node_reference.md

Node Reference

Display data

Node	Description
Pt Show Size	Displays PyTorch Size object as a string.
Pt Show Text	Displays PyTorch tensor as a string. Note that the tensor is partially printed out when

IO

Node	Description
Pt Save Model	A wrapper class for saving a PyTorch model.

Miscellaneous

Node	Description
Ptn Model With Closure	A model that is followed by a closure function.

PyTorch wrapper - Arithmetic operations

Node	Description
Pt Add	Adds two PyTorch tensors.
Pt Div	Divides one PyTorch tensor by another element-wise.
Pt Floor Div	Performs element-wise floor division on two PyTorch tensors.
Pt Mul	Multiplies two PyTorch tensors element-wise.
Pt Pow	Raises one PyTorch tensor to the power of another element-wise.
Pt Remainder	Computes the element-wise remainder of division between two PyTorch tensors.
Pt Sub	Subtracts one PyTorch tensor from another.

PyTorch wrapper - Bitwise operations

Node	Description
Pt Bitwise And	Performs a bitwise AND operation on two PyTorch tensors element-wise.
Pt Bitwise Left Shift	Performs a bitwise left shift operation on two PyTorch tensors element-wise.
Pt Bitwise Not	Performs a bitwise NOT operation on a PyTorch tensor element-wise.
Pt Bitwise Or	Performs a bitwise OR operation on two PyTorch tensors element-wise.
Pt Bitwise Right Shift	Performs a bitwise right shift operation on two PyTorch tensors element-wise.
Pt Bitwise Xor	Performs a bitwise XOR operation on two PyTorch tensors element-wise.

PyTorch wrapper - Callable

Node	Description
Pt Tokenizer	The tokenizer to encode a string or a list of string to token IDs.
Ptf GELU	The GELU activation function.
Ptf LeakyReLU	The LeakyReLU activation function.
Ptf Log Softmax	The log softmax activation function.
Ptf ReLU	The ReLU activation function.
Ptf SiLU	The SiLU activation function.
Ptf Sigmoid	The sigmoid activation function.
Ptf Softmax	The softmax activation function.
Ptf Softplus	The Softplus activation function.
Ptf Tanh	The tanh activation function.

PyTorch wrapper - Comparison operations

Node	Description
Pt Eq	Tests whether two PyTorch tensors are equal element-wise.
Pt Ge	Tests whether elements in the first PyTorch tensor are greater than or equal to the corresponding elements in the second tensor.
Pt Gt	Tests whether elements in the first PyTorch tensor are greater than the corresponding elements in the second tensor.
Pt Le	Tests whether elements in the first PyTorch tensor are less than or equal to the corresponding elements in the second tensor.
Pt Lt	Tests whether elements in the first PyTorch tensor are less than the corresponding elements in the second tensor.
Pt Ne	Tests whether two PyTorch tensors are not equal element-wise.

PyTorch wrapper - Data type conversion

Node	Description
Pt To Bfloat16	Converts the input tensor's data type to bfloat16.
Pt To Float16	Converts the input tensor's data type to float16.
Pt To Float32	Converts the input tensor's data type to float32.
Pt To Float64	Converts the input tensor's data type to float64.
Pt To Int16	Converts the input tensor's data type to int16.
Pt To Int32	Converts the input tensor's data type to int32.
Pt To Int64	Converts the input tensor's data type to int64.
Pt To Int8	Converts the input tensor's data type to int8.
Pt To Uint8	Converts the input tensor's data type to uint8.

