A Module that reads [x_t, embedding(t), c] as one row, conditioned by concatenation as in tests/diffusion_integration_test.cpp: x_t, then a sinusoidal timestep embedding (SinusoidalTimestepEmbedding), then a fixed conditioning vector such as a one-hot class. Its input relevance is split back into those three parts.
More...
#include <trajectory_lrp.hpp>
|
| | ConcatDenoiser (Module &network, int64_t dim, int64_t time_dim, std::vector< float > condition, DeviceBackend *backend, LRPRuleConfig config=TrajectoryNetworkRules()) |
| |
| void | set_condition (std::vector< float > condition) |
| | Replaces the conditioning, for instance with another class.
|
| |
| const std::vector< float > & | condition () const |
| |
| std::vector< float > | input_row (const std::vector< float > &x_t, int64_t t) const |
| | The row the network reads at timestep t.
|
| |
| std::vector< float > | predict (const std::vector< float > &x_t, int64_t t) override |
| | The predicted noise at timestep t, the same size as x_t.
|
| |
| DenoiserRelevance | relevance (const std::vector< float > &relevance_eps) override |
| | Relevance on the last predict()'s inputs, from relevance_eps on its output.
|
| |
| virtual | ~ContinuousDenoiser ()=default |
| |
A Module that reads [x_t, embedding(t), c] as one row, conditioned by concatenation as in tests/diffusion_integration_test.cpp: x_t, then a sinusoidal timestep embedding (SinusoidalTimestepEmbedding), then a fixed conditioning vector such as a one-hot class. Its input relevance is split back into those three parts.
◆ ConcatDenoiser()
- Parameters
-
| network | Maps (1, dim + time_dim + condition.size()) to (1, dim). It and the backend must outlive this. |
| config | The rules the network's relevance pass uses. |
- Exceptions
-
| std::invalid_argument | if dim <= 0 or time_dim < 0. |
◆ condition()
| const std::vector< float > & pulsatrix::ConcatDenoiser::condition |
( |
| ) |
const |
|
inline |
◆ input_row()
| std::vector< float > pulsatrix::ConcatDenoiser::input_row |
( |
const std::vector< float > & |
x_t, |
|
|
int64_t |
t |
|
) |
| const |
The row the network reads at timestep t.
◆ predict()
| std::vector< float > pulsatrix::ConcatDenoiser::predict |
( |
const std::vector< float > & |
x_t, |
|
|
int64_t |
t |
|
) |
| |
|
overridevirtual |
◆ relevance()
| DenoiserRelevance pulsatrix::ConcatDenoiser::relevance |
( |
const std::vector< float > & |
relevance_eps | ) |
|
|
overridevirtual |
◆ set_condition()
| void pulsatrix::ConcatDenoiser::set_condition |
( |
std::vector< float > |
condition | ) |
|
Replaces the conditioning, for instance with another class.
The documentation for this class was generated from the following file: