Model Config¶
-
class
ModelConfig(model_json, base_dir=None, labels=None, colors=None)¶ The model configuration parameters.
- Parameters
model_json (
dict) – The parsed alwaysai.model.json.labels (
Optional[List[str]]) – The label list for the model.colors (
Optional[ndarray]) – The color list for the model.
-
classmethod
from_model_id(model_id)¶ - Return type
ModelConfig
-
property
config¶ The config loaded from the model JSON file
- Return type
dict
-
property
model_parameters¶ The model parameters in the config
- Return type
dict
-
property
id¶ The model ID
- Return type
str
-
property
label_file¶ Path to the label file
- Return type
Optional[str]
-
property
colors_file¶ Path to the colors file
- Return type
Optional[str]
-
property
model_file¶ Path to the model weights file
- Return type
str
-
property
config_file¶ Relative path to the model framework config file
- Return type
Optional[str]
-
property
mean¶ The RGB/BGR mean values for the model
- Return type
Tuple[float,float,float]
-
property
scalefactor¶ The scale factor for the model input
- Return type
float
-
property
size¶ The input image size of the model
- Return type
Tuple[int,int]
-
property
purpose¶ The purpose of the model
- Return type
SupportedPurposes
-
property
framework_type¶ The framework type of the model
- Return type
str
-
property
crop¶ Whether or not to crop the image prior to inferencing
- Return type
bool
-
property
colors_dtype¶ The data type of the color values
- Return type
str
-
property
labels¶ The labels of the model
- Return type
Optional[List[str]]
-
property
colors¶ The colors for each label of the model.
Each array element is a 3 dimensional array of 8 bit integers representing red, green, and blue
- Return type
Optional[ndarray]
-
property
swaprb¶ Whether to swap the red and blue channels of the image prior to inference
- Return type
bool
-
property
architecture¶ The architecture of the model
- Return type
Optional[str]
-
property
softmax¶ Whether to perform softmax after the inference
- Return type
bool
-
property
device¶ The device the model was built for
- Return type
Optional[SupportedDevices]
-
property
output_layer_names¶ The output layer names of the model
- Return type
Optional[List[str]]
-
property
hailo_quantize_input¶ Whether to quantize input of Hailo model
- Return type
Optional[bool]
-
property
hailo_quantize_output¶ Whether to quantize output of Hailo model
- Return type
Optional[bool]
-
property
hailo_input_format¶ Input format for Hailo model
- Return type
Optional[str]
-
property
hailo_output_format¶ Output format of Hailo model
- Return type
Optional[str]
-
property
dnn_support¶ Whether DNN Engine supports the model
- Return type
bool
-
property
dnn_cuda_support¶ Whether DNN CUDA Engine supports the model
- Return type
bool
-
property
tensor_rt_support¶ Whether TensorRT Engine supports the model
- Return type
bool
-
property
hailo_support¶ Whether Hailo RT Engine supports the model
- Return type
bool
-
property
qaic_support¶ Whether QAIC RT Engine supports the model
- Return type
bool
-
property
onnx_rt_support¶ Whether ONNX RT Engine supports the model
- Return type
bool
-
property
pytorch_support¶ Whether PYTORCH Engine supports the model
- Return type
bool
-
property
batch_size¶ Inference batch size of model
- Return type
int
-
property
hub_repo¶ Torch hub repo
- Return type
Optional[str]
-
property
hub_model¶ Torch hub model
- Return type
Optional[str]
-
property
hub_pretrained¶ Torch pretrained model
- Return type
Optional[bool]
-
property
hub_force_reload¶ Torch force reload the model
- Return type
Optional[bool]