        # initialize matcher
+        self.matcher = get_model(self.match_conf)
+        # initialize extractor
+        if self.dense:
+            self.extractor = None
+        else:
+            self.extractor = get_feature_model(self.conf["feature"])
+
+    def _forward(self, img0, img1):
+        if self.dense:
+            pred = match_dense.match_images(
+                self.matcher,
+                img0,
+                img1,
+                self.match_conf["preprocessing"],
+                device=self.device,
+            )
+            last_fixed = "{}".format(  # noqa: F841
+                self.match_conf["model"]["name"]
+            )
+        else:
+            pred0 = extract_features.extract(
+                self.extractor, img0, self.extract_conf["preprocessing"]
+            )
+            pred1 = extract_features.extract(
+                self.extractor, img1, self.extract_conf["preprocessing"]
+            )
+            pred = match_features.match_images(self.matcher, pred0, pred1)
+        return pred
+
+    def _convert_pred(self, pred):
+        ret = {
+            k: v.cpu().detach()[0].numpy() if isinstance(v, torch.Tensor) else v
+            for k, v in pred.items()
+        }
+        ret = {
+            k: v[0].cpu().detach().numpy() if isinstance(v, list) else v
+            for k, v in ret.items()
+        }
+        return ret
+
+    @torch.inference_mode()
+    def extract(self, img0: np.ndarray, **kwargs) -> Dict[str, np.ndarray]:
+        """Extract features from a single image.
+        Args:
+            img0 (np.ndarray): image
+        Returns:
+            Dict[str, np.ndarray]: feature dict
+        """
+
+        # setting prams
+        self.extractor.conf["max_keypoints"] = kwargs.get("max_keypoints", 512)
+        self.extractor.conf["keypoint_threshold"] = kwargs.get(
+            "keypoint_threshold", 0.0
+        )
+
+        pred = extract_features.extract(
+            self.extractor, img0, self.extract_conf["preprocessing"]
+        )
+        pred = self._convert_pred(pred)
+        # back to origin scale
+        s0 = pred["original_size"] / pred["size"]
+        pred["keypoints_orig"] = (
+            match_features.scale_keypoints(pred["keypoints"] + 0.5, s0) - 0.5
+        )
+        # TODO: rotate back
+        binarize = kwargs.get("binarize", False)
+        if binarize:
+            assert "descriptors" in pred
+            pred["descriptors"] = (pred["descriptors"] > 0).astype(np.uint8)
+            pred["descriptors"] = pred["descriptors"].T  # N x DIM
+        return pred
+
+    @torch.inference_mode()
+    def forward(
+        self,
+        img0: np.ndarray,
+        img1: np.ndarray,
+    ) -> Dict[str, np.ndarray]:
+        """
+        Forward pass of the image matching API.
+        Args:
+            img0: A 3D NumPy array of shape (H, W, C) representing the first image.
+                  Values are in the range [0, 1] and are in RGB mode.
+            img1: A 3D NumPy array of shape (H, W, C) representing the second image.
+                  Values are in the range [0, 1] and are in RGB mode.
+        Returns:
+            A dictionary containing the following keys:
+            - image0_orig: The original image 0.
+            - image1_orig: The original image 1.
+            - keypoints0_orig: The keypoints detected in image 0.
+            - keypoints1_orig: The keypoints detected in image 1.
+            - mkeypoints0_orig: The raw matches between image 0 and image 1.
+            - mkeypoints1_orig: The raw matches between image 1 and image 0.
+            - mmkeypoints0_orig: The RANSAC inliers in image 0.
+            - mmkeypoints1_orig: The RANSAC inliers in image 1.
+            - mconf: The confidence scores for the raw matches.
+            - mmconf: The confidence scores for the RANSAC inliers.
+        """
+        # Take as input a pair of images (not a batch)
+        assert isinstance(img0, np.ndarray)
+        assert isinstance(img1, np.ndarray)
+        self.pred = self._forward(img0, img1)
+        if self.conf["ransac"]["enable"]:
+            self.pred = self._geometry_check(self.pred)
+        return self.pred
+
+    def _geometry_check(
+        self,
+        pred: Dict[str, Any],
+    ) -> Dict[str, Any]:
+        """
+        Filter matches using RANSAC. If keypoints are available, filter by keypoints.
+        If lines are available, filter by lines. If both keypoints and lines are
+        available, filter by keypoints.
+        Args:
+            pred (Dict[str, Any]): dict of matches, including original keypoints.
+                                  See :func:`filter_matches` for the expected keys.
+        Returns:
+            Dict[str, Any]: filtered matches
+        """
+        pred = filter_matches(
+            pred,
+            ransac_method=self.conf["ransac"]["method"],
+            ransac_reproj_threshold=self.conf["ransac"]["reproj_threshold"],
+            ransac_confidence=self.conf["ransac"]["confidence"],
+            ransac_max_iter=self.conf["ransac"]["max_iter"],
+        )
+        return pred
+
+    def visualize(
+        self,
+        log_path: Optional[Path] = None,
+    ) -> None:
+        """
+        Visualize the matches.
+        Args:
+            log_path (Path, optional): The directory to save the images. Defaults to None.
+        Returns:
+            None
+        """
+        if self.conf["dense"]:
+            postfix = str(self.conf["matcher"]["model"]["name"])
+        else:
+            postfix = "{}_{}".format(
+                str(self.conf["feature"]["model"]["name"]),
+                str(self.conf["matcher"]["model"]["name"]),
+            )
+        titles = [
+            "Image 0 - Keypoints",
+            "Image 1 - Keypoints",
+        ]
+        pred: Dict[str, Any] = self.pred
+        image0: np.ndarray = pred["image0_orig"]
+        image1: np.ndarray = pred["image1_orig"]
+        output_keypoints: np.ndarray = plot_images(
+            [image0, image1], titles=titles, dpi=300
+        )
+        if (
+            "keypoints0_orig" in pred.keys()
+            and "keypoints1_orig" in pred.keys()
+        ):
+            plot_keypoints([pred["keypoints0_orig"], pred["keypoints1_orig"]])
+            text: str = (
+                f"# keypoints0: {len(pred['keypoints0_orig'])} \n"
+                + f"# keypoints1: {len(pred['keypoints1_orig'])}"
+            )
