Dataset from tensors in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Dataset from tensors

Which metric matters for Dataset from tensors and WHY

When using datasets created from tensors, the key metric to watch is data integrity. This means ensuring the data you feed into your model matches what you expect in shape, type, and order. While training metrics like loss and accuracy matter for model quality, the first step is to confirm your dataset correctly represents your input data. This prevents errors and ensures your model learns from the right examples.

Confusion matrix or equivalent visualization

Since Dataset from tensors is about data input, a confusion matrix is not directly applicable here. However, you can visualize the dataset content by printing batches or samples to verify correctness.

Example dataset batch:
[
  (features: [1.0, 2.0], label: 0),
  (features: [3.0, 4.0], label: 1),
  (features: [5.0, 6.0], label: 0)
]

Precision vs Recall tradeoff with concrete examples

This concept focuses on data preparation, so precision and recall tradeoffs apply after model training. However, if your dataset from tensors is incorrect (e.g., labels mismatched), your model's precision and recall will suffer. Ensuring the dataset is accurate helps your model achieve better precision (correct positive predictions) and recall (finding all positives).

What "good" vs "bad" metric values look like for this use case

Good dataset from tensors means:

• Shapes of features and labels match expected input/output.
• Data types are consistent (e.g., float32 for features, int32 for labels).
• Data samples are correctly paired (features with correct labels).

Bad dataset from tensors means:

• Shape mismatches causing runtime errors.
• Wrong data types causing model failures.
• Misaligned features and labels leading to poor training results.

Metrics pitfalls

• Data leakage: Including test data in your tensor dataset can falsely inflate training metrics.
• Overfitting indicators: If your dataset is too small or not shuffled, the model may memorize data, showing misleadingly good training metrics but poor real-world performance.
• Incorrect batching: Not batching or batching incorrectly can cause shape errors or inefficient training.

Self-check question

Your model has 98% accuracy but only 12% recall on fraud detection. Is it good for production? Why not?

Answer: No, it is not good. High accuracy can be misleading if the dataset is imbalanced (few fraud cases). Low recall means the model misses most fraud cases, which is dangerous. For fraud detection, recall is critical to catch as many frauds as possible.

Key Result

Ensuring dataset from tensors is correctly shaped and labeled is essential for reliable model training and valid metrics.

Practice

1. What does tf.data.Dataset.from_tensor_slices() do in TensorFlow?

easy

A. It merges multiple datasets into one.

B. It converts a dataset back into tensors.

C. It creates a dataset by slicing the input tensors row-wise.

D. It shuffles the dataset randomly.

Solution

1. Step 1: Understand the function purpose

   tf.data.Dataset.from_tensor_slices() takes tensors and creates a dataset by slicing them row-wise, so each element is one slice.

2. Step 2: Compare with other options

   Options B, C, and D describe different dataset operations, not the slicing creation step.

3. Final Answer:

   It creates a dataset by slicing the input tensors row-wise. -> Option C

4. Quick Check:

   Dataset from tensor slices = row-wise slicing [OK]

Hint: Remember: from_tensor_slices splits tensors row-wise [OK]

Common Mistakes:

• Confusing from_tensor_slices with shuffling
• Thinking it merges datasets
• Assuming it converts datasets back to tensors

2. Which of the following is the correct syntax to create a dataset from a tensor data_tensor using TensorFlow?

easy

A. dataset = tf.data.Dataset.from_tensor_slices(data_tensor)

B. dataset = tf.data.Dataset.create_from_tensor(data_tensor)

C. dataset = tf.data.Dataset.tensor_slices(data_tensor)

D. dataset = tf.data.from_tensor_slices(data_tensor)

Solution

1. Step 1: Recall the correct method name

   The correct TensorFlow method to create a dataset from tensor slices is tf.data.Dataset.from_tensor_slices().

2. Step 2: Check syntax correctness

   dataset = tf.data.Dataset.from_tensor_slices(data_tensor) matches the exact syntax. Options A, B, and D use incorrect method names or missing parts.

