python - Is the a way for a loaded Keras Model wrapped into a KerasClassifier without fitting(No Training)

Question

def get_model():
    return load_model("model.h5")

model = KerasClassifier(build_fn = get_model)
# model.fit(X_train,y_train)

plt.figure(figsize=(10,8))
display = plot_partial_dependence(
       model, TrainX, features, fig=fig
)

I dont want to retrain the model as it will change the model that I was trying to evaluate

question from:https://stackoverflow.com/questions/65898367/is-the-a-way-for-a-loaded-keras-model-wrapped-into-a-kerasclassifier-without-fit

Answer 1

As I understand,
IF you are trying to import .h5 files of a pre-trained model and use that for the predict : then, Yes. you can

from tensorflow.keras.models import load_model

model = load_model("path to .h5 files")
## if there is a separate weight file
model.load_weights("path to weight .h5 file")

after that, you can use model variable for predictions.

but
If you are trying to see how the model is trained, then you have to get log files for a particular training instance. And use tensorboard to visualize easily.