Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

assets/python: models thresholds tuning #942

Merged
merged 3 commits into from
Feb 4, 2025
Merged

assets/python: models thresholds tuning #942

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1957532
python: go back to -dev version
reyammer Feb 3, 2025
947bbab
assets: more models thresholds tuning
reyammer Feb 3, 2025
ebcc5e2
rust: update model thresholds
reyammer Feb 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion assets/models/standard_v3_0/config.min.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"beg_size":1024,"mid_size":0,"end_size":1024,"use_inputs_at_offsets":false,"medium_confidence_threshold":0.5,"min_file_size_for_dl":8,"padding_token":256,"block_size":4096,"target_labels_space":["3gp","ace","ai","aidl","apk","applebplist","appleplist","asm","asp","autohotkey","autoit","awk","batch","bazel","bib","bmp","bzip","c","cab","cat","chm","clojure","cmake","cobol","coff","coffeescript","cpp","crt","crx","cs","csproj","css","csv","dart","deb","dex","dicom","diff","dm","dmg","doc","dockerfile","docx","dsstore","dwg","dxf","elf","elixir","emf","eml","epub","erb","erlang","flac","flv","fortran","gemfile","gemspec","gif","gitattributes","gitmodules","go","gradle","groovy","gzip","h5","handlebars","haskell","hcl","hlp","htaccess","html","icns","ico","ics","ignorefile","ini","internetshortcut","ipynb","iso","jar","java","javabytecode","javascript","jinja","jp2","jpeg","json","jsonl","julia","kotlin","latex","lha","lisp","lnk","lua","m3u","m4","macho","makefile","markdown","matlab","mht","midi","mkv","mp3","mp4","mscompress","msi","mum","npy","npz","nupkg","objectivec","ocaml","odp","ods","odt","ogg","one","onnx","otf","outlook","parquet","pascal","pcap","pdb","pdf","pebin","pem","perl","php","pickle","png","po","postscript","powershell","ppt","pptx","prolog","proteindb","proto","psd","python","pythonbytecode","pytorch","qt","r","randombytes","randomtxt","rar","rdf","rpm","rst","rtf","ruby","rust","scala","scss","sevenzip","sgml","shell","smali","snap","solidity","sql","sqlite","squashfs","srt","stlbinary","stltext","sum","svg","swf","swift","tar","tcl","textproto","tga","thumbsdb","tiff","toml","torrent","tsv","ttf","twig","txt","typescript","vba","vcxproj","verilog","vhdl","vtt","vue","wasm","wav","webm","webp","winregistry","wmf","woff","woff2","xar","xls","xlsb","xlsx","xml","xpi","xz","yaml","yara","zig","zip","zlibstream"],"thresholds":{"handlebars":0.9,"ignorefile":0.95,"latex":0.95,"markdown":0.9,"pascal":0.95},"overwrite_map":{"randombytes":"unknown","randomtxt":"txt"},"version_major":3}
{"beg_size":1024,"mid_size":0,"end_size":1024,"use_inputs_at_offsets":false,"medium_confidence_threshold":0.5,"min_file_size_for_dl":8,"padding_token":256,"block_size":4096,"target_labels_space":["3gp","ace","ai","aidl","apk","applebplist","appleplist","asm","asp","autohotkey","autoit","awk","batch","bazel","bib","bmp","bzip","c","cab","cat","chm","clojure","cmake","cobol","coff","coffeescript","cpp","crt","crx","cs","csproj","css","csv","dart","deb","dex","dicom","diff","dm","dmg","doc","dockerfile","docx","dsstore","dwg","dxf","elf","elixir","emf","eml","epub","erb","erlang","flac","flv","fortran","gemfile","gemspec","gif","gitattributes","gitmodules","go","gradle","groovy","gzip","h5","handlebars","haskell","hcl","hlp","htaccess","html","icns","ico","ics","ignorefile","ini","internetshortcut","ipynb","iso","jar","java","javabytecode","javascript","jinja","jp2","jpeg","json","jsonl","julia","kotlin","latex","lha","lisp","lnk","lua","m3u","m4","macho","makefile","markdown","matlab","mht","midi","mkv","mp3","mp4","mscompress","msi","mum","npy","npz","nupkg","objectivec","ocaml","odp","ods","odt","ogg","one","onnx","otf","outlook","parquet","pascal","pcap","pdb","pdf","pebin","pem","perl","php","pickle","png","po","postscript","powershell","ppt","pptx","prolog","proteindb","proto","psd","python","pythonbytecode","pytorch","qt","r","randombytes","randomtxt","rar","rdf","rpm","rst","rtf","ruby","rust","scala","scss","sevenzip","sgml","shell","smali","snap","solidity","sql","sqlite","squashfs","srt","stlbinary","stltext","sum","svg","swf","swift","tar","tcl","textproto","tga","thumbsdb","tiff","toml","torrent","tsv","ttf","twig","txt","typescript","vba","vcxproj","verilog","vhdl","vtt","vue","wasm","wav","webm","webp","winregistry","wmf","woff","woff2","xar","xls","xlsb","xlsx","xml","xpi","xz","yaml","yara","zig","zip","zlibstream"],"thresholds":{"handlebars":0.9,"ignorefile":0.95,"latex":0.95,"markdown":0.9,"ocaml":0.9,"pascal":0.95,"rst":0.9,"sql":0.9,"tsv":0.9},"overwrite_map":{"randombytes":"unknown","randomtxt":"txt"},"version_major":3}
2 changes: 1 addition & 1 deletion python/src/magika/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# limitations under the License.


