在xcode中使用mlmodel模型,之前说的最简单的方法是将模型拖进工程中即可,xcode会自动生成有关模型的前向预测接口,这种方式非常简单,但是更新模型就很不方便。
今天说下另外一种通过URL加载mlmodel的方式。具体可以查阅apple开发者官方文档 https://developer.apple.com/documentation/coreml/mlmodel:
流程如下:
1.提供mlmodel的文件所在路径model_path
代码语言:javascript复制NSString *model_path = "path_to/.mlmodel"
2.将NSSting类型转换为NSURL,并根据路径对模型进行编译(编译出的为.mlmodelc 文件, 这是一个临时文件,如果需要,可以将其保存到一个固定位置:https://developer.apple.com/documentation/coreml/core_ml_api/downloading_and_compiling_a_model_on_the_user_s_device)
代码语言:javascript复制NSURL *url = [NSURL fileURLWithPath:model_path isDirectory:FALSE];
NSURL *compile_url = [MLModel compileModelAtURL:url error:&error];
3.根据编译后模型所在路径,加载模型,类型为MLModel
代码语言:javascript复制MLModel *compiled_model = [MLModel modelWithContentsOfURL:compile_url configuration:model_config error:&error];
4.需要注意的是采用动态编译方式,coreml只是提供了一种代理方式MLFeatureProvider,类似于C 中的虚函数。因此需要自己重写模型输入和获取模型输出的类接口(该类继承自MLFeatureProvider)。如下自己封装的MLModelInput和MLModelOutput类。MLModelInput类可以根据模型的输入名称InputName,传递data给模型。而MLModelOutput可以根据不同的输出名称featureName获取预测结果。
这个是头文件:
代码语言:javascript复制#import <Foundation/Foundation.h>
#import <CoreML/CoreML.h>
NS_ASSUME_NONNULL_BEGIN
/// Model Prediction Input Type
API_AVAILABLE(macos(10.13), ios(11.0), watchos(4.0), tvos(11.0))
@interface MLModelInput : NSObject<MLFeatureProvider>
//the input name,default is image
@property (nonatomic, strong) NSString *inputName;
//data as color (kCVPixelFormatType_32BGRA) image buffer
@property (readwrite, nonatomic) CVPixelBufferRef data;
- (instancetype)init NS_UNAVAILABLE;
- (instancetype)initWithData:(CVPixelBufferRef)data inputName:(NSString *)inputName;
@end
API_AVAILABLE(macos(10.13), ios(11.0), watchos(4.0), tvos(11.0))
@interface MLModelOutput : NSObject<MLFeatureProvider>
//the output name, defalut is feature
@property (nonatomic, strong) NSString *outputName;
// feature as multidimensional array of doubles
@property (readwrite, nonatomic) MLMultiArray *feature;
- (instancetype)init NS_UNAVAILABLE;
- (instancetype)initWithFeature:(MLMultiArray *)feature;
@end
NS_ASSUME_NONNULL_END
这个是类方法实现的文件:
代码语言:javascript复制@implementation MLModelInput
- (instancetype)initWithData:(CVPixelBufferRef)data inputName:(nonnull NSString *)inputName {
if (self) {
_data = data;
_inputName = inputName;
}
return self;
}
- (NSSet<NSString *> *)featureNames {
return [NSSet setWithArray:@[self.inputName]];
}
- (nullable MLFeatureValue *)featureValueForName:(nonnull NSString *)featureName {
if ([featureName isEqualToString:self.inputName]) {
return [MLFeatureValue featureValueWithPixelBuffer:_data];
}
return nil;
}
@end
@implementation MLModelOutput
- (instancetype)initWithFeature:(MLMultiArray *)feature{
if (self) {
_feature = feature;
_outputName = DefalutOutputValueName;
}
return self;
}
- (NSSet<NSString *> *)featureNames{
return [NSSet setWithArray:@[self.outputName]];
}
- (nullable MLFeatureValue *)featureValueForName:(nonnull NSString *)featureName {
if ([featureName isEqualToString:self.outputName]) {
return [MLFeatureValue featureValueWithMultiArray:_feature];
}
return nil;
}
@end
5. 模型预测,获取预测结果。上面这两个类接口写完后,就可以整理输入数据为CvPixelBuffer,然后通过获取模型描述MLModelDescription得到输入名称,根据输入名称创建MLModelInput,预测,然后再根据MLModelOutput中的featureNames获取对应的预测输出数据,类型为MLMultiArray:
代码语言:javascript复制MLModelDescription *model_description = compiled_model.modelDescription;
NSDictionary *dict = model_description.inputDescriptionsByName;
NSArray<NSString *> *feature_names = [dict allKeys];
NSString *input_feature_name = feature_names[0];
NSError *error;
MLModelInput *model_input = [[MLModelInput alloc] initWithData:buffer inputName:input_feature_name];
id<MLFeatureProvider> model_output = [compiled_model predictionFromFeatures:model_input options:option error:&error];
6.读取MLMultiArray中的预测结果数据做后续处理..