CV MCQ — Chapter 19 0 Questions
CV Libraries & Frameworks

CV Libraries & Frameworks MCQ

OpenCV, PyTorch torchvision, and TensorFlow/Keras vision APIs for production workflows.

Easy: 0 Q Medium: 0 Q Hard: 0 Q

OpenCV MCQ

OpenCV essentials

OpenCV provides optimized implementations for image I/O, color conversion, geometric transforms, filtering, morphology, feature detection, and video capture. Python's cv2 wraps C++ for speed; BGR is default for historical reasons—not RGB.

BGR vs RGB

cv2.imread stores color images as BGR; swap channels before sending to libraries expecting RGB.

Key ideas

cv2.imread / imwrite

Load/save; flags control color vs grayscale.

cvtColor

BGR↔RGB, BGR↔HSV, grayscale conversions.

resize / warp

Geometry and camera-like remaps.

GaussianBlur / Canny

Smoothing and edge pipelines.

Minimal script

import cv2 → img = cv2.imread(path) → process → cv2.imshow / VideoCapture loop

Pro tip: Use cv2.waitKey for window events; release VideoCapture to avoid camera locks.

PyTorch Vision MCQ

torchvision building blocks

torchvision supplies standard vision datasets, composable transforms (including v2 on newer versions), and reference CNN implementations with optional pretrained ImageNet weights. It pairs with torch.utils.data.DataLoader for batched training and evaluation.

Normalize correctly

Use dataset-specific mean/std (e.g. ImageNet) when fine-tuning pretrained backbones.

Key ideas

datasets.ImageFolder

Folder-per-class layout for custom classification.

transforms

Resize, crop, flip, tensorize, normalize.

models.*

resnet, convnext, etc. with weights enums.

DataLoader

Batching, shuffle, num_workers for throughput.

Train loop sketch

dataset + transform → DataLoader → model → loss → optimizer.step()

Pro tip: Pin memory and multiple workers speed GPU transfer on Linux; match image size to model expectation.

TensorFlow Vision MCQ

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

Pro tip: Use mixed precision policy on supported GPUs for faster training with minimal code changes.