+            add_text(0, text, fs=15)
+        output_keypoints = fig2im(output_keypoints)
+        # plot images with raw matches
+        titles = [
+            "Image 0 - Raw matched keypoints",
+            "Image 1 - Raw matched keypoints",
+        ]
+        output_matches_raw, num_matches_raw = display_matches(
+            pred, titles=titles, tag="KPTS_RAW"
+        )
+        # plot images with ransac matches
+        titles = [
+            "Image 0 - Ransac matched keypoints",
+            "Image 1 - Ransac matched keypoints",
+        ]
+        output_matches_ransac, num_matches_ransac = display_matches(
+            pred, titles=titles, tag="KPTS_RANSAC"
+        )
+        if log_path is not None:
+            img_keypoints_path: Path = log_path / f"img_keypoints_{postfix}.png"
+            img_matches_raw_path: Path = (
+                log_path / f"img_matches_raw_{postfix}.png"
+            )
+            img_matches_ransac_path: Path = (
+                log_path / f"img_matches_ransac_{postfix}.png"
+            )
+            cv2.imwrite(
+                str(img_keypoints_path),
+                output_keypoints[:, :, ::-1].copy(),  # RGB -> BGR
+            )
+            cv2.imwrite(
+                str(img_matches_raw_path),
+                output_matches_raw[:, :, ::-1].copy(),  # RGB -> BGR
+            )
+            cv2.imwrite(
+                str(img_matches_ransac_path),
+                output_matches_ransac[:, :, ::-1].copy(),  # RGB -> BGR
+            )
+            plt.close("all")
+
+
+@serve.deployment(
+    num_replicas=4,
+    ray_actor_options={"num_cpus": 2, "num_gpus": 1}
+)
+@serve.ingress(app)
+class ImageMatchingService:
+    def __init__(self, conf: dict, device: str):
+        self.conf = conf
+        self.api = ImageMatchingAPI(conf=conf, device=device)
+
+    @app.get("/")
+    def root(self):
+        return "Hello, world!"
+
+    @app.get("/version")
+    async def version(self):
+        return {"version": get_version()}
+
+    @app.post("/v1/match")
+    async def match(
+        self, image0: UploadFile = File(...), image1: UploadFile = File(...)
+    ):
+        """
+        Handle the image matching request and return the processed result.
+        Args:
+            image0 (UploadFile): The first image file for matching.
+            image1 (UploadFile): The second image file for matching.
+        Returns:
+            JSONResponse: A JSON response containing the filtered match results
+                            or an error message in case of failure.
+        """
+        try:
+            # Load the images from the uploaded files
+            image0_array = self.load_image(image0)
+            image1_array = self.load_image(image1)
+            print('image0_array',image0_array.shape)
+            print('image1_array',image1_array.shape)
+
+            # Perform image matching using the API
+            output = self.api(image0_array, image1_array)
+
+            # Keys to skip in the output
+            skip_keys = ["image0_orig", "image1_orig"]
+
+            # Postprocess the output to filter unwanted data
+            pred = self.postprocess(output, skip_keys)
+
+            # Return the filtered prediction as a JSON response
+            return JSONResponse(content=pred)
+        except Exception as e:
+            # Return an error message with status code 500 in case of exception
+            return JSONResponse(content={"error": str(e)}, status_code=500)
+
+    @app.post("/v1/extract")
+    async def extract(self, input_info: ImagesInput):
+        """
+        Extract keypoints and descriptors from images.
+        Args:
+            input_info: An object containing the image data and options.
+        Returns:
+            A list of dictionaries containing the keypoints and descriptors.
+        """
+        try:
+            preds = []
+            for i, input_image in enumerate(input_info.data):
+                # Load the image from the input data
+                image_array = to_base64_nparray(input_image)
+                # Extract keypoints and descriptors
+                output = self.api.extract(
+                    image_array,
+                    max_keypoints=input_info.max_keypoints[i],
+                    binarize=input_info.binarize,
+                )
+                # Do not return the original image and image_orig
+                # skip_keys = ["image", "image_orig"]
+                skip_keys = []
+
+                # Postprocess the output
+                pred = self.postprocess(output, skip_keys)
+                preds.append(pred)
+            # Return the list of extracted features
+            return JSONResponse(content=preds)
+        except Exception as e:
+            # Return an error message if an exception occurs
+            return JSONResponse(content={"error": str(e)}, status_code=500)
+
+    def load_image(self, file_path: Union[str, UploadFile]) -> np.ndarray:
+        """
+        Reads an image from a file path or an UploadFile object.
+        Args:
+            file_path: A file path or an UploadFile object.
+        Returns:
+            A numpy array representing the image.
+        """
+        if isinstance(file_path, str):
+            file_path = Path(file_path).resolve(strict=False)
+        else:
+            file_path = file_path.file
+        with Image.open(file_path) as img:
+            image_array = np.array(img)
+        return image_array
+
+    def postprocess(
+        self, output: dict, skip_keys: list, binarize: bool = True
+    ) -> dict:
+        pred = {}
+        for key, value in output.items():
+            if key in skip_keys:
+                continue
+            if isinstance(value, np.ndarray):
+                pred[key] = value.tolist()
+        return pred
+
+    def run(self, host: str = "0.0.0.0", port: int = 8001):
+        import uvicorn
+        uvicorn.run(app, host=host, port=port)
+
+
+def read_config(config_path: Path) -> dict:
+    with open(config_path, "r") as f:
+        conf = yaml.safe_load(f)
+    return conf
+
+
+# api server
+conf = read_config(Path(__file__).parent / "config/api.yaml")
+service = ImageMatchingService.bind(conf=conf["api"], device=DEVICE)
+
+# handle = serve.run(service, route_prefix="/")
+# serve run api.server_ray:service
+
+# build to generate config file
+# serve build api.server_ray:service -o api/config/ray.yaml
+# serve run api/config/ray.yaml

api/test/CMakeLists.txt

@@ -0,0 +1,16 @@
+cmake_minimum_required(VERSION 3.10)
+project(imatchui)
+
+set(OpenCV_DIR /usr/include/opencv4)
+find_package(OpenCV REQUIRED)
+
+find_package(Boost REQUIRED COMPONENTS system)
+if(Boost_FOUND)
+    include_directories(${Boost_INCLUDE_DIRS})
+endif()
+
+add_executable(client client.cpp)
+
+target_include_directories(client PRIVATE ${Boost_LIBRARIES} ${OpenCV_INCLUDE_DIRS})
+
+target_link_libraries(client PRIVATE curl jsoncpp b64 ${OpenCV_LIBS})

api/test/build_and_run.sh

@@ -0,0 +1,16 @@
+# g++ main.cpp -I/usr/include/opencv4 -lcurl -ljsoncpp -lb64 -lopencv_core -lopencv_imgcodecs -o main
+# sudo apt-get update
+# sudo apt-get install libboost-all-dev -y
+# sudo apt-get install libcurl4-openssl-dev libjsoncpp-dev libb64-dev libopencv-dev -y
+
+cd build
+cmake ..
+make -j12
+
+echo " ======== RUN DEMO ========"
+
+./client
+
+echo " ======== END DEMO ========"
+
+cd ..

api/test/client.cpp

@@ -0,0 +1,84 @@
+#include <curl/curl.h>
+#include <opencv2/opencv.hpp>
+#include "helper.h"
+
+int main() {
+    std::string img_path = "../../../datasets/sacre_coeur/mapping_rot/02928139_3448003521_rot45.jpg";
+    cv::Mat original_img = cv::imread(img_path, cv::IMREAD_GRAYSCALE);
+
+    if (original_img.empty()) {
+        throw std::runtime_error("Failed to decode image");
+    }
+
+    // Convert the image to Base64
+    std::string base64_img = image_to_base64(original_img);
+
+    // Convert the Base64 back to an image
+    cv::Mat decoded_img = base64_to_image(base64_img);
+    cv::imwrite("decoded_image.jpg", decoded_img);
+    cv::imwrite("original_img.jpg", original_img);
+
+    // The images should be identical
+    if (cv::countNonZero(original_img != decoded_img) != 0) {
+        std::cerr << "The images are not identical" << std::endl;
+        return -1;
+    } else {
+        std::cout << "The images are identical!" << std::endl;
+    }
+
+    // construct params
+    APIParams params{
+        .data = {base64_img},
+        .max_keypoints = {100, 100},
+        .timestamps = {"0", "1"},
+        .grayscale = {0},
+        .image_hw = {{480, 640}, {240, 320}},
+        .feature_type = 0,
+        .rotates = {0.0f, 0.0f},
+        .scales = {1.0f, 1.0f},
+        .reference_points = {
+            {1.23e+2f, 1.2e+1f},
+            {5.0e-1f, 3.0e-1f},
+            {2.3e+2f, 2.2e+1f},
+            {6.0e-1f, 4.0e-1f}
+        },
+        .binarize = {1}
+    };
+
+    KeyPointResults kpts_results;
+
+    // Convert the parameters to JSON
+    Json::Value jsonData = paramsToJson(params);
+    std::string url = "http://127.0.0.1:8001/v1/extract";
+    Json::StreamWriterBuilder writer;
+    std::string output = Json::writeString(writer, jsonData);
+
+    CURL* curl;
+    CURLcode res;
+    std::string readBuffer;
+
+    curl_global_init(CURL_GLOBAL_DEFAULT);
+    curl = curl_easy_init();
+    if (curl) {
+        struct curl_slist* hs = NULL;
+        hs = curl_slist_append(hs, "Content-Type: application/json");
+        curl_easy_setopt(curl, CURLOPT_HTTPHEADER, hs);
+        curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
+        curl_easy_setopt(curl, CURLOPT_POSTFIELDS, output.c_str());
+        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, WriteCallback);
+        curl_easy_setopt(curl, CURLOPT_WRITEDATA, &readBuffer);
+        res = curl_easy_perform(curl);
+
+        if (res != CURLE_OK)
+            fprintf(stderr, "curl_easy_perform() failed: %s\n",
+                    curl_easy_strerror(res));
+        else {
+            // std::cout << "Response from server: " << readBuffer << std::endl;
+           kpts_results =  decode_response(readBuffer);
+        }
+        curl_easy_cleanup(curl);
+    }
+    curl_global_cleanup();
+
+    return 0;
+}

