/kka_gallery

fruit detection mainly based on faster rcnn model in pytorch

fruit-detection

fruit detection mainly based on faster rcnn model in pytorch

some results

Original outputs Outputs with group label
image image
image image
image image
image image
image image

model

The faster rcnn uses a resnet50 backbone.You can change the depth of the resnet model. Depth must be one of 18, 34, 50, 101 or 152. Note that deeper models are more accurate but are slower and use more memory.

image-outpainting

edge guided image outpainting

some results

origin input cropped_input edge_input result_without_edge result_with_edge
image image image image image
image image image image image
image image image image image
image image image image image
image image image image image
image image image image image

image-captioning

some results

input output
image a giraffe standing next to a tree in a field
image a bunch of food is on a table
image a table with a vase of flowers on the table