Create python-publish.yml (#54)

Updates the requirements on [pillow](https://github.com/python-pillow/Pillow) to permit the latest version.
- [Release notes](https://github.com/python-pillow/Pillow/releases)
- [Changelog](https://github.com/python-pillow/Pillow/blob/main/CHANGES.rst)
- [Commits](https://github.com/python-pillow/Pillow/compare/9.2.0...10.3.0)

---
updated-dependencies:
- dependency-name: pillow
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/pylint.yml

@@ -0,0 +1,24 @@
+name: Pylint
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install pylint
+    - name: Analysing the code with pylint
+      run: |
+        pylint $(git ls-files '*.py')

.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

.pylintrc

@@ -0,0 +1,631 @@
+[MAIN]
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Clear in-memory caches upon conclusion of linting. Useful if running pylint
+# in a server-like mode.
+clear-cache-post-run=no
+
+# Load and enable all available extensions. Use --list-extensions to see a list
+# all available extensions.
+#enable-all-extensions=
+
+# In error mode, messages with a category besides ERROR or FATAL are
+# suppressed, and no reports are done by default. Error mode is compatible with
+# disabling specific errors.
+#errors-only=
+
+# Always return a 0 (non-error) status code, even if lint errors are found.
+# This is primarily useful in continuous integration scripts.
+#exit-zero=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-allow-list=
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code. (This is an alternative name to extension-pkg-allow-list
+# for backward compatibility.)
+extension-pkg-whitelist=
+
+# Return non-zero exit code if any of these messages/categories are detected,
+# even if score is above --fail-under value. Syntax same as enable. Messages
+# specified are enabled, while categories only check already-enabled messages.
+fail-on=
+
+# Specify a score threshold under which the program will exit with error.
+fail-under=10
+
+# Interpret the stdin as a python script, whose filename needs to be passed as
+# the module_or_package argument.
+#from-stdin=
+
+# Files or directories to be skipped. They should be base names, not paths.
+ignore=CVS
+
+# Add files or directories matching the regular expressions patterns to the
+# ignore-list. The regex matches against paths and can be in Posix or Windows
+# format. Because '\\' represents the directory delimiter on Windows systems,
+# it can't be used as an escape character.
+ignore-paths=
+
+# Files or directories matching the regular expression patterns are skipped.
+# The regex matches against base names, not paths. The default value ignores
+# Emacs file locks
+ignore-patterns=^\.#
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis). It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use, and will cap the count on Windows to
+# avoid hangs.
+jobs=1
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python module names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Minimum Python version to use for version dependent checks. Will default to
+# the version used to run pylint.
+py-version=3.10
+
+# Discover python modules and packages in the file system subtree.
+recursive=no
+
+# Add paths to the list of the source roots. Supports globbing patterns. The
+# source root is an absolute path or a path relative to the current working
+# directory used to determine a package namespace for modules located under the
+# source root.
+source-roots=
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+# In verbose mode, extra non-checker-related info will be displayed.
+#verbose=
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style. If left empty, argument names will be checked with the set
+# naming style.
+#argument-rgx=
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style. If left empty, attribute names will be checked with the set naming
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=foo,
+          bar,
+          baz,
+          toto,
+          tutu,
+          tata
+
+# Bad variable names regexes, separated by a comma. If names match any regex,
+# they will always be refused
+bad-names-rgxs=
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style. If left empty, class attribute names will be checked
+# with the set naming style.
+#class-attribute-rgx=
+
+# Naming style matching correct class constant names.
+class-const-naming-style=UPPER_CASE
+
+# Regular expression matching correct class constant names. Overrides class-
+# const-naming-style. If left empty, class constant names will be checked with
+# the set naming style.
+#class-const-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style. If left empty, class names will be checked with the set naming style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style. If left empty, constant names will be checked with the set naming
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style. If left empty, function names will be checked with the set
+# naming style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           ex,
+           Run,
+           _
+
+# Good variable names regexes, separated by a comma. If names match any regex,
+# they will always be accepted
+good-names-rgxs=
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style. If left empty, inline iteration names will be checked
+# with the set naming style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style. If left empty, method names will be checked with the set naming style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style. If left empty, module names will be checked with the set naming style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Regular expression matching correct type alias names. If left empty, type
+# alias names will be checked with the set naming style.
+#typealias-rgx=
+
+# Regular expression matching correct type variable names. If left empty, type
+# variable names will be checked with the set naming style.
+#typevar-rgx=
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style. If left empty, variable names will be checked with the set
+# naming style.
+#variable-rgx=
+
+
+[CLASSES]
+
+# Warn about protected attribute access inside special methods
+check-protected-access-in-special-methods=no
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp,
+                      asyncSetUp,
+                      __post_init__
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,_fields,_replace,_source,_make,os._exit
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs
+
+
+[DESIGN]
+
+# List of regular expressions of class ancestor names to ignore when counting
+# public methods (see R0903)
+exclude-too-few-public-methods=
+
+# List of qualified class names to ignore when counting class parents (see
+# R0901)
+ignored-parents=
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement (see R0916).
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when caught.
+overgeneral-exceptions=builtins.BaseException,builtins.Exception
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=100
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[IMPORTS]
+
+# List of modules that can be imported at any level, not just the top level
+# one.
+allow-any-import-level=
+
+# Allow explicit reexports by alias from a package __init__.
+allow-reexport-from-package=no
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=
+
+# Output a graph (.gv or any supported image format) of external dependencies
+# to the given file (report RP0402 must not be disabled).
+ext-import-graph=
+
+# Output a graph (.gv or any supported image format) of all (i.e. internal and
+# external) dependencies to the given file (report RP0402 must not be
+# disabled).
+import-graph=
+
+# Output a graph (.gv or any supported image format) of internal dependencies
+# to the given file (report RP0402 must not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+# Couples of modules and preferred modules, separated by a comma.
+preferred-modules=
+
+
+[LOGGING]
+
+# The type of string formatting that logging methods do. `old` means using %
+# formatting, `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE,
+# UNDEFINED.
+confidence=HIGH,
+           CONTROL_FLOW,
+           INFERENCE,
+           INFERENCE_FAILURE,
+           UNDEFINED
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then re-enable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[METHOD_ARGS]
+
+# List of qualified names (i.e., library.method) which require a timeout
+# parameter e.g. 'requests.api.get,requests.api.post'
+timeout-methods=requests.api.delete,requests.api.get,requests.api.head,requests.api.options,requests.api.patch,requests.api.post,requests.api.put,requests.api.request
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+# Regular expression of note tags to take in consideration.
+notes-rgx=
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit,argparse.parse_error
+
+
+[REPORTS]
+
+# Python expression which should return a score less than or equal to 10. You
+# have access to the variables 'fatal', 'error', 'warning', 'refactor',
+# 'convention', and 'info' which contain the number of messages in each
+# category, as well as 'statement' which is the total number of statements
+# analyzed. This score is used by the global evaluation report (RP0004).
+evaluation=max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10))
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+#output-format=
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[SIMILARITIES]
+
+# Comments are removed from the similarity computation
+ignore-comments=yes
+
+# Docstrings are removed from the similarity computation
+ignore-docstrings=yes
+
+# Imports are removed from the similarity computation
+ignore-imports=yes
+
+# Signatures are removed from the similarity computation
+ignore-signatures=yes
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. No available dictionaries : You need to install
+# both the python package and the system dependency for enchant to work..
+spelling-dict=
+
+# List of comma separated words that should be considered directives if they
+# appear at the beginning of a comment and should not be checked.
+spelling-ignore-comment-directives=fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains the private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to the private dictionary (see the
+# --spelling-private-dict-file option) instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[STRING]
+
+# This flag controls whether inconsistent-quotes generates a warning when the
+# character used as a quote delimiter is used inconsistently within a module.
+check-quote-consistency=no
+
+# This flag controls whether the implicit-str-concat should generate a warning
+# on implicit string concatenation in sequences defined over several lines.
+check-str-concat-over-line-jumps=no
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=cv2.*
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of symbolic message names to ignore for Mixin members.
+ignored-checks-for-mixins=no-member,
+                          not-async-context-manager,
+                          not-context-manager,
+                          attribute-defined-outside-init
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local,argparse.Namespace
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+# Regex pattern to define which classes are considered mixins.
+mixin-class-rgx=.*[Mm]ixin
+
+# List of decorators that change the signature of a decorated function.
+signature-mutators=
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of names allowed to shadow builtins
+allowed-redefined-builtins=
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io

README.md

@@ -1,89 +1,78 @@
-**Forked from [rooneysh/Labelme2YOLO](https://github.com/rooneysh/Labelme2YOLO)**
-
 # Labelme2YOLO
 
 [![PyPI - Version](https://img.shields.io/pypi/v/labelme2yolo.svg)](https://pypi.org/project/labelme2yolo)
 ![PyPI - Downloads](https://img.shields.io/pypi/dm/labelme2yolo?style=flat)
+[![PYPI - Downloads](https://static.pepy.tech/badge/labelme2yolo)](https://pepy.tech/project/labelme2yolo)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/labelme2yolo.svg)](https://pypi.org/project/labelme2yolo)
-[![Codacy Badge](https://app.codacy.com/project/badge/Grade/12122fe86f8643c4aa5667c20d528f61)](https://www.codacy.com/gh/GreatV/labelme2yolo/dashboard?utm_source=github.com&utm_medium=referral&utm_content=GreatV/labelme2yolo&utm_campaign=Badge_Grade)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/12122fe86f8643c4aa5667c20d528f61)](https://www.codacy.com/gh/GreatV/labelme2yolo/dashboard?utm_source=github.com\&utm_medium=referral\&utm_content=GreatV/labelme2yolo\&utm_campaign=Badge_Grade)
 
-Help converting LabelMe Annotation Tool JSON format to YOLO text file format. 
-If you've already marked your segmentation dataset by LabelMe, it's easy to use this tool to help converting to YOLO format dataset.
+Labelme2YOLO is a powerful tool for converting LabelMe's JSON format to [YOLOv5](https://github.com/ultralytics/yolov5) dataset format. This tool can also be used for YOLOv5/YOLOv8 segmentation datasets, if you have already made your segmentation dataset with LabelMe, it is easy to use this tool to help convert to YOLO format dataset.
