print("KCC sub-listing: ",kcc_sublist)
#Check for KCC sub-listing
if(kcc_sublist!=0):
output_dimension=len(kcc_sublist)
else:
output_dimension=assembly_kccs
print("Process Parameter Dimension: ",output_dimension)
input_size=(voxel_dim,voxel_dim,voxel_dim,voxel_channels)
model_depth=cftrain.encode_decode_params['model_depth']
inital_filter_dim=cftrain.encode_decode_params['inital_filter_dim']
dl_model=Bayes_DLModel(model_type,output_dimension,optimizer,loss_func,regularizer_coeff,output_type)
#changed to attention model
model=dl_model.bayes_unet_model_3d_hybrid(inital_filter_dim,model_depth,categorical_kccs,voxel_dim,voxel_channels,output_heads)
print(model.summary())
#sys.exit()
#importing file names for model input
input_file_names_x=config.encode_decode_construct['input_data_files_x']
input_file_names_y=config.encode_decode_construct['input_data_files_y']
input_file_names_z=config.encode_decode_construct['input_data_files_z']
test_input_file_names_x=config.encode_decode_construct['input_test_data_files_x']
test_input_file_names_y=config.encode_decode_construct['input_test_data_files_y']
test_input_file_names_z=config.encode_decode_construct['input_test_data_files_z']
dataset.append(get_data.data_import(file_names_y, data_folder))
dataset.append(get_data.data_import(file_names_z, data_folder))
point_index = get_data.load_mapping_index(mapping_index)
#Make an Object of the Measurement System Class
measurement_system = HexagonWlsScanner(data_type, application,
system_noise, part_type,
data_format)
#Make an Object of the Assembly System Class
assembly_system = PartType(assembly_type, assembly_kccs, assembly_kpis,
part_name, part_type, voxel_dim, voxel_channels,
point_dim)
#Import model architecture
output_dimension = assembly_kccs
dl_model = Bayes_DLModel(model_type, output_dimension, optimizer,
loss_func, regularizer_coeff, output_type)
model = dl_model.bayes_cnn_model_3d(voxel_dim, voxel_channels)
#Inference from simulated data
inference_model = deploy_model.get_model(model, model_path, voxel_dim,
voxel_channels)
kcc_dataset = get_data.data_import(kcc_files, kcc_folder)
input_conv_data, kcc_subset_dump, kpi_subset_dump = get_data.data_convert_voxel_mc(
vrm_system, dataset, point_index, kcc_dataset)
y_pred = np.zeros_like(kcc_dataset)
y_pred, y_std, y_aleatoric_std = deploy_model.model_inference(
input_conv_data, inference_model, y_pred, kcc_dataset.values,
plots_path)
dataset.append(get_data.data_import(file_names_z, data_folder))
point_index = get_data.load_mapping_index(mapping_index)
#Make an Object of the Measurement System Class
measurement_system = HexagonWlsScanner(data_type, application,
system_noise, part_type,
data_format)
#Make an Object of the Assembly System Class
assembly_system = PartType(assembly_type, assembly_kccs, assembly_kpis,
part_name, part_type, voxel_dim, voxel_channels,
point_dim)
#Import model architecture
output_dimension = assembly_kccs
dl_model = Bayes_DLModel(model_type, output_dimension, optimizer,
loss_func, regularizer_coeff, output_type)
model = dl_model.bayes_cnn_model_3d_hybrid(categorical_kccs, voxel_dim,
voxel_channels)
#Inference from simulated data
inference_model = deploy_model.get_model(model, model_path, voxel_dim,
voxel_channels)
kcc_dataset = get_data.data_import(kcc_files, kcc_folder)
input_conv_data, kcc_subset_dump, kpi_subset_dump = get_data.data_convert_voxel_mc(
vrm_system, dataset, point_index, kcc_dataset)
kcc_regression, kcc_classification = hy_util.split_kcc(kcc_subset_dump)
y_out_test = [kcc_regression, kcc_classification]