def test_model_evaluate_method():
model = Model()
model.set_model(pytorch_model)
model.compile(optimizer=Adam(), loss_function=MSELoss())
TrainLogger("ignore/")
test_gen = train_generator()
model.fit(
train_data=(X_train, y_train),
validation_data=(X_validation, y_validation),
epochs=1,
batch_size=32,
)
model.evaluate(test_data=(X_test, y_test))
model.evaluate(test_data=(X_test, y_test), batch_size=4)
model.evaluate(test_data=test_gen, batch_size=4, tests_steps=4)
with pytest.raises(ValueError):
model.evaluate(test_data=(X_test, y_test), batch_size=400)
X_validation = X[int(len(X)*train_data_size):]
y_validation = y[int(len(y)*train_data_size):]
print("Size of Train data is", len(X_train))
print("Size of Validation data is ", len(X_validation))
print("Size of Test data is ", len(X_test))
# Making the model
# Initializing the PyTorch model
p_model = MNISTModel()
# Initializing a NeuralPy model
model = Model()
# Converting the PyTorch model to NeuralPy model
model.set_model(p_model)
# Printing the summary of the model
print(model.summary())
# Compiling the model
model.compile(optimizer=Adam(), loss_function=CrossEntropyLoss(), metrics=["accuracy"])
# Training the model
# Using the fit method
history = model.fit(train_data=(X_train, y_train), test_data=(X_validation, y_validation), epochs=10, batch_size=32)
# Evaluating the model
ev = model.evaluate(X=X_test, y=y_test, batch_size=32)
print(f"Loss: {ev['loss']} and accuracy: {ev['accuracy']}%")