 
----------
+## New Features
+
+* export data as yolo polygon annotation (for YOLOv5 & YOLOV8 segmentation)
+* Now you can choose the output format of the label text. The two available alternatives are `polygon` and bounding box (`bbox`).
 
-## New
-- export data as yolo polygon annotation (for YOLOv5 v7.0 segmentation)
-- Now you can choose the output format of the label text. The available options are `plygon` and `bbox`.
 ## Installation
 
-```console
+```shell
 pip install labelme2yolo
 ```
 
-## Parameters Explain
-**--json_dir** LabelMe JSON files folder path.
+## Arguments
 
-**--val_size (Optional)** Validation dataset size, for example 0.2 means 20% for validation.
+**--json\_dir** LabelMe JSON files folder path.
 
-**--test_size (Optional)** Test dataset size, for example 0.2 means 20% for Test.
+**--val\_size (Optional)** Validation dataset size, for example 0.2 means 20% for validation.
 
-**--json_name (Optional)** Convert single LabelMe JSON file.
+**--test\_size (Optional)** Test dataset size, for example 0.1 means 10% for Test.
 
-**--output_format (Optional)** The output format of label.
+**--json\_name (Optional)** Convert single LabelMe JSON file.
+
+**--output\_format (Optional)** The output format of label.
+
+**--label\_list (Optional)** The pre-assigned category labels.
 
 ## How to Use
 
-### 1. Convert JSON files, split training, validation and test dataset by --val_size and --test_size
-Put all LabelMe JSON files under **labelme_json_dir**, and run this python command.
-```bash
+### 1. Converting JSON files and splitting training, validation datasets
+
+You may need to place all LabelMe JSON files under **labelme\_json\_dir** and then run the following command:
+
+```shell
+labelme2yolo --json_dir /path/to/labelme_json_dir/
+```
+
+This tool will generate dataset labels and images with YOLO format in different folders, such as
+
+```plaintext
+/path/to/labelme_json_dir/YOLODataset/labels/train/
+/path/to/labelme_json_dir/YOLODataset/labels/val/
+/path/to/labelme_json_dir/YOLODataset/images/train/
+/path/to/labelme_json_dir/YOLODataset/images/val/
+/path/to/labelme_json_dir/YOLODataset/dataset.yaml
+```
+
+### 2. Converting JSON files and splitting training, validation, and test datasets with --val\_size and --test\_size
+
+You may need to place all LabelMe JSON files under **labelme\_json\_dir** and then run the following command:
+
+```shell
 labelme2yolo --json_dir /path/to/labelme_json_dir/ --val_size 0.15 --test_size 0.15
 ```
-Script would generate YOLO format dataset labels and images under different folders, for example,
-```bash
+
+This tool will generate dataset labels and images with YOLO format in different folders, such as
+
+```plaintext
 /path/to/labelme_json_dir/YOLODataset/labels/train/
 /path/to/labelme_json_dir/YOLODataset/labels/test/
 /path/to/labelme_json_dir/YOLODataset/labels/val/
 /path/to/labelme_json_dir/YOLODataset/images/train/
 /path/to/labelme_json_dir/YOLODataset/images/test/
 /path/to/labelme_json_dir/YOLODataset/images/val/
-
 /path/to/labelme_json_dir/YOLODataset/dataset.yaml
 ```
 
-### 2. Convert JSON files, split training and validation dataset by folder
-If you already split train dataset and validation dataset for LabelMe by yourself, please put these folder under labelme_json_dir, for example,
-```bash
-/path/to/labelme_json_dir/train/
-/path/to/labelme_json_dir/val/
-```
-Put all LabelMe JSON files under **labelme_json_dir**. 
-Script would read train and validation dataset by folder.
-Run this python command.
-```bash
-labelme2yolo --json_dir /path/to/labelme_json_dir/
-```
-Script would generate YOLO format dataset labels and images under different folders, for example,
-```bash
-/path/to/labelme_json_dir/YOLODataset/labels/train/
-/path/to/labelme_json_dir/YOLODataset/labels/val/
-/path/to/labelme_json_dir/YOLODataset/images/train/
-/path/to/labelme_json_dir/YOLODataset/images/val/
-
-/path/to/labelme_json_dir/YOLODataset/dataset.yaml
-```
-
-### 3. Convert single JSON file
-Put LabelMe JSON file under **labelme_json_dir**. , and run this python command.
-```bash
-labelme2yolo --json_dir /path/to/labelme_json_dir/ --json_name 2.json
-```
-Script would generate YOLO format text label and image under **labelme_json_dir**, for example,
-```bash
-/path/to/labelme_json_dir/2.text
-/path/to/labelme_json_dir/2.png
-```
-
 ## How to build package/wheel
 
 1. [install hatch](https://hatch.pypa.io/latest/install/)
@@ -95,4 +84,6 @@ hatch build
 
 ## License
 
+**Forked from [rooneysh/Labelme2YOLO](https://github.com/rooneysh/Labelme2YOLO)**
+
 `labelme2yolo` is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.