api/test/helper.h

@@ -0,0 +1,410 @@
+
+#include <sstream>
+#include <fstream>
+#include <vector>
+#include <b64/encode.h>
+#include <jsoncpp/json/json.h>
+#include <opencv2/opencv.hpp>
+
+// base64 to image
+#include <boost/archive/iterators/binary_from_base64.hpp>
+#include <boost/archive/iterators/transform_width.hpp>
+#include <boost/archive/iterators/base64_from_binary.hpp>
+
+/// Parameters used in the API
+struct APIParams {
+    /// A list of images, base64 encoded
+    std::vector<std::string> data;
+
+    /// The maximum number of keypoints to detect for each image
+    std::vector<int> max_keypoints;
+
+    /// The timestamps of the images
+    std::vector<std::string> timestamps;
+
+    /// Whether to convert the images to grayscale
+    bool grayscale;
+
+    /// The height and width of each image
+    std::vector<std::vector<int>> image_hw;
+
+    /// The type of feature detector to use
+    int feature_type;
+
+    /// The rotations of the images
+    std::vector<double> rotates;
+
+    /// The scales of the images
+    std::vector<double> scales;
+
+    /// The reference points of the images
+    std::vector<std::vector<float>> reference_points;
+
+    /// Whether to binarize the descriptors
+    bool binarize;
+};
+
+/**
+ * @brief Contains the results of a keypoint detector.
+ *
+ * @details Stores the keypoints and descriptors for each image.
+ */
+class KeyPointResults {
+public:
+    KeyPointResults() {}
+
+    /**
+     * @brief Constructor.
+     *
+     * @param kp The keypoints for each image.
+     */
+    KeyPointResults(const std::vector<std::vector<cv::KeyPoint>>& kp, 
+                    const std::vector<cv::Mat>& desc)
+        : keypoints(kp), descriptors(desc) {}
+
+    /**
+     * @brief Append keypoints to the result.
+     *
+     * @param kpts The keypoints to append.
+     */
+    inline void append_keypoints(std::vector<cv::KeyPoint>& kpts) {
+        keypoints.emplace_back(kpts);
+    }
+
+    /**
+     * @brief Append descriptors to the result.
+     *
+     * @param desc The descriptors to append.
+     */
+    inline void append_descriptors(cv::Mat& desc) {
+        descriptors.emplace_back(desc);
+    }
+
+    /**
+     * @brief Get the keypoints.
+     *
+     * @return The keypoints.
+     */
+    inline std::vector<std::vector<cv::KeyPoint>> get_keypoints() {
+        return keypoints;
+    }
+
+    /**
+     * @brief Get the descriptors.
+     *
+     * @return The descriptors.
+     */
+    inline std::vector<cv::Mat> get_descriptors() {
+        return descriptors;
+    }
+
+private:
+    std::vector<std::vector<cv::KeyPoint>> keypoints;
+    std::vector<cv::Mat> descriptors;
+    std::vector<std::vector<float>> scores;
+};
+
+
+/**
+ * @brief Decodes a base64 encoded string.
+ *
+ * @param base64 The base64 encoded string to decode.
+ * @return The decoded string.
+ */
+std::string base64_decode(const std::string& base64) {
+    using namespace boost::archive::iterators;
+    using It = transform_width<binary_from_base64<std::string::const_iterator>, 8, 6>;
+
+    // Find the position of the last non-whitespace character
+    auto end = base64.find_last_not_of(" \t\n\r");
+    if (end != std::string::npos) {
+        // Move one past the last non-whitespace character
+        end += 1;
+    }
+
+    // Decode the base64 string and return the result
+    return std::string(It(base64.begin()), It(base64.begin() + end));
+}
+
+
+
+/**
+ * @brief Decodes a base64 string into an OpenCV image
+ *
+ * @param base64 The base64 encoded string
+ * @return The decoded OpenCV image
+ */
+cv::Mat base64_to_image(const std::string& base64) {
+    // Decode the base64 string
+    std::string decodedStr = base64_decode(base64);
+
+    // Decode the image
+    std::vector<uchar> data(decodedStr.begin(), decodedStr.end());
+    cv::Mat img = cv::imdecode(data, cv::IMREAD_GRAYSCALE);
+
+    // Check for errors
+    if (img.empty()) {
+        throw std::runtime_error("Failed to decode image");
+    }
+
+    return img;
+}
+
+
+/**
+ * @brief Encodes an OpenCV image into a base64 string
+ *
+ * This function takes an OpenCV image and encodes it into a base64 string.
+ * The image is first encoded as a PNG image, and then the resulting
+ * bytes are encoded as a base64 string.
+ *
+ * @param img The OpenCV image
+ * @return The base64 encoded string
+ *
