YOLACT ResNet 50 is a simple, fully convolutional model for real-time instance segmentation described in "YOLACT: Real-time Instance Segmentation" paper. Model pretrained in Pytorch* on COCO dataset. For details, see the repository.
Metric | Value |
---|---|
Type | Instance segmentation |
GFlops | 118.575 |
MParams | 36.829 |
Source framework | PyTorch* |
Metric | Value |
---|---|
AP@masks | 28.00% |
AP@boxes | 30.69% |
Image, name: input.1
, shape: [1x3x550x550], format: [BxCxHxW], where:
Expected color order: RGB
. Mean values - [123.675,116.28,103.53], scale values - [58.395,57.12,57.375].
Image, name: input.1
, shape: [1x3x550x550], format: [BxCxHxW], where:
Expected color order: BGR
.
conf
. Contains score distribution over all classes in the [0,1] range . The model was trained on the Microsoft* COCO dataset version with 80 categories of objects, 0 class is for background. Output shape is [1, 19248, 81] in [B, N, C] format, whereB
- batch size,N
- number of detected boxes,C
- number of classes.boxes
. Contains detection boxes coordinates in a format [y_min, x_min, y_max, x_max]
, where (x_min
, y_min
) are coordinates of the top left corner, (x_max
, y_max
) are coordinates of the right bottom corner. Coordinates are normalized in [0, 1] range. Output shape is [1, 19248, 4] in [B, N, 4] format, whereB
- batch size,N
- number of detected boxes.proto
. Contains the features projection for instance mask decoding. Output shape is [1, 138, 138, 32] in [B, H, W, C], whereB
- batch size,H
- mask height,W
- mask width,C
- channels.mask
. Contains segmentation heatmaps of detected objects for all classes for every output bounding box. Output shape is [B, N, C] format, whereB
- batch size,N
- number of detected boxes,C
- channels. Final mask prediction can be obtained by matrix multiplication of proto
and transposed mask
outputs.Converted model outputs are the same as in the original model.
The original model is distributed under the MIT license.