pyproject.toml

@@ -6,27 +6,27 @@ build-backend = "hatchling.build"
 name = "labelme2yolo"
 description = "This script converts the JSON format output by LabelMe to the text format required by YOLO serirs."
 readme = "README.md"
-requires-python = ">=3.7"
+requires-python = ">=3.8"
 license = "MIT"
 keywords = []
 authors = [
   { name = "GreatV(Wang Xin)", email = "xinwang614@gmail.com" },
 ]
 classifiers = [
-  "Development Status :: 4 - Beta",
+  "Development Status :: 5 - Production/Stable",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.7",
   "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
-  "Programming Language :: Python :: Implementation :: CPython",
-  "Programming Language :: Python :: Implementation :: PyPy",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "License :: OSI Approved :: MIT License",
 ]
 dependencies = [
   "opencv-python>=4.1.2",
-  "Pillow>=9.2,<9.5",
-  "scikit-learn>=1.1.1,<1.3.0",
-  "numpy>=1.23.1,<1.25.0"
+  "Pillow>=9.2,<10.4",
+  "numpy>=1.23.1,<1.27.0",
+  "rich"
 ]
 dynamic = ["version"]
 
@@ -54,7 +54,7 @@ cov = "pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=labelm
 no-cov = "cov --no-cov"
 
 [[tool.hatch.envs.test.matrix]]
-python = ["37", "38", "39", "310"]
+python = ["38", "39", "310", "311", "312"]
 
 [tool.coverage.run]
 branch = true

requirements.txt

@@ -1,4 +1,4 @@
 opencv-python
 Pillow
-scikit-learn
 numpy
+rich

src/labelme2yolo/__about__.py

@@ -1,5 +1,7 @@
 # SPDX-FileCopyrightText: 2023-present Wang Xin <xinwang614@gmail.com>
 #
 # SPDX-License-Identifier: MIT
-
-__version__ = '0.0.9'
+"""
+about version
+"""
+__version__ = "0.1.7"

src/labelme2yolo/__main__.py

@@ -1,6 +1,9 @@
 # SPDX-FileCopyrightText: 2022-present Wang Xin <xinwang614@gmail.com>
 #
 # SPDX-License-Identifier: MIT
+"""
+main
+"""
 import sys
 
 if __name__ == "__main__":

src/labelme2yolo/cli/__init__.py

@@ -1,13 +1,22 @@
 # SPDX-FileCopyrightText: 2022-present Wang Xin <xinwang614@gmail.com>
 #
 # SPDX-License-Identifier: MIT
+"""
+cli init
+"""
 import argparse
-
+from labelme2yolo.__about__ import __version__
 from labelme2yolo.l2y import Labelme2YOLO
 
 
 def run():
+    """
+    run cli
+    """
     parser = argparse.ArgumentParser("labelme2yolo")
+    parser.add_argument(
+        "-v", "--version", action="version", version="%(prog)s " + __version__
+    )
     parser.add_argument(
         "--json_dir", type=str, help="Please input the path of the labelme json files."
     )
@@ -15,14 +24,14 @@ def run():
         "--val_size",
         type=float,
         nargs="?",
-        default=None,
-        help="Please input the validation dataset size, for example 0.1.",
+        default=0.2,
+        help="Please input the validation dataset size, for example 0.2.",
     )
     parser.add_argument(
         "--test_size",
         type=float,
         nargs="?",
-        default=None,
+        default=0.0,
         help="Please input the test dataset size, for example 0.1.",
     )
     parser.add_argument(
@@ -39,6 +48,14 @@ def run():
         help='The default output format for labelme2yolo is "polygon".'
         ' However, you can choose to output in bbox format by specifying the "bbox" option.',
     )
+    parser.add_argument(
+        "--label_list",
+        type=str,
+        nargs="+",
+        default=None,
+        help="The ordered label list, for example --label_list cat dog",
+        required=False,
+    )
 
     args = parser.parse_args()
 
@@ -46,7 +63,7 @@ def run():
         parser.print_help()
         return 0
 
-    convertor = Labelme2YOLO(args.json_dir, args.output_format)
+    convertor = Labelme2YOLO(args.json_dir, args.output_format, args.label_list)
 
     if args.json_name is None:
         convertor.convert(val_size=args.val_size, test_size=args.test_size)

src/labelme2yolo/l2y.py

@@ -5,36 +5,58 @@ Created on Aug 18, 2021
 @author: GreatV(Wang Xin)
 """
 import base64
+import glob
 import io
 import json
 import math
 import os
+import random
 import shutil
-from collections import OrderedDict
-from multiprocessing import Pool
+import uuid
+import logging
+from functools import partial
 
-import cv2
-import numpy as np
+from multiprocessing import Pool
 import PIL.ExifTags
 import PIL.Image
 import PIL.ImageOps
-from sklearn.model_selection import train_test_split
+import cv2
+import numpy as np
+from rich.progress import Progress
+
+# set seed
+random.seed(12345678)
+random.Random().seed(12345678)
+np.random.seed(12345678)
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger("labelme2yolo")
 
 
-# number of LabelMe2YOLO multiprocessing threads
-NUM_THREADS = max(1, os.cpu_count() - 1)
+def train_test_split(dataset_index, test_size=0.2):
+    """Split dataset into train set and test set with test_size"""
+    test_size = min(max(0.0, test_size), 1.0)
+    total_size = len(dataset_index)
+    train_size = int(round(total_size * (1.0 - test_size)))
+    random.shuffle(dataset_index)
+    train_index = dataset_index[:train_size]
+    test_index = dataset_index[train_size:]
+
+    return train_index, test_index
 
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_data_to_pil(img_data):
-    f = io.BytesIO()
-    f.write(img_data)
-    img_pil = PIL.Image.open(f)
+    """Convert img_data(byte) to PIL.Image"""
+    file = io.BytesIO()
+    file.write(img_data)
+    img_pil = PIL.Image.open(file)
     return img_pil
 
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_data_to_arr(img_data):
+    """Convert img_data(byte) to numpy.ndarray"""
     img_pil = img_data_to_pil(img_data)
     img_arr = np.array(img_pil)
     return img_arr
