Reshaping (view, reshape, squeeze, unsqueeze) in PyTorch - Model Pipeline Trace

Model Pipeline - Reshaping (view, reshape, squeeze, unsqueeze)

This pipeline shows how a tensor changes shape using PyTorch functions: view, reshape, squeeze, and unsqueeze. These operations help prepare data for models by changing dimensions without altering data values.

Data Flow - 5 Stages

1Input Tensor

1 row x 12 columns→Start with a 1D tensor of 12 elements→1 row x 12 columns

[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]

↓

2Reshape to 3x4

1 row x 12 columns→Use reshape(3,4) to make 3 rows and 4 columns→3 rows x 4 columns

[[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12]]

↓

3View as 4x3

3 rows x 4 columns→Use view(4,3) to change shape to 4 rows and 3 columns→4 rows x 3 columns

[[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]

↓

4Unsqueeze dimension

4 rows x 3 columns→Add a new dimension at position 1 using unsqueeze(1)→4 rows x 1 x 3 columns

[[[1, 2, 3]], [[4, 5, 6]], [[7, 8, 9]], [[10, 11, 12]]]

↓

5Squeeze dimension

4 rows x 1 x 3 columns→Remove the dimension of size 1 at position 1 using squeeze(1)→4 rows x 3 columns

[[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]

Training Trace - Epoch by Epoch

Loss
0.5 |****
0.4 |****
0.3 |***
0.2 |**
0.1 |*
    +---------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.45	0.60	Initial training with original tensor shape
2	0.35	0.70	After reshaping, model learns better structure
3	0.28	0.78	Continued improvement with correct input shape
4	0.22	0.83	Loss decreases steadily, accuracy rises
5	0.18	0.87	Model converges well with reshaped data

Prediction Trace - 5 Layers

Layer 1: Input tensor

Layer 2: reshape(3,4)

Layer 3: view(4,3)

Layer 4: unsqueeze(1)

Layer 5: squeeze(1)

Model Quiz - 3 Questions

What does the PyTorch function 'unsqueeze' do to a tensor?

A Changes the order of elements in the tensor

B Removes all dimensions of size 1

C Adds a dimension of size 1 at a specified position

D Flattens the tensor into 1D

Key Insight

Reshaping tensors correctly is crucial for machine learning models to understand data structure. Functions like view, reshape, squeeze, and unsqueeze let us change tensor shapes without changing data, enabling smooth data flow through models.