Avs-mlrt
From Avisynth wiki
| Abstract | |
|---|---|
| Author | Asd-g |
| Version | 1.0.1 |
| Download | avs-mlrt.7z |
| Category | Multipurpose |
| License | GPLv3 |
| Discussion | |
Contents |
Description
This project provides AviSynth+ ML filter runtimes for variety of platforms.
This is a partial port of the VapourSynth plugin vs-mlrt.
To simplify usage, a wrapper mlrt.avsi is provided for all bundled models.
Custom models can be found in this doom9 thread.
Filters
- mlrt_ncnn - ncnn is a popular AI inference runtime. mlrt_ncnn provides a vulkan based runtime for some AI filters. It includes support for on-the-fly ONNX to ncnn native format conversion so as to provide a unified interface across all runtimes provided by this project.
- mlrt_ov - OpenVINO is an AI inference runtime developed by Intel, mainly targeting x86 CPUs and Intel GPUs. The mlrt_ov plugin provides optimized pure CPU & Intel GPU runtime for some popular AI filters. Intel GPU supports Gen 8+ on Broadwell+ and the Arc series GPUs.
Requirements
- Vulkan compatible device (mlrt_ncnn only)
- Intel GPU (mlrt_ov only, device="GPU" only)
- [x64]: AviSynth+ r3928 or greater (AviSynth+ 3.7.3 (test 6, r3935 can be downloaded from here)
- Microsoft VisualC++ Redistributable Package 2022 (can be downloaded from here)
Syntax and Parameters
mlrt_ncnn
- mlrt_ncnn (clip[] input, string "network_path", int "overlap_w", int "overlap_h", int "tilesize_w", int "tilesize_h", int "device_id", int "num_streams", bool "builtin", string "builtindir", bool "fp16", bool "path_is_serialization", bool "list_gpu")
- clip =
- Clips to process.
- They must be in RGB/Gray 32-bit planar format, have same dimensions and same number of frames.
- clip =
- string network_path =
- Path to the model.
- string network_path =
- int overlap_w = 0
- int overlap_w = 0
- Overlap width and overlap height of the tiles, respectively.
- Must be less than or equal to
tilesize_w/tilesize_h/ 2. - Default: 0.
- int overlap_w = 0
- int tilesize_w = input_width
- int tilesize_h = input_height
- Tile width and height, respectively.
- Use smaller value to reduce GPU memory usage.
- Must be specified when
overlap_w/overlap_h> 0. - Default: input_width, input_height.
- int tilesize_w = input_width
- int device_id =
- GPU device to use.
- By default the default device is selected.
- int device_id =
- int num_streams = 1
- GPU parallel execution.
- Default: 1.
- int num_streams = 1
- bool builtin = True
- Whether the models are in the same location with the plugin.
- Default: True.
- bool builtin = True
- string builtindir = "models"
- Root folder when
builtinis used. - Default: "models".
- Root folder when
- string builtindir = "models"
- bool fp16 = False
- Enable FP16 mode.
- Default: False.
- bool fp16 = False
- bool path_is_serialization = False
- Whether the model is serialized into one contiguous memory buffer.
- Default: False.
- bool path_is_serialization = False
- bool list_gpu = False
- Simply print a list of available GPU devices on the frame and does nothing else.
- Default: False.
- bool list_gpu = False
mlrt_ov
Download the required OpenVINO runtimes from here.
After there are few options:
- Add the extracted files to PATH.
- Place the extracted files in the same location as mlrt_ov.dll.
- (Requires LoadDLL) Create AutoLoadDll.avsi with following:
LoadDLL("path_to\tbb.dll")
LoadDLL("path_to\openvino.dll")
LoadPlugin("mlrt_ov.dll")
- mlrt_ov (clip[] input, string "network_path", int "overlap_w", int "overlap_h", int "tilesize_w", int "tilesize_h", string "device", bool "builtin", string "builtindir", bool "fp16", string "config", bool "path_is_serialization", bool "list_devices", string[] "fp16_blacklist_ops", string "dot_path")
- clip =
- Clips to process.
