I am trying to create a Pipeline with 3 sub-models: a Feature Vectorizer -> a NN regressor converted from PyTorch -> a Feature Extractor (to convert the output tensor to a Double value).
The pipeline works fine when I use just a Vectorizer and an Extractor, this is the code:
vectorizer = models.feature_vectorizer.create_feature_vectorizer(
input_features=["windSpeed", "theoreticalPowerCurve", "windDirection"], # Multiple input features
output_feature_name="input"
)
preProc_spec = vectorizer[0]
ct.utils.convert_double_to_float_multiarray_type(preProc_spec)
extractor = models.array_feature_extractor.create_array_feature_extractor(
input_features=[("input",datatypes.Array(3,))], # Multiple input features
output_name="output",
extract_indices = 1
)
ct.utils.convert_double_to_float_multiarray_type(extractor)
pipeline_network = pipeline.PipelineRegressor (
input_features = ["windSpeed", "theoreticalPowerCurve", "windDirection"],
output_features=["output"]
)
pipeline_network.add_model(preProc_spec)
pipeline_network.add_model(extractor)
ct.utils.convert_double_to_float_multiarray_type(pipeline_network.spec)
ct.utils.save_spec(pipeline_network.spec,"Final.mlpackage")
This model works ok. I created a regression NN using PyTorch and converted to Core ML either
import torch
import torch.nn as nn
class TurbinePowerModel(nn.Module):
def __init__(self):
super().__init__()
self.linear1 = nn.Linear(3, 4)
self.activation1 = nn.ReLU()
#self.linear2 = nn.Linear(5, 4)
#self.activation2 = nn.ReLU()
self.output = nn.Linear(4, 1)
def forward(self, x):
#x = F.normalize(x, dim = 0)
x = self.linear1(x)
x = self.activation1(x)
# x = self.linear2(x)
# x = self.activation2(x)
x = self.output(x)
return x
def forward_inference(self, windSpeed,theoreticalPowerCurve,windDirection):
input_tensor = torch.tensor([windSpeed,
theoreticalPowerCurve,
windDirection], dtype=torch.float32)
return self.forward(input_tensor)
model = torch.load('TurbinePowerRegression-1layer.pt', weights_only=False)
import coremltools as ct
print(ct.__version__)
import pandas as pd
from sklearn.preprocessing import StandardScaler
df = pd.read_csv('T1_clean.csv',delimiter=';')
X = df[['WindSpeed','TheoreticalPowerCurve','WindDirection']]
y = df[['ActivePower']]
scaler = StandardScaler()
X = scaler.fit_transform(X)
y = scaler.fit_transform(y)
X_tensor = torch.tensor(X, dtype=torch.float32)
y_tensor = torch.tensor(y, dtype=torch.float32)
traced_model = torch.jit.trace(model, X_tensor[0])
mlmodel = ct.convert(
traced_model,
inputs=[ct.TensorType(name="input", shape=X_tensor[0].shape)],
classifier_config=None # Optional, for classification tasks
)
mlmodel.save("TurbineBase.mlpackage")
This model has a Multiarray(Float 32 3) as input and a Multiarray(Float32 1) as output.
When I try to include it in the middle of the pipeline (Adjusting the output and input types of the other models accordingly), the process runs ok, but I have the following error when opening the generated model on Xcode:
What's is missing on the models. How can I set or adjust this metadata properly?
Thanks!!!
