TensorRT acceleration in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the TensorRT Python module.

Computer Vision

import [1]

Drag options to blanks, or click blank then click option'

Atensorrt

Btensorflow

Ccv2

Dtorch

Attempts:

3 left

💡 Hint

Common Mistakes

Importing TensorFlow or PyTorch instead of TensorRT.

Using OpenCV (cv2) which is unrelated to TensorRT.

The TensorRT Python API is accessed by importing the tensorrt module.

2fill in blank

medium

Complete the code to create a TensorRT logger with warning level.

Computer Vision

logger = tensorrt.Logger([1])

Drag options to blanks, or click blank then click option'

Atensorrt.Logger.ERROR

Btensorrt.Logger.WARNING

Ctensorrt.Logger.INFO

Dtensorrt.Logger.VERBOSE

Attempts:

3 left

💡 Hint

Common Mistakes

Using INFO or VERBOSE which produce too many messages.

Using ERROR which hides warnings.

To create a logger that shows warnings, use tensorrt.Logger.WARNING.

3fill in blank

hard

Fix the error in building a TensorRT engine from a network definition.

Computer Vision

builder = tensorrt.Builder(logger)
network = builder.create_network()
config = builder.create_builder_config()
engine = builder.[1](network, config)

Drag options to blanks, or click blank then click option'

Abuild_cuda_engine

Bbuild_engine

Ccreate_engine

Dcompile_engine

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-existent methods like 'build_engine' or 'create_engine'.

Confusing engine building with network creation.

The correct method to build an engine from a network and config is build_cuda_engine.

4fill in blank

hard

Fill both blanks to create an execution context and allocate device memory for input.

Computer Vision

context = engine.[1]()
input_memory = cuda.mem_alloc(engine.[2](0))

Drag options to blanks, or click blank then click option'

Acreate_execution_context

Bexecute

Cget_binding_shape

Dallocate_memory

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'execute' instead of creating context.

Allocating memory without knowing the correct size.

Use create_execution_context to get the context, and get_binding_shape to find input size for memory allocation.

5fill in blank

hard

Fill all three blanks to run inference and copy output from device to host.

Computer Vision

context.execute_v2(bindings=[input_memory, [1]])
cuda.memcpy_dtoh([2], [3])

Drag options to blanks, or click blank then click option'

Ainput_memory

Boutput_host

Coutput_device

Dinput_host

Attempts:

3 left

💡 Hint

Common Mistakes

Passing host memory instead of device memory in bindings.

Copying data from host to device instead of device to host.

Pass device memory pointers in bindings to execute_v2. Then copy output from device (output_device) to host (output_host).