TensorFlow Vision MCQ
tf.data pipelines, `keras.applications`, and preprocessing layers integrated in the TF/Keras 2 workflow.
TF / Keras
Stack
tf.data
Pipeline
Applications
Xception…
SavedModel
Serve
TensorFlow for vision
Use tf.data.Dataset to build efficient input pipelines (map, batch, prefetch). keras.applications provides pretrained CNNs; preprocessing can live in the model via Rescaling / RandomFlip layers for export-friendly graphs. SavedModel packages inference for TF Serving and mobile converters.
Augment in the graph
Keras preprocessing layers keep train and serve transforms aligned when exported.
Key ideas
tf.data
from_tensor_slices, map, batch, prefetch to device.
Rescaling / Augment
Layers for resize, flip, rotate in-model.
applications
ResNet50(include_top=False) feature extractor.
SavedModel
Signatures for serving and TFLite conversion.
Fine-tune pattern
base = Xception(weights='imagenet', include_top=False) → GlobalAveragePooling2D → Dense