MODEL EXPLORER / SKIP CONNECTIONS
The residual path
What happens where the skip path rejoins?
THE SAME MODEL, ON YOUR MACHINE
Pick up where
the graph leaves off.
Follow a wider representation through a residual block, then see why the classifier head needs the same width.
Use in VS Code ↗1. Save these files in one folder
2. Reproduce the example
Use Python 3.13 in a dedicated environment, matching the tested recipe. These commands are for macOS / Linux shells.
python3.13 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
python run.pyExpected output: [1,10]
Input: [1,64] · float32 ones · CPU / eval · seed 0
3. Open the source in TensorViz
Install the preview, open this folder in local VS Code, and choose Open as Graph above ResidualClassifier in model.py. Select your Python environment. Save before choosing Validate.
Installation and supported setup ↗
The recipe was run with Python 3.13.13 and Torch 2.7.1. This is an untrained example; a successful shape check does not measure accuracy.
ABOUT THIS EXAMPLE
Follow a wider representation through a residual block, then see why the classifier head needs the same width.
Explore the before / after change ↗Source, capture & limitations +
A small, untrained teaching model, not a ResNet implementation. The public graph is a static architecture snapshot. Recorded validation is a separate asset.
Original TensorViz teaching example. PyTorch provides the underlying operators.
No separate redistribution license has been declared for these project examples.
- Content revision
13b3cfaa26bbee6f- Source SHA-256
51202cd1fd0195075233c3ba6ecc45c6d065e0d3da33a3f87b78d7f39de4b135- Captured
- 2026-09-16 · Python 3.13.13 / Torch 2.7.1
One explicit CPU forward per version with the recorded input and seed.
Read the model manifest ↗