PyTorch wrapper - Distribution

Node	Description
Ptd Bernoulli	Instantiates a Bernoulli distribution object.
Ptd Beta	Instantiates a Beta distribution object.
Ptd Binomial	Instantiates a Binomial distribution object.
Ptd Categorical	Instantiates a Categorical distribution object from the input probabilities or logits. You have to specify one of them and not both.
Ptd Chi2	Instantiates a Chi-squared distribution object.
Ptd Exponential	Instantiates a Exponential distribution object.
Ptd Gamma	Instantiates a Gamma distribution object.
Ptd Normal	Instantiates a Normal distribution object.
Ptd Poisson	Instantiates a Poisson distribution object.
Ptd Student T	Instantiates a StudentT distribution object.
Ptd Uniform	Instantiates a Uniform distribution object.
Ptdm Cdf	Computes the cumulative distribution function for the input distribution.
Ptdm Cdf Tensor	Computes the cumulative distribution function for the input distribution. This nodes accepts a tensor so it can be used to compute cdf for multiple values contained in a tensor.
Ptdm Icdf	Computes the inverse of the cumulative distribution function for the input distribution.
Ptdm Icdf Tensor	Computes the inverse of cumulative distribution function for the input distribution. This nodes accepts a tensor so it can be used to compute cdf for multiple values contained in a tensor.
Ptdm Log Prob	Computes the log of probability for the input distribution.
Ptdm Log Prob Tensor	Computes the log of probability for the input distribution. This nodes accepts a tensor so it can be used to compute log of probability for multiple values contained in a tensor.
Ptdm Pdf	Computes the probability density for the input distribution.
Ptdm Pdf Tensor	Computes the probability density for the input distribution. This nodes accepts a tensor so it can be used to compute pdf for multiple values contained in a tensor.
Ptdm Pmf	Computes the probability for the input distribution.
Ptdm Pmf Tensor	Computes the probability for the input distribution. This nodes accepts a tensor so it can be used to compute pmf for multiple values contained in a tensor.
Ptdm Sample	Samples from the input distribution.

PyTorch wrapper - Image processing

Node	Description
Pt Crop	Crops a PyTorch tensor to the specified size. The input tensor must have a shape of (c, h, w) or (b, c, h, w).
Pt From Image	Casts an Image tensor as a PyTorch tensor.
Pt From Image Transpose	Casts an image tensor to a PyTorch tensor and transposes it from (H, W, C) to (C, H, W). For rank-4 inputs, the batch axis remains unchanged.
Pt Interpolate By Scale Factor	Resizes a PyTorch tensor using interpolation by scale factor. The input tensor must have a shape of (c, h, w) or (b, c, h, w).
Pt Interpolate To Size	Resizes a PyTorch tensor using interpolation. The input tensor must have a shape of (c, h, w) or (b, c, h, w).
Pt Pad	Pads a PyTorch tensor to the specified size. Padded area will be black. The input tensor must have a shape of (c, h, w) or (b, c, h, w).
Pt To Image	Casts a PyTorch tensor as an Image tensor.
Pt To Image Transpose	Casts a PyTorch tensor as an Image tensor and transposes it from (C, H, W) to (H, W, C). For rank-4 inputs, the batch axis remains unchanged.

PyTorch wrapper - Indexing and Slicing Operations

Node	Description
Pt Gather	Generates a tensor based on the index tensor using PyTorch's gather function.
Pt Index Select	Extracts elements from the input tensor along a specified dimension using an index tensor.
Pt Masked Select	Extracts elements from the input tensor whose corresponding value in masked_tens is True.
Pt Scatter	Generates a new tensor by replacing values at specified positions using an index tensor.
Pt Where	Generates a new tensor by selecting values based on a condition tensor.

PyTorch wrapper - Logical operations

Node	Description
Pt Logical And	Performs a logical AND operation on two PyTorch tensors element-wise.
Pt Logical Not	Performs a logical NOT operation on a PyTorch tensor element-wise.
Pt Logical Or	Performs a logical OR operation on two PyTorch tensors element-wise.
Pt Logical Xor	Performs a logical XOR operation on two PyTorch tensors element-wise.

