ResNet and skip connections in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - ResNet and skip connections

Which metric matters for ResNet and skip connections and WHY

For ResNet models, common metrics like accuracy and loss are important to see how well the model learns. But because ResNet is deep, watch training and validation loss to check if skip connections help avoid problems like vanishing gradients. Skip connections help the model learn better by letting information flow directly, so metrics like training speed and stable accuracy gains matter.

Confusion matrix example for ResNet image classification

      | Predicted Cat | Predicted Dog |
      |---------------|---------------|
      | True Cat: 45  | False Dog: 5  |
      | False Cat: 3  | True Dog: 47  |

      Total samples = 45 + 5 + 3 + 47 = 100

      Precision (Cat) = TP / (TP + FP) = 45 / (45 + 3) = 0.9375
      Recall (Cat) = TP / (TP + FN) = 45 / (45 + 5) = 0.9

      Precision (Dog) = 47 / (47 + 5) = 0.904
      Recall (Dog) = 47 / (47 + 3) = 0.94
    

Precision vs Recall tradeoff with ResNet

Imagine ResNet is used to detect cats in photos. If you want to be sure every cat found is really a cat, you want high precision (few false cats). But if you want to find all cats, even if some are wrong, you want high recall.

Skip connections help ResNet learn deeper features, improving both precision and recall by reducing errors from too shallow or too deep layers.

Good vs Bad metric values for ResNet

Good: Accuracy above 90%, balanced precision and recall near 90% or more, and stable training loss showing skip connections help learning.

Bad: Accuracy stuck around 50-60%, big gap between training and validation loss (overfitting), or very low recall meaning the model misses many true cases.

Common pitfalls in metrics with ResNet and skip connections

• Accuracy paradox: High accuracy but poor recall if data is unbalanced.
• Ignoring training vs validation loss differences can hide overfitting.
• Not checking if skip connections are correctly implemented can cause training to fail silently.
• Data leakage can inflate metrics falsely.

Self-check question

Your ResNet model has 98% accuracy but only 12% recall on the cat class. Is it good for production? Why or why not?

Answer: No, it is not good. The model misses most cats (low recall), so it fails to find many true cats even if overall accuracy looks high. This means it is unreliable for detecting cats.

Key Result

Skip connections in ResNet improve training stability and accuracy by enabling better gradient flow, reflected in balanced precision and recall.

Practice

1. What is the main purpose of skip connections in a ResNet model?

easy

A. To replace convolutional layers with fully connected layers

B. To reduce the number of layers in the network

C. To allow information to flow directly across layers, helping training

D. To increase the size of the input images

Solution

1. Step 1: Understand skip connections role

   Skip connections let the input bypass some layers and add directly to the output, helping information flow.

2. Step 2: Connect to training deep networks

   This helps avoid problems like vanishing gradients, making training deep networks easier and more accurate.

3. Final Answer:

   To allow information to flow directly across layers, helping training -> Option C

4. Quick Check:

   Skip connections improve training by direct flow [OK]

Hint: Skip connections let info skip layers to ease training [OK]

Common Mistakes:

• Thinking skip connections reduce layers
• Confusing skip connections with input size changes
• Assuming skip connections replace convolution

2. Which of the following is the correct way to add a skip connection in PyTorch between input tensor x and output tensor out?

easy

A. out = x - out

B. out = x * out

C. out = x / out

D. out = x + out

Solution

1. Step 1: Recall skip connection operation

   Skip connections add the input tensor to the output tensor element-wise.

2. Step 2: Match with correct syntax

   The addition operation out = x + out correctly implements the skip connection.

3. Final Answer:

   out = x + out -> Option D

4. Quick Check:

   Skip connection = addition [OK]

Hint: Skip connections use addition, not multiplication or division [OK]

Common Mistakes:

• Using multiplication instead of addition
• Using subtraction or division which breaks skip connection
• Confusing order of operands

3. Consider this PyTorch code snippet for a ResNet block:

import torch
import torch.nn as nn

class SimpleResBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 3, kernel_size=3, padding=1)
        self.relu = nn.ReLU()
        self.conv.weight.data.fill_(0.0)
        self.conv.bias.data.fill_(1.0)

    def forward(self, x):
        out = self.conv(x)
        out = self.relu(out)
        out = out + x
        return out

block = SimpleResBlock()
input_tensor = torch.ones(1, 3, 5, 5)
output = block(input_tensor)
print(output[0,0,0,0].item())

What will be printed?

medium

A. 2.0

B. 1.0

C. 0.0

D. An error occurs

Solution

1. Step 1: Analyze convolution output

   The convolution with kernel size 3 and padding 1 keeps the input size. Since input is all ones, convolution output will be some positive values (not zero).

2. Step 2: Add input and apply ReLU

   ReLU keeps positive values. Then adding input tensor (all ones) increases values. So output values > 1.

3. Final Answer:

   2.0 -> Option A

4. Quick Check:

   Output = conv + input > 1 [OK]

Hint: Skip connection adds input, so output > input value [OK]

Common Mistakes:

• Assuming output equals input without addition
• Ignoring padding effect on size
• Expecting zero or error due to shape mismatch

4. You wrote this PyTorch code for a ResNet block but get a runtime error:

def forward(self, x):
    out = self.conv(x)
    out = self.relu(out)
    out = out + x
    return out

The error says: "The size of tensor a (64) must match the size of tensor b (128) at non-singleton dimension 1." What is the likely cause?

medium

A. The convolution changes the number of channels, so shapes don't match for addition

B. ReLU changes tensor shape unexpectedly

C. Input tensor is None

D. The addition operator is used incorrectly

Solution

1. Step 1: Understand error message

   The error says channel sizes differ (64 vs 128), so tensors can't be added element-wise.

2. Step 2: Check convolution output channels

   If convolution changes channels from 64 to 128, input and output shapes differ, causing addition error.

3. Final Answer:

   The convolution changes the number of channels, so shapes don't match for addition -> Option A

4. Quick Check:

   Channel mismatch causes addition error [OK]

Hint: Check channel sizes before adding tensors [OK]

Common Mistakes:

• Blaming ReLU for shape errors
• Ignoring channel dimension mismatch
• Assuming addition works regardless of shape

5. In a ResNet architecture, if the input tensor has shape (batch_size, 64, 32, 32) and the convolution layer in the block changes channels to 128 with stride 2, how can you correctly implement the skip connection?

hard

A. Add input tensor directly without changes

B. Use a 1x1 convolution with stride 2 on the input to match shape before addition

C. Use max pooling on output tensor before addition

D. Skip connection is not needed in this case

Solution

1. Step 1: Identify shape mismatch

   Input has 64 channels and size 32x32; output has 128 channels and size 16x16 due to stride 2.

2. Step 2: Match shapes for addition

   To add tensors, input must be transformed to 128 channels and 16x16 size, done by 1x1 convolution with stride 2.

3. Final Answer:

   Use a 1x1 convolution with stride 2 on the input to match shape before addition -> Option B

4. Quick Check:

   Match shape with 1x1 conv before skip add [OK]

Hint: Use 1x1 conv to match shape for skip connection [OK]

Common Mistakes:

• Adding tensors with different shapes directly
• Using pooling on output instead of input
• Skipping skip connection when channels differ