3. Final Answer:

   dataset = tf.data.Dataset.from_tensor_slices(data_tensor) -> Option A

4. Quick Check:

   Correct method name and syntax = dataset = tf.data.Dataset.from_tensor_slices(data_tensor) [OK]

Hint: Use exact method: Dataset.from_tensor_slices() [OK]

Common Mistakes:

• Using wrong method names
• Missing Dataset class before method
• Confusing with other dataset creation functions

3. What will be the output of the following code?

import tensorflow as tf
x = tf.constant([[1, 2], [3, 4], [5, 6]])
dataset = tf.data.Dataset.from_tensor_slices(x)
for element in dataset:
    print(element.numpy())

medium

A. [[1 2]
[3 4]
[5 6]]

B. [[1], [2], [3], [4], [5], [6]]

C. [1, 2, 3, 4, 5, 6]

D. [1 2]
[3 4]
[5 6]

Solution

1. Step 1: Understand from_tensor_slices behavior

   The method slices the tensor row-wise, so each element is a 1D tensor representing one row.

2. Step 2: Analyze the loop output

   Each iteration prints one row as a numpy array, so output lines are [1 2], then [3 4], then [5 6].

3. Final Answer:

   [1 2] [3 4] [5 6] -> Option D

4. Quick Check:

   Row-wise slices printed line by line = [1 2] [3 4] [5 6] [OK]

Hint: from_tensor_slices outputs row slices printed separately [OK]

Common Mistakes:

• Expecting full tensor printed at once
• Confusing row slices with flattened output
• Assuming column-wise slicing

4. Identify the error in this code snippet:

import tensorflow as tf
x = tf.constant([1, 2, 3])
dataset = tf.data.Dataset.from_tensor_slices(x)
for element in dataset:
    print(element.numpy())
print(dataset.batch(2))

medium

A. Calling batch() after iteration does not return a new dataset.

B. print(dataset.batch(2)) prints a dataset object, not batches.

C. from_tensor_slices() requires a list, not a tensor.

D. The loop should use dataset.batch(2) instead of dataset.

Solution

1. Step 1: Understand batch() output

   The batch() method returns a new dataset object that groups elements, but printing it directly shows the object info, not the batch contents.

2. Step 2: Check what print(dataset.batch(2)) does

   It prints a dataset representation, not the actual batched data. To see batches, you must iterate over it.

3. Final Answer:

   print(dataset.batch(2)) prints a dataset object, not batches. -> Option B

4. Quick Check:

   Printing dataset.batch() shows object info, not data [OK]

Hint: Iterate to see batches; print shows object info only [OK]

Common Mistakes:

• Expecting print to show batch data
• Thinking batch modifies original dataset in place
• Confusing tensor and list input types

5. You have two tensors:

features = tf.constant([[1, 2], [3, 4], [5, 6]])
labels = tf.constant([0, 1, 0])

You want to create a dataset that pairs each feature row with its label for training. Which code correctly creates this dataset?

hard

A. dataset = tf.data.Dataset.from_tensor_slices((features, labels))

B. dataset = tf.data.Dataset.from_tensor_slices(features).zip(labels)

C. dataset = tf.data.Dataset.from_tensor_slices(features + labels)

D. dataset = tf.data.Dataset.from_tensor_slices(features).batch(labels)

Solution

1. Step 1: Understand pairing tensors in dataset

   To pair features and labels, pass a tuple of tensors to from_tensor_slices(). This creates dataset elements as (feature_row, label) pairs.

2. Step 2: Evaluate each option

   dataset = tf.data.Dataset.from_tensor_slices((features, labels)) correctly uses a tuple. dataset = tf.data.Dataset.from_tensor_slices(features).zip(labels) tries to zip a tensor, which is invalid. dataset = tf.data.Dataset.from_tensor_slices(features + labels) adds tensors incorrectly. dataset = tf.data.Dataset.from_tensor_slices(features).batch(labels) misuses batch() with labels.

3. Final Answer:

   dataset = tf.data.Dataset.from_tensor_slices((features, labels)) -> Option A

4. Quick Check:

   Tuple input pairs tensors row-wise = dataset = tf.data.Dataset.from_tensor_slices((features, labels)) [OK]

Hint: Use tuple inside from_tensor_slices to pair tensors [OK]

Common Mistakes:

• Trying to zip a tensor directly
• Adding tensors instead of pairing
• Using batch() incorrectly with labels