Dataset from files in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Dataset from files

Which metric matters for Dataset from files and WHY

When working with datasets loaded from files, the key metric is data loading efficiency. This means how fast and correctly the data is read and prepared for training. If data loading is slow or incorrect, the model training will be delayed or produce wrong results. While this is not a model accuracy metric, it is critical to ensure the data pipeline works well before training.

Once the dataset is loaded, usual model metrics like accuracy, loss, precision, and recall become important to evaluate the model trained on that data.

Confusion matrix or equivalent visualization

For dataset loading, there is no confusion matrix. But to check data correctness, you can visualize samples or check batch shapes.

Example batch shape: (batch_size, image_height, image_width, channels)
Example labels shape: (batch_size,)

For classification tasks, after training, a confusion matrix shows how many samples were correctly or incorrectly classified.

Precision vs Recall tradeoff with concrete examples

This section is about model evaluation, not dataset loading. But if dataset loading causes errors (like wrong labels), it will hurt both precision and recall.

For example, if labels are mixed up during loading, the model may have low precision (many false positives) and low recall (many false negatives).

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

Good dataset loading:

• Fast loading speed matching training needs
• Correct data shapes and types
• No missing or corrupted samples
• Labels correctly matched to data

Bad dataset loading:

• Slow loading causing training delays
• Shape mismatches causing errors
• Corrupted or missing data samples
• Incorrect labels causing poor model performance

Metrics pitfalls

• Data leakage: Loading test data into training set by mistake can cause overly optimistic metrics.
• Overfitting indicators: If dataset loading is inconsistent, model may overfit on wrong data.
• Incorrect preprocessing: Not normalizing or augmenting data properly during loading can hurt model accuracy.
• Batch size mismatch: Loading batches with wrong size or shape causes training errors.

Self-check question

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

Answer: No, it is not good. The low recall means the model misses many fraud cases, which is dangerous. High accuracy can be misleading if the dataset is imbalanced (few fraud cases). You need to improve recall to catch more fraud.

Key Result

Efficient and correct dataset loading is essential to enable reliable model training and accurate evaluation.

Practice

1. What is the main purpose of using tf.data.Dataset.from_tensor_slices() with file paths in TensorFlow?

easy

A. To convert tensors into image files

B. To directly read image data from files into memory

C. To save datasets to disk as files

D. To create a dataset that holds file paths which can be read later

Solution

1. Step 1: Understand the function purpose

   tf.data.Dataset.from_tensor_slices() creates a dataset from a tensor, often a list of file paths, not the file contents themselves.

2. Step 2: Clarify dataset content

   The dataset holds file paths as strings, which can be mapped later to read actual file data.

3. Final Answer:

   To create a dataset that holds file paths which can be read later -> Option D

4. Quick Check:

   from_tensor_slices(file_paths) = dataset of paths [OK]

Hint: Remember: from_tensor_slices holds paths, not file data [OK]

Common Mistakes:

• Thinking it reads file contents immediately
• Confusing dataset creation with saving files
• Assuming it converts tensors to images

2. Which of the following is the correct way to create a dataset from a list of image file paths in TensorFlow?

easy

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

B. dataset = tf.data.Dataset.read_files(image_paths)

C. dataset = tf.data.Dataset.load(image_paths)

D. dataset = tf.data.Dataset.create(image_paths)

Solution

1. Step 1: Recall correct TensorFlow method

   The method to create a dataset from a list of tensors (like file paths) is from_tensor_slices().

2. Step 2: Verify options

   Methods like tf.data.Dataset.load(), tf.data.Dataset.read_files(), and tf.data.Dataset.create() are not valid TensorFlow dataset creation methods.