- They must be in RGB/Gray 32-bit planar format, have same dimensions and same number of frames.
- clip =
- string network_path =
- Path to the model.
- string network_path =
- int overlap_w = 0
- int overlap_w = 0
- Overlap width and overlap height of the tiles, respectively.
- Must be less than or equal to
tilesize_w/tilesize_h/ 2. - Default: 0.
- int overlap_w = 0
- int tilesize_w = input_width
- int tilesize_h = input_height
- Tile width and height, respectively.
- Use smaller value to reduce GPU memory usage.
- Must be specified when
overlap_w/overlap_h> 0. - Default: input_width, input_height.
- int tilesize_w = input_width
- string device = "CPU"
- Device to use - CPU or GPU.
- For example, if there are more than one GPU device, to use the first device - "GPU.0", to use the second device - "GPU.1"
- Default: "CPU".
- string device = "CPU"
- bool builtin = True
- Whether the models are in the same location with the plugin.
- Default: True.
- bool builtin = True
- string builtindir = "models"
- Root folder when
builtinis used. - Default: "models".
- Root folder when
- string builtindir = "models"
- bool fp16 = False
- Enable FP16 mode.
- Default: False.
- bool fp16 = False
- string config =
- Configuration parameters.
- CPU configuration parameters can be found here.
- GPU configuration parameters can be found here.
KEY_prefix must be omitted.- Format is:
param=value. - If more than one parameter is specified, the parameters must be separated by space.
- For example, to disable all internal CPU threading:
config="CPU_THROUGHPUT_STREAMS=0 CPU_THREADS_NUM=1 CPU_BIND_THREAD=NO"
- string config =
- bool path_is_serialization = False
- Whether the model is serialized into one contiguous memory buffer.
- Default: False.
- bool path_is_serialization = False
- bool list_devices = False
- Simply print a list of available CPU/GPU devices on the frame and does nothing else.
- Default: False.
- bool list_devices = False
- string[] fp16_blacklist_ops = ["ArrayFeatureExtractor", "Binarizer", "CastMap", "CategoryMapper", "DictVectorizer", "FeatureVectorizer", "Imputer", "LabelEncoder", "LinearClassifier", "LinearRegressor", "Normalizer", "OneHotEncoder", "SVMClassifier", "TreeEnsembleRegressor", "ZipMap", "NonMaxSuppression", "TopK", "RoiAlign", "Range", "CumSum", "Min", "Max"]
- Configurable FP16 operations black list.
- Default: ["ArrayFeatureExtractor", "Binarizer", "CastMap", "CategoryMapper", "DictVectorizer", "FeatureVectorizer", "Imputer", "LabelEncoder", "LinearClassifier", "LinearRegressor", "Normalizer", "OneHotEncoder", "SVMClassifier", "TreeEnsembleRegressor", "ZipMap", "NonMaxSuppression", "TopK", "RoiAlign", "Range", "CumSum", "Min", "Max"].
- string[] fp16_blacklist_ops = ["ArrayFeatureExtractor", "Binarizer", "CastMap", "CategoryMapper", "DictVectorizer", "FeatureVectorizer", "Imputer", "LabelEncoder", "LinearClassifier", "LinearRegressor", "Normalizer", "OneHotEncoder", "SVMClassifier", "TreeEnsembleRegressor", "ZipMap", "NonMaxSuppression", "TopK", "RoiAlign", "Range", "CumSum", "Min", "Max"]
- string dot_path =
- Path for .dot file.
- Allows to serialize to xDot format.
- string dot_path =
Examples
mlrt_ncnn Changelog
Version Date Changes
v1.0.1 2023/03/20 - Changed AviSynth+ requirements.
v1.0.0 2023/01/27 - Initial release
mlrt_ov Changelog
Version Date Changes
v1.0.0 2023/03/20 - Initial release
External Links
Back to External Filters ←