@@ -42,6 +64,7 @@ def img_data_to_arr(img_data):
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_b64_to_arr(img_b64):
+    """Convert img_b64(str) to numpy.ndarray"""
     img_data = base64.b64decode(img_b64)
     img_arr = img_data_to_arr(img_data)
     return img_arr
@@ -49,27 +72,27 @@ def img_b64_to_arr(img_b64):
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_pil_to_data(img_pil):
-    f = io.BytesIO()
-    img_pil.save(f, format="PNG")
-    img_data = f.getvalue()
+    """Convert PIL.Image to img_data(byte)"""
+    file = io.BytesIO()
+    img_pil.save(file, format="PNG")
+    img_data = file.getvalue()
     return img_data
 
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_arr_to_b64(img_arr):
+    """Convert numpy.ndarray to img_b64(str)"""
     img_pil = PIL.Image.fromarray(img_arr)
-    f = io.BytesIO()
-    img_pil.save(f, format="PNG")
-    img_bin = f.getvalue()
-    if hasattr(base64, "encodebytes"):
-        img_b64 = base64.encodebytes(img_bin)
-    else:
-        img_b64 = base64.encodestring(img_bin)
+    file = io.BytesIO()
+    img_pil.save(file, format="PNG")
+    img_bin = file.getvalue()
+    img_b64 = base64.encodebytes(img_bin)
     return img_b64
 
 
 # copy form https://github.com/wkentaro/labelme/blob/main/labelme/utils/image.py
 def img_data_to_png_data(img_data):
+    """Convert img_data(byte) to png_data(byte)"""
     with io.BytesIO() as f_out:
         f_out.write(img_data)
         img = PIL.Image.open(f_out)
@@ -80,169 +103,186 @@ def img_data_to_png_data(img_data):
             return f_in.read()
 
 
-def get_label_id_map(json_dir):
-    label_set = set()
+def extend_point_list(point_list, out_format="polygon"):
+    """Extend point list to polygon or bbox"""
+    x_min = min(float(point) for point in point_list[::2])
+    x_max = max(float(point) for point in point_list[::2])
+    y_min = min(float(point) for point in point_list[1::2])
+    y_max = max(float(point) for point in point_list[1::2])
 
-    for file_name in os.listdir(json_dir):
-        if file_name.endswith("json"):
-            json_path = os.path.join(json_dir, file_name)
-            data = json.load(open(json_path))
-            for shape in data["shapes"]:
-                label_set.add(shape["label"])
+    if out_format == "bbox":
+        x_i = x_min
+        y_i = y_min
+        w_i = x_max - x_min
+        h_i = y_max - y_min
+        x_i = x_i + w_i / 2
+        y_i = y_i + h_i / 2
+        return np.array([x_i, y_i, w_i, h_i])
 
-    return OrderedDict([(label, label_id) for label_id, label in enumerate(label_set)])
+    return np.array([x_min, y_min, x_max, y_min, x_max, y_max, x_min, y_max])
 
 
-def extend_point_list(point_list, format="polygon"):
-    xmin = min([float(point) for point in point_list[::2]])
-    xmax = max([float(point) for point in point_list[::2]])
-    ymin = min([float(point) for point in point_list[1::2]])
-    ymax = max([float(point) for point in point_list[1::2]])
+def save_yolo_label(obj_list, label_dir, target_dir, target_name):
+    """Save yolo label to txt file"""
+    txt_path = os.path.join(label_dir, target_dir, target_name)
 
-    if (format == "polygon"):
-        return np.array([xmin, ymin, xmax, ymin, xmax, ymax, xmin, ymax])
-    if (format == "bbox"):
-        return np.array([xmin, ymin, xmax - xmin, ymax - ymin])
-
-
-def save_yolo_label(json_name, label_dir_path, target_dir, yolo_obj_list):
-    txt_path = os.path.join(label_dir_path,
-                            target_dir,
-                            json_name.replace(".json", ".txt"))
-
-    with open(txt_path, "w+") as f:
-        for yolo_obj in yolo_obj_list:
-            label, points = yolo_obj
+    with open(txt_path, "w+", encoding="utf-8") as file:
+        for label, points in obj_list:
             points = [str(item) for item in points]
-            yolo_obj_line = f"{label} {' '.join(points)}\n"
-            f.write(yolo_obj_line)
+            line = f"{label} {' '.join(points)}\n"
+            file.write(line)
 
 
-def save_yolo_image(json_data, json_name, image_dir_path, target_dir):
-    img_name = json_name.replace(".json", ".png")
-    img_path = os.path.join(image_dir_path, target_dir, img_name)
+def save_yolo_image(json_data, json_dir, image_dir, target_dir, target_name):
+    """Save yolo image to image_dir_path/target_dir"""
+    img_path = os.path.join(image_dir, target_dir, target_name)
 
-    if not os.path.exists(img_path):
+    if json_data["imageData"]:
         img = img_b64_to_arr(json_data["imageData"])
         PIL.Image.fromarray(img).save(img_path)
+    else:
+        image_name = json_data["imagePath"]
+        src_image_name = os.path.join(json_dir, image_name)
+        src_image = cv2.imread(src_image_name)
+        cv2.imwrite(img_path, src_image)
 
     return img_path
 
 
-class Labelme2YOLO(object):
+class Labelme2YOLO:
+    """Labelme to YOLO format converter"""
 
-    def __init__(self, json_dir, output_format):
-        self._json_dir = json_dir
+    def __init__(self, json_dir, output_format, label_list):
+        self._json_dir = os.path.expanduser(json_dir)
         self._output_format = output_format
+        self._label_list = []
+        self._label_id_map = {}
+        self._label_dir_path = ""
+        self._image_dir_path = ""
 
-        self._label_id_map = get_label_id_map(self._json_dir)
+        if label_list:
+            self._label_list = label_list
+            self._label_id_map = {
+                label: label_id for label_id, label in enumerate(label_list)
+            }
+        else:
+            logger.info("Searching label list from json files ...")
+            # get label list from json files for parallel processing
+            json_files = glob.glob(
+                os.path.join(self._json_dir, "**", "*.json"), recursive=True
+            )
+            for json_file in json_files:
+                with open(json_file, encoding="utf-8") as file:
+                    json_data = json.load(file)
+                    for shape in json_data["shapes"]:
+                        if shape["label"] not in self._label_list:
+                            self._label_list.append(shape["label"])
+            self._label_id_map = {
+                label: label_id for label_id, label in enumerate(self._label_list)
+            }
 
-    def _make_train_val_dir(self):
-        self._label_dir_path = os.path.join(self._json_dir,
-                                            'YOLODataset/labels/')
-        self._image_dir_path = os.path.join(self._json_dir,
-                                            'YOLODataset/images/')
+    def _update_id_map(self, label: str):
+        if label not in self._label_list:
+            self._label_list.append(label)
+            self._label_id_map[label] = len(self._label_id_map)
 
-        for yolo_path in (os.path.join(self._label_dir_path + 'train/'),
-                          os.path.join(self._label_dir_path + 'val/'),
-                          os.path.join(self._label_dir_path + 'test/'),
-                          os.path.join(self._image_dir_path + 'train/'),
-                          os.path.join(self._image_dir_path + 'val/'),
-                          os.path.join(self._image_dir_path + 'test/')):
-            if os.path.exists(yolo_path):
-                shutil.rmtree(yolo_path)
+    def _make_train_val_dir(self, create_test_dir=False):
+        self._label_dir_path = os.path.join(self._json_dir, "YOLODataset/labels/")
+        self._image_dir_path = os.path.join(self._json_dir, "YOLODataset/images/")
 
-            os.makedirs(yolo_path)
+        for yolo_path in [self._label_dir_path, self._image_dir_path]:
+            shutil.rmtree(yolo_path, ignore_errors=True)
 
-    def _train_test_split(self, folders, json_names, val_size, test_size):
-        if len(folders) > 0 and 'train' in folders and 'val' in folders and 'test' in folders:
-            train_folder = os.path.join(self._json_dir, 'train/')
-            train_json_names = [train_sample_name + '.json'
-                                for train_sample_name in os.listdir(train_folder)
-                                if os.path.isdir(os.path.join(train_folder, train_sample_name))]
+        parts = ["train", "val", "test"] if create_test_dir else ["train", "val"]
+        image_dirs = [os.path.join(self._image_dir_path, part) for part in parts]
+        label_dirs = [os.path.join(self._label_dir_path, part) for part in parts]
+        dirs = image_dirs + label_dirs
+        for yolo_path in dirs:
+            os.makedirs(yolo_path, exist_ok=True)
 
-            val_folder = os.path.join(self._json_dir, 'val/')
-            val_json_names = [val_sample_name + '.json'
-                              for val_sample_name in os.listdir(val_folder)
-                              if os.path.isdir(os.path.join(val_folder, val_sample_name))]
+    def _get_dataset_part_json_names(self, dataset_part: str):
+        """Get json names in dataset_part folder"""
+        set_folder = os.path.join(self._json_dir, dataset_part)
+        json_names = []
+        for sample_name in os.listdir(set_folder):
+            set_dir = os.path.join(set_folder, sample_name)
+            if os.path.isdir(set_dir):
+                json_names.append(sample_name + ".json")
+        return json_names
 
-            test_folder = os.path.join(self._json_dir, 'test/')
-            test_json_names = [test_sample_name + '.json'
-                               for test_sample_name in os.listdir(test_folder)
-                               if os.path.isdir(os.path.join(test_folder, test_sample_name))]
-
-            return train_json_names, val_json_names, test_json_names
-
-        train_idxs, val_idxs = train_test_split(range(len(json_names)),
-                                                test_size=val_size)
-        tmp_train_len = len(train_idxs)
-        test_idxs = []
+    def _train_test_split(self, json_names, val_size, test_size=None):
+        """Split json names to train, val, test"""
+        total_size = len(json_names)
+        dataset_index = list(range(total_size))
+        train_ids, val_ids = train_test_split(dataset_index, test_size=val_size)
+        test_ids = []
         if test_size is None:
             test_size = 0.0
-        if test_size > 1e-8:
-            train_idxs, test_idxs = train_test_split(
-                range(tmp_train_len), test_size=test_size / (1 - val_size))
-        train_json_names = [json_names[train_idx] for train_idx in train_idxs]
-        val_json_names = [json_names[val_idx] for val_idx in val_idxs]
-        test_json_names = [json_names[test_idx] for test_idx in test_idxs]
+        if test_size > 0.0:
+            train_ids, test_ids = train_test_split(
+                train_ids, test_size=test_size / (1 - val_size)
+            )
+        train_json_names = [json_names[train_idx] for train_idx in train_ids]
+        val_json_names = [json_names[val_idx] for val_idx in val_ids]
+        test_json_names = [json_names[test_idx] for test_idx in test_ids]
 
         return train_json_names, val_json_names, test_json_names
 
     def convert(self, val_size, test_size):
-        json_names = [file_name for file_name in os.listdir(self._json_dir)
-                      if os.path.isfile(os.path.join(self._json_dir, file_name)) and
-                      file_name.endswith('.json')]
-        folders = [file_name for file_name in os.listdir(self._json_dir)
-                   if os.path.isdir(os.path.join(self._json_dir, file_name))]
-        train_json_names, val_json_names, test_json_names = self._train_test_split(
-            folders, json_names, val_size, test_size)
+        """Convert labelme format to yolo format"""
+        json_names = glob.glob(
+            os.path.join(self._json_dir, "**", "*.json"), recursive=True
+        )
+        json_names = sorted(json_names)
 
-        self._make_train_val_dir()
+        train_json_names, val_json_names, test_json_names = self._train_test_split(
+            json_names, val_size, test_size
+        )
+
+        self._make_train_val_dir(test_size > 0.0)
 
         # convert labelme object to yolo format object, and save them to files
         # also get image from labelme json file and save them under images folder
-        for target_dir, json_names in zip(('train/', 'val/', 'test/'),
-                                          (train_json_names, val_json_names, test_json_names)):
-            pool = Pool(NUM_THREADS)
+        dirs = ("train", "val", "test")
+        names = (train_json_names, val_json_names, test_json_names)
+        for target_dir, json_names in zip(dirs, names):
+            logger.info("Converting %s set ...", target_dir)
+            with Pool(os.cpu_count() - 1) as pool, Progress() as progress:
+                task = progress.add_task("[cyan]Converting...", total=len(json_names))
+                func = partial(self.covert_json_to_text, target_dir)
+                for _ in pool.imap_unordered(func, json_names):
+                    progress.update(task, advance=1)
 
-            for json_name in json_names:
-                pool.apply_async(self.covert_json_to_text,
-                                 args=(target_dir, json_name))
-            pool.close()
-            pool.join()
-
-        print('Generating dataset.yaml file ...')
         self._save_dataset_yaml()
 
     def covert_json_to_text(self, target_dir, json_name):
-        json_path = os.path.join(self._json_dir, json_name)
-        json_data = json.load(open(json_path))
+        """Convert json file to yolo format text file and save them to files"""
+        with open(json_name, encoding="utf-8") as file:
+            json_data = json.load(file)
 
-        print('Converting %s for %s ...' %
-              (json_name, target_dir.replace('/', '')))
-
-        img_path = save_yolo_image(json_data,
-                                   json_name,
-                                   self._image_dir_path,
-                                   target_dir)
+        filename: str = uuid.UUID(int=random.Random().getrandbits(128)).hex
+        image_name = f"{filename}.png"
+        label_name = f"{filename}.txt"
+        img_path = save_yolo_image(
+            json_data, self._json_dir, self._image_dir_path, target_dir, image_name
+        )
         yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
-        save_yolo_label(json_name,
-                        self._label_dir_path,
-                        target_dir,
-                        yolo_obj_list)
+        save_yolo_label(yolo_obj_list, self._label_dir_path, target_dir, label_name)
 
     def convert_one(self, json_name):
+        """Convert one json file to yolo format text file and save them to files"""
         json_path = os.path.join(self._json_dir, json_name)
-        json_data = json.load(open(json_path))
+        with open(json_path, encoding="utf-8") as file:
+            json_data = json.load(file)
 
-        print('Converting %s ...' % json_name)
-
-        img_path = save_yolo_image(json_data, json_name,
-                                   self._json_dir, '')
+        image_name = json_name.replace(".json", ".png")
+        label_name = json_name.replace(".json", ".txt")
+        img_path = save_yolo_image(
+            json_data, self._json_dir, self._image_dir_path, "", image_name
+        )
 
         yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
-        save_yolo_label(json_name, self._json_dir,
-                        '', yolo_obj_list)
+        save_yolo_label(yolo_obj_list, self._label_dir_path, "", label_name)
 
     def _get_yolo_object_list(self, json_data, img_path):
         yolo_obj_list = []
@@ -251,65 +291,86 @@ class Labelme2YOLO(object):
         for shape in json_data["shapes"]:
             # labelme circle shape is different from others
             # it only has 2 points, 1st is circle center, 2nd is drag end point
-            if shape['shape_type'] == 'circle':
-                yolo_obj = self._get_circle_shape_yolo_object(
-                    shape, img_h, img_w)
+            if shape["shape_type"] == "circle":
+                yolo_obj = self._get_circle_shape_yolo_object(shape, img_h, img_w)
             else:
-                yolo_obj = self._get_other_shape_yolo_object(
-                    shape, img_h, img_w)
+                yolo_obj = self._get_other_shape_yolo_object(shape, img_h, img_w)
 
-            yolo_obj_list.append(yolo_obj)
+            if yolo_obj:
+                yolo_obj_list.append(yolo_obj)
 
         return yolo_obj_list
 
     def _get_circle_shape_yolo_object(self, shape, img_h, img_w):
-        obj_center_x, obj_center_y = shape['points'][0]
+        obj_center_x, obj_center_y = shape["points"][0]
 
-        radius = math.sqrt((obj_center_x - shape['points'][1][0]) ** 2 +
-                           (obj_center_y - shape['points'][1][1]) ** 2)
-        obj_w = 2 * radius
-        obj_h = 2 * radius
+        radius = math.sqrt(
+            (obj_center_x - shape["points"][1][0]) ** 2
+            + (obj_center_y - shape["points"][1][1]) ** 2
+        )
+        num_points = 36
+        points = np.zeros(2 * num_points)
+        for i in range(num_points):
+            angle = 2.0 * math.pi * i / num_points
+            points[2 * i] = (obj_center_x + radius * math.cos(angle)) / img_w
+            points[2 * i + 1] = (obj_center_y + radius * math.sin(angle)) / img_h
 
-        yolo_center_x = round(float(obj_center_x / img_w), 6)
-        yolo_center_y = round(float(obj_center_y / img_h), 6)
-        yolo_w = round(float(obj_w / img_w), 6)
-        yolo_h = round(float(obj_h / img_h), 6)
+        if shape["label"]:
+            label = shape["label"]
+            if label not in self._label_list:
+                self._update_id_map(label)
+            label_id = self._label_id_map[shape["label"]]
 
-        label_id = self._label_id_map[shape['label']]
+            return label_id, points.tolist()
 
-        return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
+        return None
 
     def _get_other_shape_yolo_object(self, shape, img_h, img_w):
-
-        point_list = shape['points']
+        point_list = shape["points"]
         points = np.zeros(2 * len(point_list))
         points[::2] = [float(point[0]) / img_w for point in point_list]
         points[1::2] = [float(point[1]) / img_h for point in point_list]
+
         if len(points) == 4:
             if self._output_format == "polygon":
                 points = extend_point_list(points)
             if self._output_format == "bbox":
                 points = extend_point_list(points, "bbox")
-        label_id = self._label_id_map[shape['label']]
 
-        return label_id, points.tolist()
+        if shape["label"]:
+            label = shape["label"]
+            if label not in self._label_list:
+                self._update_id_map(label)
+            label_id = self._label_id_map[shape["label"]]
+
+            return label_id, points.tolist()
+
+        return None
 
     def _save_dataset_yaml(self):
-        yaml_path = os.path.join(
-            self._json_dir, 'YOLODataset/', 'dataset.yaml')
+        yaml_path = os.path.join(self._json_dir, "YOLODataset/", "dataset.yaml")
 
-        with open(yaml_path, 'w+') as yaml_file:
-            yaml_file.write('train: %s\n' %
-                            os.path.join(self._image_dir_path, 'train/'))
-            yaml_file.write('val: %s\n' %
-                            os.path.join(self._image_dir_path, 'val/'))
-            yaml_file.write('test: %s\n' %
-                            os.path.join(self._image_dir_path, 'test/'))
-            yaml_file.write('nc: %i\n' % len(self._label_id_map))
-
-            names_str = ''
+        with open(yaml_path, "w+", encoding="utf-8") as yaml_file:
+            train_dir = os.path.join(self._image_dir_path, "train/")
+            val_dir = os.path.join(self._image_dir_path, "val/")
+            test_dir = os.path.join(self._image_dir_path, "test/")
 
+            names_str = ""
             for label, _ in self._label_id_map.items():
-                names_str += "'%s', " % label
+                names_str += f'"{label}", '
             names_str = names_str.rstrip(", ")
-            yaml_file.write("names: [%s]" % names_str)
+
+            if os.path.exists(test_dir):
+                content = (
+                    f"train: {train_dir}\nval: {val_dir}\ntest: {test_dir}\n"
+                    f"nc: {len(self._label_id_map)}\n"
+                    f"names: [{names_str}]"
+                )
+            else:
+                content = (
+                    f"train: {train_dir}\nval: {val_dir}\n"
+                    f"nc: {len(self._label_id_map)}\n"
+                    f"names: [{names_str}]"
+                )
+
+            yaml_file.write(content)