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.

Practice

1. What does saving weights only in TensorFlow mean?

easy

A. Saving the entire model including architecture and optimizer

B. Saving just the learned parameters without the model structure

C. Saving only the model architecture without weights

D. Saving the training dataset along with the model

Solution

1. Step 1: Understand what weights represent

   Weights are the learned parameters of a model after training.

2. Step 2: Differentiate saving weights only vs full model

   Saving weights only means storing these parameters without saving the model's structure or optimizer state.

3. Final Answer:

   Saving just the learned parameters without the model structure -> Option B

4. Quick Check:

   Saving weights only = learned parameters only [OK]

Hint: Weights only means parameters, not architecture or optimizer [OK]

Common Mistakes:

• Confusing weights with full model saving
• Thinking architecture is saved with weights only
• Assuming dataset is saved with weights

2. Which of the following is the correct syntax to save only weights of a TensorFlow model named model to a file weights.h5?

easy

A. model.save_weights(weights='weights.h5')

B. model.save('weights.h5')

C. model.save_weights('weights.h5')

D. tf.save_weights(model, 'weights.h5')

Solution

1. Step 1: Recall TensorFlow method to save weights

   The method to save weights is model.save_weights(filepath).

2. Step 2: Check syntax correctness

   model.save_weights('weights.h5') uses correct method and argument format. model.save('weights.h5') saves full model, C is invalid TensorFlow syntax, A uses wrong argument name.

3. Final Answer:

   model.save_weights('weights.h5') -> Option C

4. Quick Check:

   Use model.save_weights(filepath) to save weights [OK]

Hint: Use model.save_weights('filename') to save weights only [OK]

Common Mistakes:

• Using model.save() instead of save_weights()
• Incorrect argument names or order
• Trying to use non-existent TensorFlow functions

3. Consider this code snippet:

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Dense(5, input_shape=(3,))
])
model.save_weights('w.h5')

new_model = tf.keras.Sequential([
  tf.keras.layers.Dense(5, input_shape=(3,))
])
new_model.load_weights('w.h5')
print(new_model.get_weights()[0].shape)

What will be the printed output?

medium

A. (3, 5)

B. (5, 3)

C. (5,)

D. Error: weights shape mismatch

Solution

1. Step 1: Understand model architecture

   The model has one Dense layer with 5 units and input shape (3,), so weights shape is (input_dim, units) = (3, 5).

2. Step 2: Loading weights into identical architecture

   Since new_model has the same architecture, loading weights works and weights shape remains (3, 5).

3. Final Answer:

   (3, 5) -> Option A

4. Quick Check:

   Weights shape = (input_dim, units) = (3, 5) [OK]

Hint: Weights shape = (input features, output units) in Dense layers [OK]

Common Mistakes:

• Confusing input and output dimensions order
• Assuming error when architectures match
• Expecting bias shape instead of weights

4. You saved weights using model.save_weights('w.h5'). When loading weights with new_model.load_weights('w.h5'), you get an error about mismatched shapes. What is the most likely cause?

medium

A. TensorFlow does not support loading weights from .h5 files

B. The weights file is corrupted

C. You forgot to compile the new model before loading weights

D. The new model architecture is different from the original model

Solution

1. Step 1: Understand weight loading requirements

   Weights can only be loaded if the new model has the same architecture as the original model.

2. Step 2: Analyze error cause

   Mismatched shapes error usually means layer sizes differ between saved and new model.

3. Final Answer:

   The new model architecture is different from the original model -> Option D

4. Quick Check:

   Model architectures must match to load weights [OK]

Hint: Check model architectures match before loading weights [OK]

Common Mistakes:

• Assuming file corruption without checking architecture
• Thinking compile is needed before loading weights
• Believing .h5 files are unsupported for weights

5. You want to share your trained model's learned parameters with a friend, but not the full model code. Which approach is best to save and share only the weights, and what must your friend do to use them?

hard

A. Save weights with model.save_weights(); friend recreates model architecture then loads weights

B. Save full model with model.save(); friend loads full model directly

C. Save weights as a numpy file; friend loads weights without model code

D. Save model architecture as JSON; friend loads architecture and trains from scratch

Solution

1. Step 1: Identify saving weights only method

   Use model.save_weights() to save only learned parameters without model structure.

2. Step 2: Explain how friend uses weights

   Friend must recreate the exact model architecture in code, then load weights with load_weights().

3. Final Answer:

   Save weights with model.save_weights(); friend recreates model architecture then loads weights -> Option A

4. Quick Check:

   Save weights only + recreate model to load weights [OK]

Hint: Save weights only, friend rebuilds model then loads weights [OK]

Common Mistakes:

• Thinking weights can be loaded without model code
• Confusing full model save with weights only
• Assuming JSON architecture saves weights