What does mean «model» → «faster_rcnn» → «feature_extractor» → «first_stage_features_stride» in TensorFlow?

dmitrii_fediuk · May 16, 2019, 5:12am

tensorflow/models/blob/v1.13.0/research/object_detection/samples/configs/faster_rcnn_resnet101_voc07.config#L18-L18


first_stage_features_stride: 16

dmitrii_fediuk · May 16, 2019, 5:15am

github.com

tensorflow/models/blob/v1.13.0/research/object_detection/protos/faster_rcnn.proto#L179-L180


      
          // Output stride of extracted RPN feature map.
          optional int32 first_stage_features_stride = 2 [default=16];

First stage feature stride is describing what is the output stride.

stackoverflow.com/a/45343352

github.com

tensorflow/models/blob/v1.13.0/research/slim/nets/resnet_v1.py#L159-L168


      
          Training for image classification on Imagenet is usually done with [224, 224]
          inputs, resulting in [7, 7] feature maps at the output of the last ResNet
          block for the ResNets defined in [1] that have nominal stride equal to 32.
          However, for dense prediction tasks we advise that one uses inputs with
          spatial dimensions that are multiples of 32 plus 1, e.g., [321, 321]. In
          this case the feature maps at the ResNet output will have spatial shape
          [(height - 1) / output_stride + 1, (width - 1) / output_stride + 1]
          and corners exactly aligned with the input image corners, which greatly
          facilitates alignment of the features to the image. Using as input [225, 225]
          images results in [8, 8] feature maps at the output of the last ResNet block.