__version__ = "0.6.1-rc1"
__version__ = "0.6.1-dev"


import dotenv
Expand Down
2 changes: 1 addition & 1 deletion python/src/magika/models/standard_v3_0/config.min.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"beg_size":1024,"mid_size":0,"end_size":1024,"use_inputs_at_offsets":false,"medium_confidence_threshold":0.5,"min_file_size_for_dl":8,"padding_token":256,"block_size":4096,"target_labels_space":["3gp","ace","ai","aidl","apk","applebplist","appleplist","asm","asp","autohotkey","autoit","awk","batch","bazel","bib","bmp","bzip","c","cab","cat","chm","clojure","cmake","cobol","coff","coffeescript","cpp","crt","crx","cs","csproj","css","csv","dart","deb","dex","dicom","diff","dm","dmg","doc","dockerfile","docx","dsstore","dwg","dxf","elf","elixir","emf","eml","epub","erb","erlang","flac","flv","fortran","gemfile","gemspec","gif","gitattributes","gitmodules","go","gradle","groovy","gzip","h5","handlebars","haskell","hcl","hlp","htaccess","html","icns","ico","ics","ignorefile","ini","internetshortcut","ipynb","iso","jar","java","javabytecode","javascript","jinja","jp2","jpeg","json","jsonl","julia","kotlin","latex","lha","lisp","lnk","lua","m3u","m4","macho","makefile","markdown","matlab","mht","midi","mkv","mp3","mp4","mscompress","msi","mum","npy","npz","nupkg","objectivec","ocaml","odp","ods","odt","ogg","one","onnx","otf","outlook","parquet","pascal","pcap","pdb","pdf","pebin","pem","perl","php","pickle","png","po","postscript","powershell","ppt","pptx","prolog","proteindb","proto","psd","python","pythonbytecode","pytorch","qt","r","randombytes","randomtxt","rar","rdf","rpm","rst","rtf","ruby","rust","scala","scss","sevenzip","sgml","shell","smali","snap","solidity","sql","sqlite","squashfs","srt","stlbinary","stltext","sum","svg","swf","swift","tar","tcl","textproto","tga","thumbsdb","tiff","toml","torrent","tsv","ttf","twig","txt","typescript","vba","vcxproj","verilog","vhdl","vtt","vue","wasm","wav","webm","webp","winregistry","wmf","woff","woff2","xar","xls","xlsb","xlsx","xml","xpi","xz","yaml","yara","zig","zip","zlibstream"],"thresholds":{"handlebars":0.9,"ignorefile":0.95,"latex":0.95,"markdown":0.9,"pascal":0.95},"overwrite_map":{"randombytes":"unknown","randomtxt":"txt"},"version_major":3}
{"beg_size":1024,"mid_size":0,"end_size":1024,"use_inputs_at_offsets":false,"medium_confidence_threshold":0.5,"min_file_size_for_dl":8,"padding_token":256,"block_size":4096,"target_labels_space":["3gp","ace","ai","aidl","apk","applebplist","appleplist","asm","asp","autohotkey","autoit","awk","batch","bazel","bib","bmp","bzip","c","cab","cat","chm","clojure","cmake","cobol","coff","coffeescript","cpp","crt","crx","cs","csproj","css","csv","dart","deb","dex","dicom","diff","dm","dmg","doc","dockerfile","docx","dsstore","dwg","dxf","elf","elixir","emf","eml","epub","erb","erlang","flac","flv","fortran","gemfile","gemspec","gif","gitattributes","gitmodules","go","gradle","groovy","gzip","h5","handlebars","haskell","hcl","hlp","htaccess","html","icns","ico","ics","ignorefile","ini","internetshortcut","ipynb","iso","jar","java","javabytecode","javascript","jinja","jp2","jpeg","json","jsonl","julia","kotlin","latex","lha","lisp","lnk","lua","m3u","m4","macho","makefile","markdown","matlab","mht","midi","mkv","mp3","mp4","mscompress","msi","mum","npy","npz","nupkg","objectivec","ocaml","odp","ods","odt","ogg","one","onnx","otf","outlook","parquet","pascal","pcap","pdb","pdf","pebin","pem","perl","php","pickle","png","po","postscript","powershell","ppt","pptx","prolog","proteindb","proto","psd","python","pythonbytecode","pytorch","qt","r","randombytes","randomtxt","rar","rdf","rpm","rst","rtf","ruby","rust","scala","scss","sevenzip","sgml","shell","smali","snap","solidity","sql","sqlite","squashfs","srt","stlbinary","stltext","sum","svg","swf","swift","tar","tcl","textproto","tga","thumbsdb","tiff","toml","torrent","tsv","ttf","twig","txt","typescript","vba","vcxproj","verilog","vhdl","vtt","vue","wasm","wav","webm","webp","winregistry","wmf","woff","woff2","xar","xls","xlsb","xlsx","xml","xpi","xz","yaml","yara","zig","zip","zlibstream"],"thresholds":{"handlebars":0.9,"ignorefile":0.95,"latex":0.95,"markdown":0.9,"ocaml":0.9,"pascal":0.95,"rst":0.9,"sql":0.9,"tsv":0.9},"overwrite_map":{"randombytes":"unknown","randomtxt":"txt"},"version_major":3}
2 changes: 1 addition & 1 deletion rust/lib/src/model.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ pub(crate) const CONFIG: ModelConfig = ModelConfig {
};

#[rustfmt::skip]
const THRESHOLDS: [f32; ContentType::SIZE] = [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5];
const THRESHOLDS: [f32; ContentType::SIZE] = [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.95, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.9, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5];
const OVERWRITE_MAP: [ContentType; ContentType::SIZE] = [
ContentType::_3gp,
ContentType::Ace,
Expand Down
Loading