PyTorch wrapper - Loss function

Node	Description
Ptn BCE Loss	A class to compute the binary cross entropy loss.
Ptn BCE With Logits Loss	A class to compute the sigmoid then binary cross entropy loss.
Ptn Cross Entropy Loss	A class to compute the cross entropy loss.
Ptn Huber Loss	A class to compute the Huber loss.
Ptn KL Div Loss	A class to compute the KL divergence loss.
Ptn L1 Loss	A class to compute the L1 loss.
Ptn MSE Loss	A class to compute the squared loss.
Ptn NLL Loss	A model to compute the negative log likelihood (NLL) loss.
Ptn Smooth L1 Loss	A class to compute the Smooth L1 loss.

PyTorch wrapper - Math operations

Node	Description
Pt Abs	Computes the absolute value of each element in a PyTorch tensor.
Pt Acos	Computes the arccosine (inverse cosine) of a PyTorch tensor element-wise.
Pt Asin	Computes the arcsine (inverse sine) of a PyTorch tensor element-wise.
Pt Atan	Computes the arc tangent (inverse tangent) of a PyTorch tensor element-wise.
Pt Cos	Computes the cosine of a PyTorch tensor element-wise.
Pt Cosh	Computes the hyperbolic cosine of a PyTorch tensor element-wise.
Pt Exp	Performs an exponential operation on a PyTorch tensor element-wise.
Pt Log	Computes the natural logarithm (log base e) of a PyTorch tensor element-wise.
Pt Neg	Computes the negation of each element in a PyTorch tensor.
Pt Sin	Computes the sine of a PyTorch tensor element-wise.
Pt Sinh	Computes the hyperbolic sine of a PyTorch tensor element-wise.
Pt Sqrt	Computes the square root of each element in a PyTorch tensor.
Pt Tan	Computes the tangent of a PyTorch tensor element-wise.
Pt Tanh	Computes the hyperbolic tangent of a PyTorch tensor element-wise.

PyTorch wrapper - Matrix operations

Node	Description
Pt Bmm	Performs batched matrix multiplication on two 3D PyTorch tensors.
Pt Einsum	Performs Tensor operations specified in the Einstein summation equation.
Pt Mat Mul	Performs matrix multiplication on two PyTorch tensors.
Pt Mm	Performs 2D matrix multiplication on two PyTorch tensors.

PyTorch wrapper - Model

Node	Description
Ptn Avg Pool 2d	An avgpool layer.
Ptn Batch Norm 2d	A normalization model to normalize over the batch and spatial axes for each channel.
Ptn Chained Model	Constructs a chained PyTorch model.
Ptn Chained Model With Attention Mask	A chained model that sequentially applies model_a and model_b,
Ptn Conv 2d	A convolutional model consisting of a single conv2d layer.
Ptn Conv Model	A convolutional model consisting of multiple convolutional layers.
Ptn Embedding	Constructs an embedding layer.
Ptn Embedding Transformer Linear	A Transformer encoder model with a linear head.
Ptn GRU	A gated recurrent unit (GRU) model consisting of one or more of a recurrent layer.
Ptn GRU Linear	A recurrent neural network (GRU) model with a linear head.
Ptn Hf Fine Tuned Classification Model	A binary classification model containing a Hugging Face pretrained Transformer model.
Ptn Hf Lora Classification Model	A binary classification model containing a Hugging Face pretrained Transformer model.
Ptn Instance Norm 2d	A normalization model to normalize elements over spatial axes within each channel for each sample.
Ptn LSTM	A long short-term memory (LSTM) model consisting of one or more of a recurrent layer.
Ptn LSTM Linear	A recurrent neural network (LSTM) model with a linear head.
Ptn Layer Norm	A normalization model to normalize elements over specified axes.
Ptn Linear	A linear model consisting of a single dense layer.
Ptn Linear Model	A linear model consisting of dense layers.
Ptn Masked Mean Pooling	Constructs a masked mean pooling layer.
Ptn Max Pool 2d	A maxpool layer.
Ptn Multihead Attention	A Multihead attention model.
Ptn Multihead Attention Custom	A Multihead attention model.
Ptn Pre Add Channel Axis	Adds a channel axis after the batch axis if the input is rank 3 (bs, h, w)
Ptn Pre Flatten	Flattens the input tensor before processing the tensor in the specified model.
Ptn RNN	A recurrent neural network (RNN) model consisting of one or more of a recurrent layer.
Ptn RNN Linear	A recurrent neural network (RNN) model with a linear head.
Ptn RNN Linear	A recurrent neural network (RNN) model with a linear head.
Ptn Residual Connection Model	A model that saves the input and add to the output of the specified model.
Ptn Residual Connection Model With Attention Mask	A model that saves the input and add to the output of the specified model.
Ptn Resnet Model	A Resnet model consisting of multiple Resnet layers.

PyTorch wrapper - Optimizer

Node	Description
Pto Adam	Instantiates the Adam optimizer.
Pto AdamW	Instantiates the AdamW optimizer.
Pto SGD	Instantiates the SGD optimizer.
Pto Simple	Instantiates the most basic optimizer to update W using the below formula:

PyTorch wrapper - Reduction operation & Summary statistics

Node	Description
Pt Argmax	Computes the indices of the maximum values of a PyTorch tensor along the specified dimension(s).
Pt Argmin	Computes the indices of the minimum values of a PyTorch tensor along the specified dimension(s).
Pt Max	Computes the maximum values of a PyTorch tensor along the specified dimension(s).
Pt Mean	Computes the mean of a PyTorch tensor along the specified dimension(s).
Pt Median	Computes the median of a PyTorch tensor along the specified dimension(s).
Pt Min	Computes the minimum values of a PyTorch tensor along the specified dimension(s).
Pt Prod	Computes the product of a PyTorch tensor along the specified dimension(s).
Pt Std	Computes the standard deviation of a PyTorch tensor along the specified dimension(s).
Pt Sum	Computes the sum of a PyTorch tensor along the specified dimension(s).
Pt Var	Computes the variance of a PyTorch tensor along the specified dimension(s).

PyTorch wrapper - Size object support

Node	Description
Pt Size	Extracts the PyTorch Size object of a PyTorch tensor using the size() method.
Pt Size Create	Creates a PyTorch Size using values entered in the text field.
Pt Size To Numpy	Converts PyTorch Size object to NumPy ndarray.
Pt Size To String	Converts PyTorch Size object to a Python string.

PyTorch wrapper - Tensor creation

Node	Description
Pt Arange	Creates a PyTorch tensor using torch.arange with the specified start, end, and step values.
Pt Bool Create	Creates a PyTorch tensor of dtype bool from True or False values entered as a list in the text field.
Pt Float Create	Creates a PyTorch tensor with 32-bit floating point precision
Pt From Latent	Casts a latent tensor as a PyTorch tensor.
Pt From Numpy	Converts a NumPy ndarray to a PyTorch tensor while preserving its data type.
Pt Full	Creates a PyTorch tensor filled with a specified value using the size entered in the text field.
Pt Int Create	Creates a PyTorch tensor with 32-bit integer
Pt Linspace	Creates a PyTorch tensor using torch.linspace with the specified start, end, and steps values.
Pt Ones	Creates a PyTorch tensor of ones using the size entered in the text field.
Pt Rand	Creates a PyTorch tensor with values sampled from a uniform distribution
Pt Rand Int	Creates a PyTorch tensor filled with random integers within a specified range using the size entered in the text field.
Pt Randn	Creates a PyTorch tensor with values sampled from a standard normal distribution (mean=0, std=1)
Pt Zeros	Creates a PyTorch tensor of zeros using the size entered in the text field.

PyTorch wrapper - Tensor data conversion

Node	Description
Pt To Latent	Casts a PyTorch tensor as a latent tensor.
Pt To Numpy	Converts PyTorch tensor to NumPy ndarray.
Pt To Rgb Tensors	Splits a PyTorch tensor into R, G, and B tensors.