+ * @throws std::runtime_error if the image is empty or encoding fails
+ */
+std::string image_to_base64(cv::Mat &img) {
+    if (img.empty()) {
+        throw std::runtime_error("Failed to read image");
+    }
+
+    // Encode the image as a PNG
+    std::vector<uchar> buf;
+    if (!cv::imencode(".png", img, buf)) {
+        throw std::runtime_error("Failed to encode image");
+    }
+
+    // Encode the bytes as a base64 string
+    using namespace boost::archive::iterators;
+    using It = base64_from_binary<transform_width<std::vector<uchar>::const_iterator, 6, 8>>;
+    std::string base64(It(buf.begin()), It(buf.end()));
+
+    // Pad the string with '=' characters to a multiple of 4 bytes
+    base64.append((3 - buf.size() % 3) % 3, '=');
+
+    return base64;
+}
+
+
+/**
+ * @brief Callback function for libcurl to write data to a string
+ *
+ * This function is used as a callback for libcurl to write data to a string.
+ * It takes the contents, size, and nmemb as parameters, and writes the data to
+ * the string.
+ *
+ * @param contents The data to write
+ * @param size The size of the data
+ * @param nmemb The number of members in the data
+ * @param s The string to write the data to
+ * @return The number of bytes written
+ */
+size_t WriteCallback(void* contents, size_t size, size_t nmemb, std::string* s) {
+    size_t newLength = size * nmemb;
+    try {
+        // Resize the string to fit the new data
+        s->resize(s->size() + newLength);
+    } catch (std::bad_alloc& e) {
+        // If there's an error allocating memory, return 0
+        return 0;
+    }
+
+    // Copy the data to the string
+    std::copy(static_cast<const char*>(contents),
+              static_cast<const char*>(contents) + newLength,
+              s->begin() + s->size() - newLength);
+    return newLength;
+}
+
+// Helper functions
+
+/**
+ * @brief Helper function to convert a type to a Json::Value
+ *
+ * This function takes a value of type T and converts it to a Json::Value.
+ * It is used to simplify the process of converting a type to a Json::Value.
+ *
+ * @param val The value to convert
+ * @return The converted Json::Value
+ */
+template <typename T>
+Json::Value toJson(const T& val) {
+    return Json::Value(val);
+}
+
+/**
+ * @brief Converts a vector to a Json::Value
+ *
+ * This function takes a vector of type T and converts it to a Json::Value.
+ * Each element in the vector is appended to the Json::Value array.
+ *
+ * @param vec The vector to convert to Json::Value
+ * @return The Json::Value representing the vector
+ */
+template <typename T>
+Json::Value vectorToJson(const std::vector<T>& vec) {
+    Json::Value json(Json::arrayValue);
+    for (const auto& item : vec) {
+        json.append(item);
+    }
+    return json;
+}
+
+/**
+ * @brief Converts a nested vector to a Json::Value
+ *
+ * This function takes a nested vector of type T and converts it to a Json::Value.
+ * Each sub-vector is converted to a Json::Value array and appended to the main Json::Value array.
+ *
+ * @param vec The nested vector to convert to Json::Value
+ * @return The Json::Value representing the nested vector
+ */
+template <typename T>
+Json::Value nestedVectorToJson(const std::vector<std::vector<T>>& vec) {
+    Json::Value json(Json::arrayValue);
+    for (const auto& subVec : vec) {
+        json.append(vectorToJson(subVec));
+    }
+    return json;
+}
+
+
+
+/**
+ * @brief Converts the APIParams struct to a Json::Value
+ *
+ * This function takes an APIParams struct and converts it to a Json::Value.
+ * The Json::Value is a JSON object with the following fields:
+ * - data: a JSON array of base64 encoded images
+ * - max_keypoints: a JSON array of integers, max number of keypoints for each image
+ * - timestamps: a JSON array of timestamps, one for each image
+ * - grayscale: a JSON boolean, whether to convert images to grayscale
+ * - image_hw: a nested JSON array, each sub-array contains the height and width of an image
+ * - feature_type: a JSON integer, the type of feature detector to use
+ * - rotates: a JSON array of doubles, the rotation of each image
+ * - scales: a JSON array of doubles, the scale of each image
+ * - reference_points: a nested JSON array, each sub-array contains the reference points of an image
+ * - binarize: a JSON boolean, whether to binarize the descriptors