3. Final Answer:

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

4. Quick Check:

   Correct method is from_tensor_slices [OK]

Hint: Use from_tensor_slices for lists of file paths [OK]

Common Mistakes:

• Using non-existent methods like read_files or load
• Confusing dataset creation with file reading
• Misspelling method names

3. Given the code below, what will be the output when iterating over the dataset?

import tensorflow as tf
image_paths = ["img1.jpg", "img2.jpg"]
dataset = tf.data.Dataset.from_tensor_slices(image_paths)
for item in dataset:
    print(item.numpy().decode())

medium

A. Error: decode() not found

B. [b'img1.jpg', b'img2.jpg']

C. img1.jpg\nimg2.jpg

D. Tensor objects printed

Solution

1. Step 1: Understand dataset content

   The dataset contains string tensors of file paths: b'img1.jpg', b'img2.jpg'.

2. Step 2: Decode bytes to string

   Calling item.numpy() returns bytes, and decode() converts bytes to normal strings.

3. Final Answer:

   img1.jpg\nimg2.jpg -> Option C

4. Quick Check:

   Decoded bytes = file names [OK]

Hint: Use .numpy().decode() to get string from tensor [OK]

Common Mistakes:

• Printing tensor directly without decoding
• Expecting list output instead of individual prints
• Confusing bytes and strings

4. Identify the error in the following code snippet that tries to read image files from paths:

import tensorflow as tf
image_paths = ["img1.jpg", "img2.jpg"]
dataset = tf.data.Dataset.from_tensor_slices(image_paths)
dataset = dataset.map(tf.io.read_file)
for img in dataset:
    print(img.numpy().shape)

medium

A. Cannot print shape of a scalar string tensor

B. tf.io.read_file is not a valid function

C. from_tensor_slices requires a tensor, not list

D. map() cannot be used on datasets

Solution

1. Step 1: Analyze dataset after map

   After mapping tf.io.read_file, each element is a scalar string tensor containing raw file bytes.

2. Step 2: Understand tensor shape

   img.numpy() returns Python bytes (raw file content), which has no .shape attribute. Printing img.numpy().shape raises AttributeError.

3. Final Answer:

   Cannot print shape of a scalar string tensor -> Option A

4. Quick Check:

   img.numpy() is bytes; no .shape [OK]

Hint: Raw file bytes are scalars; no shape attribute [OK]

Common Mistakes:

• Assuming read_file returns image tensor
• Thinking from_tensor_slices rejects lists
• Believing map() is invalid on datasets

5. You want to create a TensorFlow dataset from a folder of images, resize each image to 128x128, and batch them in groups of 16. Which code snippet correctly achieves this?

hard

A. dataset = tf.keras.utils.image_dataset_from_directory('images', image_size=(128,128), batch_size=16)

B. dataset = tf.data.Dataset.list_files('images/*').map(lambda x: tf.image.resize(tf.io.decode_image(tf.io.read_file(x)), (128,128))).batch(16)

C. dataset = tf.data.Dataset.from_tensor_slices('images').map(tf.io.read_file).batch(16)

D. dataset = tf.keras.preprocessing.image_dataset_from_directory('images', batch_size=128, image_size=(16,16))

Solution

1. Step 1: Understand dataset creation from folder

   dataset = tf.data.Dataset.list_files('images/*').map(lambda x: tf.image.resize(tf.io.decode_image(tf.io.read_file(x)), (128,128))).batch(16) uses list_files to get file paths, then maps reading, decoding, and resizing images correctly.

2. Step 2: Check batch and resize parameters

   Images are resized to (128,128) and batched in groups of 16 as required.

3. Final Answer:

   dataset = tf.data.Dataset.list_files('images/*').map(lambda x: tf.image.resize(tf.io.decode_image(tf.io.read_file(x)), (128,128))).batch(16) -> Option B

4. Quick Check:

   list_files + map + resize + batch = correct pipeline [OK]

Hint: Use list_files + map with decode and resize, then batch [OK]

Common Mistakes:

• Using wrong batch size or image size parameters
• Confusing keras and tf.data APIs
• Not decoding images before resizing