PyTorch wrapper - Training

Node	Description
Hf Tokenizer Encode	Hugging Face tokenizer wrapper for encoding text into token ID tensors.
Pt Apply Function	Applies a function to the input tensor.
Pt Compute Loss	Computes loss for the input with the target using the specified loss function.
Pt Data Loader	Loads data from a dataset node and creates a PyTorch DataLoader.
Pt Data Loader From Tensors	Creates a Torchvision Dataloader from a pair of tensors.
Pt Evaluate Classification Model	Performs inference on test data and computes evaluation metrics.
Pt Load Model	A wrapper class for saving a PyTorch model.
Pt Predict Classification Model	Performs inference on input data.
Pt Predict Regression Model	Performs inference on input data.
Pt Train Classification Model	Trains a classification model using a given dataset, optimizer, and number of epochs.
Pt Train Classification Model Lr	Trains a classification model using a given dataset, optimizer, and number of epochs with learning rate decay.
Pt Train Classification Transformer Model	Trains a classification Transformer model using a given dataset, loss function, optimizer, and number of epochs with learning rate decay.
Pt Train Fine Tune Classification Transformer Model	Fine-tunes a classification Transformer model using a given dataset, loss function, optimizer, and number of epochs with learning rate decay.
Pt Train Model	Trains a model using a given dataset, loss function, optimizer, and number of epochs with learning rate decay.
Pt Train RNN Model	Trains an RNN model using a given dataset, loss function, optimizer, and number of epochs with learning rate decay.
Pt Train Regression Model	Trains a regression model using a given dataset, optimizer, and number of epochs.
Pto Lr Scheduler Cosine Annealing	Creates a cosine annealing learning rate scheduler for an optimizer.
Pto Lr Scheduler Reduce On Plateau	Creates a reduce-on-plateau learning rate scheduler for an optimizer.
Pto Lr Scheduler Step	Creates a StepLR learning rate scheduler for an optimizer.
Ptv Dataset	A Torchvision Dataset class wrapper.
Ptv Dataset Len	A wrapper class that calls Python len on a dataset.
Ptv Dataset Loader	A node to combine the dataset and data loader into a single node.
Ptv Hf Dataset With Token Encode	A PyTorch Dataset class wrapper for a Hugging Face dataset that converts text to token IDs.
Ptv Hf Glove Dataset	A PyTorch Dataset class wrapper for a Hugging Face dataset that converts text to embedding using Glove.
Ptv Hf Local Dataset	A PyTorch Dataset class wrapper for a Hugging Face dataset to load a dataset that is stored on the local file system.
Ptv Image Folder Dataset	A Torchvision ImageFolder Dataset class wrapper.
Ptv Sequential Tensor Dataset	Creates a sequential tensor Dataset.
Ptv Transforms Data Augment	Applies data augmentation transformations to dataset elements.
Ptv Transforms Resize	Resizes and transforms elements of dataset to PyTorch tensors.
Ptv Transforms To Tensor	Transforms elements of dataset to PyTorch tensors.
Sp Encode	SentencePiece wrapper for encoding text into token ID tensors.
Sp Load Model	A wrapper class for loading a SentencePiece tokenization model.

PyTorch wrapper - Transform

Node	Description
Pt Concat	Concatenates two PyTorch tensors.
Pt Flatten	Flattens a PyTorch tensor into a 1D tensor.
Pt Permute	Permutes the dimensions of a PyTorch tensor according to the specified order.
Pt Reshape	Reshapes a PyTorch tensor into a specified shape using torch.reshape().
Pt Squeeze	Removes a dimension at the specified position in the input tensor if it is of size 1.
Pt Stack	Creates a new axis and stacks two PyTorch tensors along the new axis.
Pt Unsqueeze	Adds a singleton dimension at the specified position in the input tensor.
Pt View	Reshapes a PyTorch tensor into a specified shape using torch.view().