+ *
+ * @param params The APIParams struct to convert
+ * @return The Json::Value representing the APIParams struct
+ */
+Json::Value paramsToJson(const APIParams& params) {
+    Json::Value json;
+    json["data"] = vectorToJson(params.data);
+    json["max_keypoints"] = vectorToJson(params.max_keypoints);
+    json["timestamps"] = vectorToJson(params.timestamps);
+    json["grayscale"] = toJson(params.grayscale);
+    json["image_hw"] = nestedVectorToJson(params.image_hw);
+    json["feature_type"] = toJson(params.feature_type);
+    json["rotates"] = vectorToJson(params.rotates);
+    json["scales"] = vectorToJson(params.scales);
+    json["reference_points"] = nestedVectorToJson(params.reference_points);
+    json["binarize"] = toJson(params.binarize);
+    return json;
+}
+
+template<typename T>
+cv::Mat jsonToMat(Json::Value json) {
+    int rows = json.size();
+    int cols = json[0].size();
+
+    // Create a single array to hold all the data.
+    std::vector<T> data;
+    data.reserve(rows * cols);
+
+    for (int i = 0; i < rows; i++) {
+        for (int j = 0; j < cols; j++) {
+            data.push_back(static_cast<T>(json[i][j].asInt()));
+        }
+    }
+
+    // Create a cv::Mat object that points to the data.
+    cv::Mat mat(rows, cols, CV_8UC1, data.data());  // Change the type if necessary.
+    // cv::Mat mat(cols, rows,CV_8UC1, data.data());  // Change the type if necessary.
+
+    return mat;
+}
+
+
+
+/**
+ * @brief Decodes the response of the server and prints the keypoints
+ *
+ * This function takes the response of the server, a JSON string, and decodes
+ * it. It then prints the keypoints and draws them on the original image.
+ *
+ * @param response The response of the server
+ * @return The keypoints and descriptors
+ */
+KeyPointResults decode_response(const std::string& response, bool viz=true) {
+    Json::CharReaderBuilder builder;
+    Json::CharReader* reader = builder.newCharReader();
+
+    Json::Value jsonData;
+    std::string errors;
+
+    // Parse the JSON response
+    bool parsingSuccessful = reader->parse(response.c_str(),
+        response.c_str() + response.size(), &jsonData, &errors);
+    delete reader;
+
+    if (!parsingSuccessful) {
+        // Handle error
+        std::cout << "Failed to parse the JSON, errors:" << std::endl;
+        std::cout << errors << std::endl;
+        return KeyPointResults();
+    }
+
+    KeyPointResults kpts_results;
+
+    // Iterate over the images
+    for (const auto& jsonItem : jsonData) {
+        auto jkeypoints = jsonItem["keypoints"];
+        auto jkeypoints_orig = jsonItem["keypoints_orig"];
+        auto jdescriptors = jsonItem["descriptors"];
+        auto jscores = jsonItem["scores"];
+        auto jimageSize = jsonItem["image_size"];
+        auto joriginalSize = jsonItem["original_size"];
+        auto jsize = jsonItem["size"];
+
+        std::vector<cv::KeyPoint> vkeypoints;
+        std::vector<float> vscores;
+
+        // Iterate over the keypoints
+        int counter = 0;
+        for (const auto& keypoint : jkeypoints_orig) {
+            if (counter < 10) {
+                // Print the first 10 keypoints
+                std::cout << keypoint[0].asFloat() << ", "
+                    << keypoint[1].asFloat() << std::endl;
+            }
+            counter++;
+            // Convert the Json::Value to a cv::KeyPoint
+            vkeypoints.emplace_back(cv::KeyPoint(keypoint[0].asFloat(),
+                keypoint[1].asFloat(), 0.0));
+        }
+
+        if (viz && jsonItem.isMember("image_orig")) {
+
+            auto jimg_orig = jsonItem["image_orig"];
+            cv::Mat img = jsonToMat<uchar>(jimg_orig);
+            cv::imwrite("viz_image_orig.jpg", img);
+
+            // Draw keypoints on the image
+            cv::Mat imgWithKeypoints;
+            cv::drawKeypoints(img, vkeypoints, 
+                imgWithKeypoints, cv::Scalar(0, 0, 255));
+
+            // Write the image with keypoints
+            std::string filename = "viz_image_orig_keypoints.jpg";
+            cv::imwrite(filename, imgWithKeypoints);
+        }
+
+        // Iterate over the descriptors
+        cv::Mat descriptors = jsonToMat<uchar>(jdescriptors); 
+        kpts_results.append_keypoints(vkeypoints);
+        kpts_results.append_descriptors(descriptors);
+    }
+    return kpts_results;
+}

