HeyTensor is a free, browser-based tensor shape calculator built for deep learning practitioners. Whether you are designing a new neural network architecture or debugging a frustrating shape mismatch error, HeyTensor gives you instant answers without leaving your browser.
Built by Michael Lip, Solo developer with 10+ years experience. 140+ PRs merged into open source projects including Google Chrome and Axios. $400K+ earned on Upwork with 100% Job Success. Creator of 20+ Chrome extensions.
HeyTensor supports 14 layer types across both PyTorch and TensorFlow: Conv2d, Conv1d, Linear, LSTM, GRU, MultiheadAttention, BatchNorm, MaxPool2d, AvgPool2d, Flatten, Reshape, Dropout, Transpose, and Concatenate. For each layer, it computes the exact output shape and shows the formula used.
Chain Mode lets you stack layers sequentially and see the output shape at every step. If shapes become incompatible between layers, the mismatch is highlighted immediately so you can fix it before writing any code.
Paste Error Mode accepts common PyTorch RuntimeError messages. It extracts dimension numbers from the error text and suggests which layer parameters need to change. No more staring at "mat1 and mat2 shapes cannot be multiplied" wondering which layer is wrong.
Architecture Presets include LeNet-5, a Simple CNN, a ResNet Block, a Transformer Encoder Layer, and an LSTM Classifier. Load any preset to see shape propagation through a real architecture.
All calculations run in your browser. Nothing is sent to a server. Your model architectures and error messages stay on your machine.
Email: [email protected]
GitHub: github.com/theluckystrike/heytensor.com
More tools: zovo.one
TENSOR PREFLIGHT · DOWNLOADABLE PYTORCH TOOLKIT
Trace a local forward pass, inspect tensor shapes in an HTML report, and turn a repair into a regression check. Includes eight broken-and-fixed workflows, source code and setup instructions.
Use the free calculator for a layer formula or a quick shape check.
Consider Tensor Preflight when you have a local PyTorch model and want a forward-pass report plus repeatable checks. Python 3.9+ and PyTorch 2.8+ are required. It does not run your model in this website or automatically repair it.
Open the sample report before buying to check the output format.
Python 3.9+ · PyTorch 2.8+ · Runs locally
Built on open-source foundations, explore PyTorch documentation and tensor mathematics on Wikipedia.