Why pre-trained models save time in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model from torchvision.

Computer Vision

import torchvision.models as models
model = models.[1](pretrained=True)

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

Aload

Btrain

Cresnet18

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' or 'fit' instead of a model name.

Trying to call 'load' which is not a model constructor.

The function 'resnet18' loads the ResNet-18 pre-trained model from torchvision. 'train', 'load', and 'fit' are not model names.

2fill in blank

medium

Complete the code to freeze all layers of the pre-trained model to save training time.

Computer Vision

for param in model.[1]():
    param.requires_grad = False

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

Aparameters

Bchildren

Clayers

Dmodules

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'children()' which returns submodules, not parameters.

Using 'layers()' which is not a valid method.

The 'parameters()' method returns all parameters of the model. Setting requires_grad to False freezes them.

3fill in blank

hard

Fix the error in the code to replace the last layer for transfer learning.

Computer Vision

import torch.nn as nn
model.fc = nn.[1](512, 10)

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

AConv2d

BDropout

CReLU

DLinear

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2d which is for convolutional layers.

Using activation layers like ReLU or Dropout instead of Linear.

The last layer of ResNet is a fully connected (Linear) layer. We replace it with a Linear layer with output size 10.

4fill in blank

hard

Fill both blanks to set the model to evaluation mode and disable gradient calculation.

Computer Vision

model.[1]()
with torch.[2]():
    outputs = model(inputs)

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

Aeval

Btrain

Cno_grad

Denable_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using model.train() instead of model.eval().

Using torch.enable_grad() which enables gradients.

Calling model.eval() sets the model to evaluation mode. Using torch.no_grad() disables gradient calculation to save time.

5fill in blank

hard

Fill all three blanks to create a dictionary of layer names and their requires_grad status.

Computer Vision

grad_status = {name: param.[1] for name, param in model.[2]() if name.[3]('fc') == False}

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

Arequires_grad

Bnamed_parameters

Cendswith

Dstartswith

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'parameters()' instead of 'named_parameters()' which lacks names.

Using 'endswith' instead of 'startswith' to filter layer names.

Checking 'requires_grad' incorrectly.

We check requires_grad for each parameter from named_parameters(). We exclude layers starting with 'fc' to keep them trainable.

Practice

1. Why do pre-trained models save time in computer vision projects?

easy

A. They require more data to train from scratch

B. They eliminate the need for any data preprocessing

C. They always produce perfect results without any training

D. They reuse features learned from large datasets, reducing training time

Solution

1. Step 1: Understand what pre-trained models do

   Pre-trained models have already learned useful features from large datasets, so you don't start from zero.

2. Step 2: Connect this to time saved

   Since the model already knows many features, you spend less time training it on your own data.

3. Final Answer:

   They reuse features learned from large datasets, reducing training time -> Option D

4. Quick Check:

   Pre-trained models reuse features = B [OK]

Hint: Pre-trained means already learned features reused [OK]

Common Mistakes:

• Thinking pre-trained models need more data
• Believing they need no training at all
• Assuming they remove all preprocessing

2. Which of the following is the correct way to load a pre-trained model in Python using PyTorch?

easy

A. model = torchvision.models.resnet50(pretrained=True)

B. model = torchvision.models.resnet50(pretrained=False)

C. model = torchvision.load_model('resnet50')

D. model = torch.load('resnet50_pretrained')

Solution

1. Step 1: Recall PyTorch syntax for loading pre-trained models

   In PyTorch, you use torchvision.models with pretrained=True to load a pre-trained model.

2. Step 2: Check options for correctness

   model = torchvision.models.resnet50(pretrained=True) uses the correct function and argument. model = torchvision.models.resnet50(pretrained=False) loads without pre-training. Options C and D are incorrect function calls.

3. Final Answer:

   model = torchvision.models.resnet50(pretrained=True) -> Option A

4. Quick Check:

   PyTorch pre-trained load = A [OK]

Hint: Use pretrained=True to load pre-trained models in PyTorch [OK]

Common Mistakes:

• Using pretrained=False by mistake
• Calling non-existent functions like torchvision.load_model
• Trying to load model weights incorrectly

3. Consider this Python code using TensorFlow to load a pre-trained MobileNetV2 model and predict on an input image:

import tensorflow as tf
model = tf.keras.applications.MobileNetV2(weights='imagenet')
import numpy as np
input_data = np.random.rand(1, 224, 224, 3).astype('float32')
predictions = model.predict(input_data)
print(predictions.shape)

What will be the printed output shape?

medium

A. (224, 224, 3)

B. (1, 1000)

C. (1, 224, 224, 3)

D. (1000,)

Solution

1. Step 1: Understand MobileNetV2 output shape

   MobileNetV2 pre-trained on ImageNet outputs predictions for 1000 classes, so output shape is (batch_size, 1000).

2. Step 2: Check input batch size and output

   Input batch size is 1, so output shape is (1, 1000).

3. Final Answer:

   (1, 1000) -> Option B

4. Quick Check:

   Output shape = (batch, 1000 classes) = A [OK]

Hint: Output shape matches batch size and number of classes [OK]

Common Mistakes:

• Confusing input shape with output shape
• Ignoring batch dimension
• Expecting output shape to match input image size

4. You tried to fine-tune a pre-trained model but got an error: AttributeError: 'Sequential' object has no attribute 'fc'. What is the likely cause?

medium

A. You used a model architecture without an 'fc' layer and tried to access it

B. You forgot to load pre-trained weights

C. You passed wrong input shape to the model

D. You used the wrong optimizer

Solution

1. Step 1: Understand the error message

   The error says the model has no attribute 'fc', which usually means the model architecture does not have a fully connected layer named 'fc'.

2. Step 2: Connect error to cause

   Trying to access or modify 'fc' layer on a Sequential model that doesn't have it causes this error.

3. Final Answer:

   You used a model architecture without an 'fc' layer and tried to access it -> Option A

4. Quick Check:

   Missing 'fc' layer attribute = D [OK]

Hint: Check if model has the layer before accessing it [OK]

Common Mistakes:

• Assuming all models have 'fc' layer
• Ignoring error details
• Blaming optimizer or input shape wrongly

5. You want to use a pre-trained model to classify images of cats and dogs but your dataset has only 500 images. Which approach saves the most time while achieving good accuracy?

hard

A. Use a pre-trained model without any fine-tuning and directly predict

B. Train a new model from scratch with random weights on your 500 images

C. Use a pre-trained model and fine-tune only the last layer on your dataset

D. Manually label more images before training any model

Solution

1. Step 1: Consider dataset size and training time

   With only 500 images, training from scratch is slow and likely inaccurate.

2. Step 2: Use pre-trained model fine-tuning

   Fine-tuning only the last layer uses learned features and adapts to your task quickly and efficiently.

3. Final Answer:

   Use a pre-trained model and fine-tune only the last layer on your dataset -> Option C

4. Quick Check:

   Fine-tune last layer for small data = C [OK]

Hint: Fine-tune last layer for small datasets [OK]

Common Mistakes:

• Training from scratch with little data
• Skipping fine-tuning and expecting perfect results
• Spending time labeling more data unnecessarily