app.py

@@ -0,0 +1,28 @@
+import argparse
+from pathlib import Path
+from ui.app_class import ImageMatchingApp
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--server_name",
+        type=str,
+        default="0.0.0.0",
+        help="server name",
+    )
+    parser.add_argument(
+        "--server_port",
+        type=int,
+        default=7860,
+        help="server port",
+    )
+    parser.add_argument(
+        "--config",
+        type=str,
+        default=Path(__file__).parent / "ui/config.yaml",
+        help="config file",
+    )
+    args = parser.parse_args()
+    ImageMatchingApp(
+        args.server_name, args.server_port, config=args.config
+    ).run()

build_docker.sh

@@ -0,0 +1,3 @@
+docker build -t image-matching-webui:latest . --no-cache
+docker tag image-matching-webui:latest vincentqin/image-matching-webui:latest
+docker push vincentqin/image-matching-webui:latest

datasets/show/txt.txt

@@ -0,0 +1,18 @@
+2/IM_05311.jpg
+2/IM_02422.jpg
+3/IM_00748.jpg
+3/IM_04239.jpg
+4/IM_00008.jpg
+4/IM_01534.jpg
+vis/00022_00194_outdoor_180_010.png
+depth/00022_00194_outdoor_180_010.png
+vis/00022_00194_outdoor_350_010.png
+depth/00022_00194_outdoor_350_010.png
+vis/00022_00195_outdoor_000_040.png
+depth/00022_00195_outdoor_000_040.png
+vis/000289.png
+event/000289.png
+vis/000422.png
+event/000422.png
+vis/000522.png
+event/000522.png

docker/build_docker.bat

@@ -0,0 +1,3 @@
+docker build -t image-matching-webui:latest . --no-cache
+# docker tag image-matching-webui:latest vincentqin/image-matching-webui:latest
+# docker push vincentqin/image-matching-webui:latest

docker/run_docker.bat

@@ -0,0 +1 @@
+docker run -it -p 7860:7860 vincentqin/image-matching-webui:latest python app.py --server_name "0.0.0.0" --server_port=7860

docker/run_docker.sh

@@ -0,0 +1 @@
+docker run -it -p 7860:7860 vincentqin/image-matching-webui:latest python app.py --server_name "0.0.0.0" --server_port=7860

format.sh

@@ -0,0 +1,3 @@
+python -m flake8 ui/*.py api/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py 
+python -m isort ui/*.py api/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py
+python -m black ui/*.py api/*.py hloc/*.py hloc/matchers/*.py hloc/extractors/*.py

hloc/__init__.py

@@ -0,0 +1,66 @@
+import logging
+import sys
+
+import torch
+from packaging import version
+
+__version__ = "1.5"
+
+LOG_PATH = "log.txt"
+
+
+def read_logs():
+    sys.stdout.flush()
+    with open(LOG_PATH, "r") as f:
+        return f.read()
+
+
+def flush_logs():
+    sys.stdout.flush()
+    logs = open(LOG_PATH, "w")
+    logs.close()
+
+
+formatter = logging.Formatter(
+    fmt="[%(asctime)s %(name)s %(levelname)s] %(message)s",
+    datefmt="%Y/%m/%d %H:%M:%S",
+)
+
+logs_file = open(LOG_PATH, "w")
+logs_file.close()
+
+file_handler = logging.FileHandler(filename=LOG_PATH)
+file_handler.setFormatter(formatter)
+file_handler.setLevel(logging.INFO)
+stdout_handler = logging.StreamHandler()
+stdout_handler.setFormatter(formatter)
+stdout_handler.setLevel(logging.INFO)
+logger = logging.getLogger("hloc")
+logger.setLevel(logging.INFO)
+logger.addHandler(file_handler)
+logger.addHandler(stdout_handler)
+logger.propagate = False
+
+try:
+    import pycolmap
+except ImportError:
+    logger.warning("pycolmap is not installed, some features may not work.")
+else:
+    min_version = version.parse("0.6.0")
+    found_version = pycolmap.__version__
+    if found_version != "dev":
+        version = version.parse(found_version)
+        if version < min_version:
+            s = f"pycolmap>={min_version}"
+            logger.warning(
+                "hloc requires %s but found pycolmap==%s, "
+                'please upgrade with `pip install --upgrade "%s"`',
+                s,
+                found_version,
+                s,
+            )
+
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# model hub: https://huggingface.co/Realcat/imatchui_checkpoint
+MODEL_REPO_ID = "Realcat/imatchui_checkpoints"