pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::SequenceHead Class Reference

A head on an encoder's representations (last_hidden_state), for fine-tuning or probing. Pooling::Mean averages each sequence's residues (not <cls>, <eos> or padding) and applies a linear layer: (N, L, hidden) to (N, outputs), for per-protein labels. Pooling::PerResidue applies it to every token: (N, L, hidden) to (N, L, outputs), for per-residue labels (use -100 targets at <cls>, <eos> and padding). More...

#include <protein_training.hpp>

Inheritance diagram for pulsatrix::SequenceHead:
Collaboration diagram for pulsatrix::SequenceHead:

Public Types

enum class  Pooling { Mean , PerResidue }
 

Public Member Functions

 SequenceHead (int64_t hidden_size, int64_t outputs, Pooling pooling, DeviceBackend *backend, uint64_t seed=0)
 The linear layer starts as transformers' heads do: weights from N(0, 0.02²), drawn from seed, and zero bias.
 
void set_residue_mask (const Tensor &residues)
 Which tokens Pooling::Mean averages: (N, L), 1 for a residue. Set it before every forward() whose shape changes; ResidueMask() builds it.
 
Tensor backward (const Tensor &grad_output) override
 Computes the gradient w.r.t. this module's input, given the gradient w.r.t. its output. Must be called after forward() – uses state cached from that call.
 
Tensor propagate_relevance (const Tensor &relevance_out, const LRPRuleConfig &config) override
 Relevance at the representations, (N, L, hidden): the linear layer's rule, then (for Mean) each residue's share of the average.
 
OpType op_type () const override
 This module's operation-category tag, for ComputationGraph node tagging.
 
std::vector< NamedParamRef > named_parameters () override
 This module's trainable parameters, each with its hierarchical name – the one place a module declares its parameters (roadmap FND-1).
 
void set_training (bool training) override
 Sets this module's training/eval mode. Defaults to training (matches every mainstream framework's Module default).
 
std::optional< DeviceType > compute_device () const override
 The device this module computes on, so forward() can reject an input on another device before any kernel sees it (roadmap FND-8).
 
void release_activations () override
 Frees the tensors forward() kept for backward() and the relevance passes; containers release their children too. Inference that only needs the output calls it after each forward, so a deep model holds one layer's activations at a time (a 1024-token ESM-2 650M pass otherwise keeps over 10 GB of them).
 
LinearModule & linear ()
 
Pooling pooling () const
 
- Public Member Functions inherited from pulsatrix::Module
virtual ~Module ()=default
 
Tensor forward (const Tensor &input)
 Runs this module's forward computation.
 
std::pair< Tensor, NodeId > forward_traced (const Tensor &input, NodeId input_node, ComputationGraph &graph, Autograd &autograd)
 Runs forward() while also registering a ComputationGraph node (tagged with this module's op_type(), parented to input_node) and wiring an Autograd backward function that reuses this module's own backward() – the opt-in traced/explainable path, per Phase 2 Mission 0.
 
virtual bool supports_lrp_rule (LRPRule rule) const
 Whether propagate_relevance() implements rule (no silent fallback: callers such as ExplainerContext::relevance_pass() throw rather than run a module on a rule it does not implement).
 
virtual std::vector< NamedBufferRef > named_buffers ()
 This module's buffers: state a checkpoint must save that no optimizer updates.
 
virtual std::vector< NamedModuleRef > named_children ()
 This module's direct sub-modules, each under the prefix its parameters carry in named_parameters(), in the same order (TRN-7: how ApplyLora() finds a model's Linear layers). Default: none. NamedModules() walks the whole tree.
 
virtual std::vector< ParamRef > parameters ()
 This module's trainable parameters and their gradients, for an optimizer to update uniformly across module types.
 
void set_requires_grad (bool requires_grad, const std::string &prefix="")
 Freezes (false) or unfreezes (true) parameters by name (roadmap FND-2).
 
bool is_training () const
 Whether this module is currently in training mode.
 

Protected Member Functions

Tensor forward_impl (const Tensor &input) override
 

Detailed Description

A head on an encoder's representations (last_hidden_state), for fine-tuning or probing. Pooling::Mean averages each sequence's residues (not <cls>, <eos> or padding) and applies a linear layer: (N, L, hidden) to (N, outputs), for per-protein labels. Pooling::PerResidue applies it to every token: (N, L, hidden) to (N, L, outputs), for per-residue labels (use -100 targets at <cls>, <eos> and padding).

Train it alone on a frozen encoder (a probe), or with it: pass backward()'s result to EncoderLM::backward_hidden(). Parameters are named linear.weight and linear.bias.

Member Enumeration Documentation

◆ Pooling

Enumerator
Mean 
PerResidue 

Constructor & Destructor Documentation

◆ SequenceHead()

pulsatrix::SequenceHead::SequenceHead ( int64_t  hidden_size,
int64_t  outputs,
Pooling  pooling,
DeviceBackend *  backend,
uint64_t  seed = 0 
)

The linear layer starts as transformers' heads do: weights from N(0, 0.02²), drawn from seed, and zero bias.

Member Function Documentation

◆ backward()

Tensor pulsatrix::SequenceHead::backward ( const Tensor &  grad_output)
overridevirtual

Computes the gradient w.r.t. this module's input, given the gradient w.r.t. its output. Must be called after forward() – uses state cached from that call.

Parameters
grad_outputGradient w.r.t. this module's output.
Returns
Gradient w.r.t. this module's input.
Note
Promoted to the base class in Phase 2 Mission 0 – every existing subclass (LinearModule/ReluModule/Conv2DModule) already implemented this exact signature independently; making it virtual lets graph-wiring code (Module::forward_traced) call it polymorphically through a Module* without knowing the concrete subclass, the same way propagate_relevance already works.

Implements pulsatrix::Module.

◆ compute_device()

std::optional< DeviceType > pulsatrix::SequenceHead::compute_device ( ) const
inlineoverridevirtual

The device this module computes on, so forward() can reject an input on another device before any kernel sees it (roadmap FND-8).

Returns
std::nullopt (the default) skips the check: a container whose layers check their own inputs, or a user module written before this existed. Every in-tree layer returns its device; EmbeddingModule doesn't, because it reads its indices through their own backend and so accepts them from any device.

Reimplemented from pulsatrix::Module.

◆ forward_impl()

Tensor pulsatrix::SequenceHead::forward_impl ( const Tensor &  input)
overrideprotectedvirtual
Exceptions
std::invalid_argumentunless the input is (N, L, hidden), or for Mean, the residue mask is set and matches (N, L).

Implements pulsatrix::Module.

◆ linear()

LinearModule & pulsatrix::SequenceHead::linear ( )
inline

◆ named_parameters()

std::vector< NamedParamRef > pulsatrix::SequenceHead::named_parameters ( )
overridevirtual

This module's trainable parameters, each with its hierarchical name – the one place a module declares its parameters (roadmap FND-1).

Returns
{name, {value, grad}} entries pointing directly at this module's own members, in a fixed order. Names are unique within the module tree. Default: empty (a parameterless module like ReluModule needs no override).
Note
Override this, not parameters(): saving, loading, freezing by name and optimizer parameter groups all key on these names.

Reimplemented from pulsatrix::Module.

◆ op_type()

OpType pulsatrix::SequenceHead::op_type ( ) const
inlineoverridevirtual

This module's operation-category tag, for ComputationGraph node tagging.

Returns
This module's OpType (see op_type.hpp's closed set).
Note
Added in Phase 2 Mission 0 alongside backward() – lets graph-wiring code tag nodes generically through a Module* rather than switching on concrete subclass.

Implements pulsatrix::Module.

◆ pooling()

Pooling pulsatrix::SequenceHead::pooling ( ) const
inline

◆ propagate_relevance()

Tensor pulsatrix::SequenceHead::propagate_relevance ( const Tensor &  relevance_out,
const LRPRuleConfig &  config 
)
overridevirtual

Relevance at the representations, (N, L, hidden): the linear layer's rule, then (for Mean) each residue's share of the average.

Implements pulsatrix::Module.

◆ release_activations()

void pulsatrix::SequenceHead::release_activations ( )
overridevirtual

Frees the tensors forward() kept for backward() and the relevance passes; containers release their children too. Inference that only needs the output calls it after each forward, so a deep model holds one layer's activations at a time (a 1024-token ESM-2 650M pass otherwise keeps over 10 GB of them).

Note
Until the next forward(), backward() and relevance calls are invalid. The default has nothing to free.

Reimplemented from pulsatrix::Module.

◆ set_residue_mask()

void pulsatrix::SequenceHead::set_residue_mask ( const Tensor &  residues)

Which tokens Pooling::Mean averages: (N, L), 1 for a residue. Set it before every forward() whose shape changes; ResidueMask() builds it.

◆ set_training()

void pulsatrix::SequenceHead::set_training ( bool  training)
overridevirtual

Sets this module's training/eval mode. Defaults to training (matches every mainstream framework's Module default).

Note
Virtual since Phase 6 Mission 6 (SequentialModule) – Mission 5 originally shipped this as plain non-virtual state ("no composite container exists yet to cascade through"); SequentialModule overrides this to cascade to every contained layer, and needs virtual dispatch to do so correctly even when accessed through a Module* base pointer, not just its own concrete type.
BatchNormModule keeps running statistics in training mode and normalizes with them in eval mode; DropoutModule is the identity in eval mode. Call set_training(false) before explaining a model that has either, so a sample's explanation doesn't depend on the rest of its batch.

Reimplemented from pulsatrix::Module.


The documentation for this class was generated from the following file: