Faster R-CNN model

Your next task is to build a Faster R-CNN model that can detect objects of different sizes in an image. For this task, you will be using a handy class MultiScaleRoIAlign() from torchvision.ops.

FasterRCNN class has been imported from torchvision.models.detection. Your anchor_generator from the last exercise is available in your workspace and torch, torch.nn as nn, and torchvision have been imported.

This exercise is part of the course

Deep Learning for Images with PyTorch

View Course

Exercise instructions

Import MultiScaleRoIAlign from torchvision.ops.
Instantiate the RoI pooler using MultiScaleRoIAlign with featmap_names set to ["0"], output_size to 7, and sampling_ratio to 2.
Create the Faster R-CNN model passing it the backbone, num_class for a binary classification, anchor_generator, and roi_pooler.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Import MultiScaleRoIAlign
____

# Instantiate RoI pooler
roi_pooler = ____(
	____,
	____,
	____,
)

mobilenet = torchvision.models.mobilenet_v2(weights="DEFAULT")
backbone = nn.Sequential(*list(mobilenet.features.children()))
backbone.out_channels = 1280

# Create Faster R-CNN model
model = ____(
	backbone=____
	num_classes=____,
	anchor_generator=____,
	box_roi_pool=____,
)

Edit and Run Code