neon.layers.layer.RoiPooling

class neon.layers.layer.RoiPooling(HW=(7, 7), bprop_enabled=True, spatial_scale=0.0625, name=None)[source]

Bases: neon.layers.layer.Layer

RoiPooling uses max pooling to convert the features inside any ROI into a small feature map with a fixed spatial extend of H x W, where H and W are layer parameters independent of any particular ROI. Each ROI is defined as a 4-tuple as (xmin, ymin, xmax, ymax)

ROIPooling is applied independently to each feature map channel, as in standard max pooling.

ROIPooling takes as input a tuple (img_fm, rois) where: (1) img_fm: output from the convolutional layers (e.g. for VGG-16, 62x62) (2) rois: proposed ROIs, in the form (rois_per_img, 5). The first index is the

image_id within the minibatch. Since faster-rcnn uses batch size 1, this is always 0.

The output shape (out_shape) is a tuple - (batch_size, rois_per_img), then the following layers will allocate buffers accordingly.

__init__(HW=(7, 7), bprop_enabled=True, spatial_scale=0.0625, name=None)[source]

Methods

__init__([HW, bprop_enabled, spatial_scale, …])
accumulates(f) Higher order decorator function that enables accumulation functionality for that function.
allocate([shared_outputs]) Allocate output buffer to store activations from fprop.
allocate_deltas(global_deltas)
bprop(error[, alpha, beta]) Apply the backward pass transformation to the input data.
configure(in_obj) Must receive a list of shapes for configurations
fprop(inputs[, inference]) Apply the forward pass transformation to the input data.
gen_class(pdict)
get_description(**kwargs)
get_is_mklop() is_mklop true means this op is on mkl backend
get_param_attrs()
get_terminal() Used for recursively getting final nodes from layer containers.
init_buffers(inputs) Initialize buffers for images and ROIs
load_weights(pdict[, load_states]) Load weights.
nested_str([level]) Utility function for displaying layer info with a given indentation level.
recursive_gen(pdict, key) helper method to check whether the definition
serialize() Get state parameters for this layer.
set_acc_on(acc_on) Set the acc_on flag according to bool argument.
set_batch_size(N) Set minibatch size.
set_deltas(delta_buffers) Use pre-allocated (by layer containers) list of buffers for backpropagated error.
set_is_mklop()
set_next(layer) Set next_layer to provided layer.
set_not_mklop()
set_params(pdict)
set_seq_len(S) Set sequence length.
set_states(pdict)
accumulates(f)

Higher order decorator function that enables accumulation functionality for that function. Object that use this decorator are required to have an acc_param attribute. This attribute tuple declares the names for existing temp parameter and real parameter buffers. The temp parameter buffer copies the value of the parameter buffer before f is called, and after f is called the temp and normal buffers are summed. This decorator could be used to wrap any function that may want to accumulate parameters instead of overwriting.

allocate(shared_outputs=None)[source]

Allocate output buffer to store activations from fprop.

Parameters:shared_outputs (Tensor, optional) – pre-allocated tensor for activations to be computed into
allocate_deltas(global_deltas)
be = None
bprop(error, alpha=1.0, beta=0.0)[source]

Apply the backward pass transformation to the input data.

Parameters:
  • error (Tensor) – deltas back propagated from the adjacent higher layer
  • alpha (float, optional) – scale to apply to input for activation gradient bprop. Defaults to 1.0
  • beta (float, optional) – scale to apply to output activation gradient bprop. Defaults to 0.0
Returns:

deltas to propagate to the adjacent lower layer

Return type:

Tensor

classnm

Returns the class name.

configure(in_obj)[source]

Must receive a list of shapes for configurations Need both the layer container and roi dataset to configure shapes ‘in_obj’ will include be [image_shape, roi_shape] (e.g [(3, 600, 1000), 5])

Parameters:in_obj

Returns:

fprop(inputs, inference=False)[source]

Apply the forward pass transformation to the input data.

Parameters:inputs (Tensor) – input data
Returns:output data
Return type:Tensor
gen_class(pdict)
get_description(**kwargs)
get_is_mklop()

is_mklop true means this op is on mkl backend and may require convert when from non-mkl op

get_param_attrs()
get_terminal()

Used for recursively getting final nodes from layer containers.

init_buffers(inputs)[source]

Initialize buffers for images and ROIs

Parameters:inputs

Returns:

load_weights(pdict, load_states=True)

Load weights.

Parameters:
  • pdict
  • load_states – (Default value = True)
modulenm

Returns the full module path.

nested_str(level=0)

Utility function for displaying layer info with a given indentation level.

Parameters:level (int, optional) – indentation level
Returns:layer info at the given indentation level
Return type:str
recursive_gen(pdict, key)

helper method to check whether the definition dictionary is defining a NervanaObject child, if so it will instantiate that object and replace the dictionary element with an instance of that object

serialize()

Get state parameters for this layer.

Returns:whatever data this model wants to receive in order to restore state
Return type:varies
set_acc_on(acc_on)

Set the acc_on flag according to bool argument. If set to true, the layer will accumulate some (preset) parameters on calls to functions that are decorated with the accumulates decorator. In order to use this feature, accumulate_updates=True must have been passed to the layer’s allocate function

This currently only works for a few hard coded parameters in select layers

Parameters:acc_on (bool) – Value to set the acc_on flag to.
set_batch_size(N)

Set minibatch size.

Parameters:N (int) – minibatch size
set_deltas(delta_buffers)

Use pre-allocated (by layer containers) list of buffers for backpropagated error. Only set deltas for layers that own their own deltas Only allocate space if layer owns its own deltas (e.g., bias and activation work in-place, so do not own their deltas).

Parameters:delta_buffers (DeltasTree) – list of pre-allocated tensors (provided by layer container)
set_is_mklop()
set_next(layer)

Set next_layer to provided layer.

Parameters:layer (layer) – Next layer
set_not_mklop()
set_params(pdict)
set_seq_len(S)

Set sequence length.

Parameters:S (int) – sequence length
set_states(pdict)