seqgra.evaluator.gradientbased.ebphelper module

class EBAvgPool2d

Bases: torch.autograd.function.Function

apply()

static backward(ctx, grad_output)

Defines a formula for differentiating the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs did forward() return, and it should return as many tensors, as there were inputs to forward(). Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward() will have ctx.needs_input_grad[0] = True if the first input to forward() needs gradient computated w.r.t. the output.

dirty_tensors

static forward(ctx, inp, kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True)

Performs the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by any number of arguments (tensors or other types).

The context can be used to store tensors that can be then retrieved during the backward pass.

is_traceable = False

mark_dirty(*args)

Marks given tensors as modified in an in-place operation.

This should be called at most once, only from inside the forward() method, and all arguments should be inputs.

Every tensor that’s been modified in-place in a call to forward() should be given to this function, to ensure correctness of our checks. It doesn’t matter whether the function is called before or after modification.

mark_non_differentiable(*args)

Marks outputs as non-differentiable.

This should be called at most once, only from inside the forward() method, and all arguments should be outputs.

This will mark outputs as not requiring gradients, increasing the efficiency of backward computation. You still need to accept a gradient for each output in backward(), but it’s always going to be a zero tensor with the same shape as the shape of a corresponding output.

This is used e.g. for indices returned from a max Function.

mark_shared_storage(*pairs)

materialize_grads

metadata

name()

needs_input_grad

next_functions

non_differentiable

register_hook()

requires_grad

save_for_backward(*tensors)

Saves given tensors for a future call to backward().

This should be called at most once, and only from inside the forward() method.

Later, saved tensors can be accessed through the saved_tensors attribute. Before returning them to the user, a check is made to ensure they weren’t used in any in-place operation that modified their content.

Arguments can also be None.

saved_tensors

saved_variables

set_materialize_grads(value)

Sets whether to materialize output grad tensors. Default is true.

This should be called only from inside the forward() method

If true, undefined output grad tensors will be expanded to tensors full of zeros prior to calling the backward() method.

to_save

class EBConv2d

Bases: torch.autograd.function.Function

apply()

static backward(ctx, grad_output)

Defines a formula for differentiating the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs did forward() return, and it should return as many tensors, as there were inputs to forward(). Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward() will have ctx.needs_input_grad[0] = True if the first input to forward() needs gradient computated w.r.t. the output.

dirty_tensors

static forward(ctx, inp, weight, bias, stride, padding, dilation, groups)

Performs the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by any number of arguments (tensors or other types).

The context can be used to store tensors that can be then retrieved during the backward pass.

is_traceable = False

mark_dirty(*args)

Marks given tensors as modified in an in-place operation.

This should be called at most once, only from inside the forward() method, and all arguments should be inputs.

Every tensor that’s been modified in-place in a call to forward() should be given to this function, to ensure correctness of our checks. It doesn’t matter whether the function is called before or after modification.

mark_non_differentiable(*args)

Marks outputs as non-differentiable.

This should be called at most once, only from inside the forward() method, and all arguments should be outputs.

This will mark outputs as not requiring gradients, increasing the efficiency of backward computation. You still need to accept a gradient for each output in backward(), but it’s always going to be a zero tensor with the same shape as the shape of a corresponding output.

This is used e.g. for indices returned from a max Function.

mark_shared_storage(*pairs)

materialize_grads

metadata

name()

needs_input_grad

next_functions

non_differentiable

register_hook()

requires_grad

save_for_backward(*tensors)

Saves given tensors for a future call to backward().

This should be called at most once, and only from inside the forward() method.

Later, saved tensors can be accessed through the saved_tensors attribute. Before returning them to the user, a check is made to ensure they weren’t used in any in-place operation that modified their content.

Arguments can also be None.

saved_tensors

saved_variables

set_materialize_grads(value)

Sets whether to materialize output grad tensors. Default is true.

This should be called only from inside the forward() method

If true, undefined output grad tensors will be expanded to tensors full of zeros prior to calling the backward() method.

to_save

class EBLinear

Bases: torch.autograd.function.Function

apply()

static backward(ctx, grad_output)

Defines a formula for differentiating the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs did forward() return, and it should return as many tensors, as there were inputs to forward(). Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward() will have ctx.needs_input_grad[0] = True if the first input to forward() needs gradient computated w.r.t. the output.

dirty_tensors

static forward(ctx, inp, weight, bias=None)

Performs the operation.

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by any number of arguments (tensors or other types).

The context can be used to store tensors that can be then retrieved during the backward pass.

is_traceable = False

mark_dirty(*args)

Marks given tensors as modified in an in-place operation.

This should be called at most once, only from inside the forward() method, and all arguments should be inputs.

Every tensor that’s been modified in-place in a call to forward() should be given to this function, to ensure correctness of our checks. It doesn’t matter whether the function is called before or after modification.

mark_non_differentiable(*args)

Marks outputs as non-differentiable.

This should be called at most once, only from inside the forward() method, and all arguments should be outputs.

This will mark outputs as not requiring gradients, increasing the efficiency of backward computation. You still need to accept a gradient for each output in backward(), but it’s always going to be a zero tensor with the same shape as the shape of a corresponding output.

This is used e.g. for indices returned from a max Function.

mark_shared_storage(*pairs)

materialize_grads

metadata

name()

needs_input_grad

next_functions

non_differentiable

register_hook()

requires_grad

save_for_backward(*tensors)

Saves given tensors for a future call to backward().

This should be called at most once, and only from inside the forward() method.

Later, saved tensors can be accessed through the saved_tensors attribute. Before returning them to the user, a check is made to ensure they weren’t used in any in-place operation that modified their content.

Arguments can also be None.

saved_tensors

saved_variables

set_materialize_grads(value)

Sets whether to materialize output grad tensors. Default is true.

This should be called only from inside the forward() method

If true, undefined output grad tensors will be expanded to tensors full of zeros prior to calling the backward() method.

to_save