Fixes for NMS documentation. (#3305)

* Fixes for NMS documentation.

* Small fixes.

* Small fix.
This commit is contained in:
Vladimir Gavrilov
2020-11-25 14:05:14 +03:00
committed by GitHub
parent 56326a3d2d
commit 5767a54fa2
4 changed files with 16 additions and 14 deletions

View File

@@ -10,12 +10,12 @@
1. Take the box with highest score. If the score is less than `score_threshold` then stop. Otherwise add the box to the
output and continue to the next step.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
3. Return to step 1.
This algorithm is applied independently to each class of each batch element. The total number of output boxes for each
class must not exceed `max_output_boxes_per_class`.
class must not exceed `max_output_boxes_per_class`.
**Attributes**:
@@ -54,7 +54,7 @@ class must not exceed `max_output_boxes_per_class`.
**Outputs**:
* **1**: `selected_indices` - integer tensor of shape `[min(num_boxes, max_output_boxes_per_class * num_classes), 3]` containing information about selected boxes as triplets `[batch_index, class_index, box_index]`.
The output tensor is filled with 0s for output tensor elements if the total number of selected boxes is less than the output tensor size.
The output tensor is filled with -1s for output tensor elements if the total number of selected boxes is less than the output tensor size.
**Example**

View File

@@ -10,12 +10,12 @@
1. Take the box with highest score. If the score is less than `score_threshold` then stop. Otherwise add the box to the
output and continue to the next step.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
3. Return to step 1.
This algorithm is applied independently to each class of each batch element. The total number of output boxes for each
class must not exceed `max_output_boxes_per_class`.
class must not exceed `max_output_boxes_per_class`.
**Attributes**:
@@ -38,7 +38,7 @@ class must not exceed `max_output_boxes_per_class`.
* **Type**: boolean
* **Default value**: True
* **Required**: *no*
* *output_type*
* **Description**: the output tensor type
@@ -62,7 +62,7 @@ class must not exceed `max_output_boxes_per_class`.
**Outputs**:
* **1**: `selected_indices` - tensor of type *T_IND* and shape `[min(num_boxes, max_output_boxes_per_class * num_classes), 3]` containing information about selected boxes as triplets `[batch_index, class_index, box_index]`.
The output tensor is filled with 0s for output tensor elements if the total number of selected boxes is less than the output tensor size.
The output tensor is filled with -1s for output tensor elements if the total number of selected boxes is less than the output tensor size.
**Types**

View File

@@ -10,12 +10,12 @@
1. Take the box with highest score. If the score is less than `score_threshold` then stop. Otherwise add the box to the
output and continue to the next step.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
2. For each input box, calculate the IOU (intersection over union) with the box added during the previous step. If the
value is greater than the `iou_threshold` threshold then remove the input box from further consideration.
3. Return to step 1.
This algorithm is applied independently to each class of each batch element. The total number of output boxes for each
class must not exceed `max_output_boxes_per_class`.
class must not exceed `max_output_boxes_per_class`.
**Attributes**:
@@ -38,7 +38,7 @@ class must not exceed `max_output_boxes_per_class`.
* **Type**: boolean
* **Default value**: True
* **Required**: *no*
* *output_type*
* **Description**: the output tensor type
@@ -62,7 +62,7 @@ class must not exceed `max_output_boxes_per_class`.
**Outputs**:
* **1**: `selected_indices` - tensor of type *T_IND* and shape `[min(num_boxes, max_output_boxes_per_class) * num_batches * num_classes, 3]` containing information about selected boxes as triplets `[batch_index, class_index, box_index]`.
The output tensor is filled with 0s for output tensor elements if the total number of selected boxes is less than the output tensor size.
The output tensor is filled with -1s for output tensor elements if the total number of selected boxes is less than the output tensor size.
**Types**

View File

@@ -74,6 +74,8 @@ class must not exceed `max_output_boxes_per_class`.
* **3**: `valid_outputs` - 1D tensor with 1 element of type *T_IND* representing the total number of selected boxes. Optional.
Plugins which do not support dynamic output tensors produce `selected_indices` and `selected_scores` tensors of shape `[min(num_boxes, max_output_boxes_per_class) * num_batches * num_classes, 3]` which is an upper bound for the number of possible selected boxes. Output tensor elements following the really selected boxes are filled with value -1.
**Types**
* *T*: floating point type.