Saving weights only in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this TensorFlow code snippet?

Consider the following code that creates a simple model, saves only its weights, then reloads them. What will be printed?

TensorFlow

import tensorflow as tf
import numpy as np

model = tf.keras.Sequential([
    tf.keras.layers.Dense(2, input_shape=(3,), activation='relu')
])

model.compile(optimizer='adam', loss='mse')

# Train on dummy data
x = np.array([[1, 2, 3]])
y = np.array([[1, 0]])
model.fit(x, y, epochs=1, verbose=0)

# Save weights
model.save_weights('weights_only.ckpt')

# Create new model instance
new_model = tf.keras.Sequential([
    tf.keras.layers.Dense(2, input_shape=(3,), activation='relu')
])

# Load weights
new_model.load_weights('weights_only.ckpt')

# Predict with new model
pred = new_model.predict(x)
print(pred)

A [[0.5 0.1]] (approximate values, non-zero output)

B [[0. 0.]] (all zeros output)

C Raises ValueError due to shape mismatch

D Raises FileNotFoundError because weights file missing

💡 Hint

Weights saved and loaded correctly should produce similar predictions.

The weights are saved and loaded correctly, so the new model produces similar non-zero predictions after loading weights.

❓ Model Choice

intermediate

Which model architecture is compatible for loading saved weights?

You saved weights from a model with layers: Dense(4, input_shape=(5,)), Dense(2). Which new model can load these weights without error?

A Sequential model with Dense(4, input_shape=(5,)) followed by Dense(3)

B Sequential model with Dense(4, input_shape=(4,)) followed by Dense(2)

C Sequential model with Dense(5, input_shape=(5,)) followed by Dense(2)

D Sequential model with Dense(4, input_shape=(5,)) followed by Dense(2)

💡 Hint

The architecture must match exactly to load weights.

Weights can only be loaded if the new model has the exact same layer sizes and input shapes as the original model.

❓ Hyperparameter

advanced

What happens if you save weights before training?

You create a model and immediately save its weights before any training. What will the saved weights represent?

A Weights with NaN values causing errors on load

B Weights all set to zero

C Randomly initialized weights as per the layer initializers

D Weights from a previously trained model

💡 Hint

Model weights start with initial random values before training.

Before training, model weights are initialized randomly (or as per the initializer), so saving weights at this point saves these initial values.

🔧 Debug

advanced

Why does loading weights fail with this error?

You saved weights from a model with layers: Dense(3, input_shape=(2,)), Dense(1). Now you try to load weights into a model with layers: Dense(3, input_shape=(3,)), Dense(1). The error is: ValueError: Layer weight shape mismatch. What caused this?

A Input shape of the first layer differs between saved and new model

B Number of layers differs between saved and new model

C Activation functions differ between saved and new model

D Optimizer settings differ between saved and new model

💡 Hint

Weights depend on layer input and output sizes.

Weights shape depends on input and output dimensions. Changing input shape changes weight shapes, causing mismatch errors.

🧠 Conceptual

expert

Why save only weights instead of the full model?

Which is the main advantage of saving only the weights of a TensorFlow model instead of the entire model?

A Weights files are smaller and allow flexible model architecture changes when reloading

B Weights files are smaller and faster to save/load but require the same architecture to reload

C Weights files include optimizer state and training configuration for exact resuming

D Weights files can be loaded into any model regardless of architecture

💡 Hint

Weights alone do not store model architecture or optimizer info.

Saving only weights produces smaller files and faster save/load, but requires the same model architecture to reload weights correctly.