|
""" |
|
Using as reference: |
|
- https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512 |
|
- https://huggingface.co/spaces/chansung/segformer-tf-transformers/blob/main/app.py |
|
- https://huggingface.co/facebook/detr-resnet-50-panoptic |
|
""" |
|
|
|
from transformers import DetrFeatureExtractor, DetrForSegmentation |
|
from PIL import Image |
|
import gradio as gr |
|
import numpy as np |
|
import torch |
|
import torchvision |
|
|
|
|
|
|
|
def ade_palette(): |
|
"""ADE20K palette that maps each class to RGB values.""" |
|
return [ |
|
[120, 120, 120], |
|
[180, 120, 120], |
|
[6, 230, 230], |
|
[80, 50, 50], |
|
[4, 200, 3], |
|
[120, 120, 80], |
|
[140, 140, 140], |
|
[204, 5, 255], |
|
[230, 230, 230], |
|
[4, 250, 7], |
|
[224, 5, 255], |
|
[235, 255, 7], |
|
[150, 5, 61], |
|
[120, 120, 70], |
|
[8, 255, 51], |
|
[255, 6, 82], |
|
[143, 255, 140], |
|
[204, 255, 4], |
|
[255, 51, 7], |
|
[204, 70, 3], |
|
[0, 102, 200], |
|
[61, 230, 250], |
|
[255, 6, 51], |
|
[11, 102, 255], |
|
[255, 7, 71], |
|
[255, 9, 224], |
|
[9, 7, 230], |
|
[220, 220, 220], |
|
[255, 9, 92], |
|
[112, 9, 255], |
|
[8, 255, 214], |
|
[7, 255, 224], |
|
[255, 184, 6], |
|
[10, 255, 71], |
|
[255, 41, 10], |
|
[7, 255, 255], |
|
[224, 255, 8], |
|
[102, 8, 255], |
|
[255, 61, 6], |
|
[255, 194, 7], |
|
[255, 122, 8], |
|
[0, 255, 20], |
|
[255, 8, 41], |
|
[255, 5, 153], |
|
[6, 51, 255], |
|
[235, 12, 255], |
|
[160, 150, 20], |
|
[0, 163, 255], |
|
[140, 140, 140], |
|
[250, 10, 15], |
|
[20, 255, 0], |
|
[31, 255, 0], |
|
[255, 31, 0], |
|
[255, 224, 0], |
|
[153, 255, 0], |
|
[0, 0, 255], |
|
[255, 71, 0], |
|
[0, 235, 255], |
|
[0, 173, 255], |
|
[31, 0, 255], |
|
[11, 200, 200], |
|
[255, 82, 0], |
|
[0, 255, 245], |
|
[0, 61, 255], |
|
[0, 255, 112], |
|
[0, 255, 133], |
|
[255, 0, 0], |
|
[255, 163, 0], |
|
[255, 102, 0], |
|
[194, 255, 0], |
|
[0, 143, 255], |
|
[51, 255, 0], |
|
[0, 82, 255], |
|
[0, 255, 41], |
|
[0, 255, 173], |
|
[10, 0, 255], |
|
[173, 255, 0], |
|
[0, 255, 153], |
|
[255, 92, 0], |
|
[255, 0, 255], |
|
[255, 0, 245], |
|
[255, 0, 102], |
|
[255, 173, 0], |
|
[255, 0, 20], |
|
[255, 184, 184], |
|
[0, 31, 255], |
|
[0, 255, 61], |
|
[0, 71, 255], |
|
[255, 0, 204], |
|
[0, 255, 194], |
|
[0, 255, 82], |
|
[0, 10, 255], |
|
[0, 112, 255], |
|
[51, 0, 255], |
|
[0, 194, 255], |
|
[0, 122, 255], |
|
[0, 255, 163], |
|
[255, 153, 0], |
|
[0, 255, 10], |
|
[255, 112, 0], |
|
[143, 255, 0], |
|
[82, 0, 255], |
|
[163, 255, 0], |
|
[255, 235, 0], |
|
[8, 184, 170], |
|
[133, 0, 255], |
|
[0, 255, 92], |
|
[184, 0, 255], |
|
[255, 0, 31], |
|
[0, 184, 255], |
|
[0, 214, 255], |
|
[255, 0, 112], |
|
[92, 255, 0], |
|
[0, 224, 255], |
|
[112, 224, 255], |
|
[70, 184, 160], |
|
[163, 0, 255], |
|
[153, 0, 255], |
|
[71, 255, 0], |
|
[255, 0, 163], |
|
[255, 204, 0], |
|
[255, 0, 143], |
|
[0, 255, 235], |
|
[133, 255, 0], |
|
[255, 0, 235], |
|
[245, 0, 255], |
|
[255, 0, 122], |
|
[255, 245, 0], |
|
[10, 190, 212], |
|
[214, 255, 0], |
|
[0, 204, 255], |
|
[20, 0, 255], |
|
[255, 255, 0], |
|
[0, 153, 255], |
|
[0, 41, 255], |
|
[0, 255, 204], |
|
[41, 0, 255], |
|
[41, 255, 0], |
|
[173, 0, 255], |
|
[0, 245, 255], |
|
[71, 0, 255], |
|
[122, 0, 255], |
|
[0, 255, 184], |
|
[0, 92, 255], |
|
[184, 255, 0], |
|
[0, 133, 255], |
|
[255, 214, 0], |
|
[25, 194, 194], |
|
[102, 255, 0], |
|
[92, 0, 255], |
|
] |
|
|
|
feature_extractor = DetrFeatureExtractor.from_pretrained('facebook/detr-resnet-50-panoptic') |
|
model = DetrForSegmentation.from_pretrained('facebook/detr-resnet-50-panoptic') |
|
|
|
|
|
input = gr.inputs.Image() |
|
output = gr.outputs.Image() |
|
|
|
def predict_animal_mask(im): |
|
image = Image.fromarray(im) |
|
image = image.resize((200,200)) |
|
|
|
inputs = feature_extractor(images=image, return_tensors="pt") |
|
outputs = model(**inputs) |
|
logits = outputs.logits |
|
bboxes = outputs.pred_boxes |
|
masks = outputs.pred_masks |
|
|
|
|
|
label_per_pixel = torch.argmax(masks.squeeze(),dim=0).detach().numpy() |
|
color_mask = np.zeros(image.size+(3,)) |
|
for lbl, color in enumerate(ade_palette()): |
|
color_mask[label_per_pixel==lbl,:] = color |
|
|
|
|
|
pred_img = np.array(image.convert('RGB'))*0.5 + color_mask*0.5 |
|
pred_img = pred_img.astype(np.uint8) |
|
|
|
return pred_img |
|
|
|
|
|
|
|
|
|
gr.Interface(predict_animal_mask, |
|
inputs = input, |
|
outputs = output, |
|
title = 'Animals* segmentation in images', |
|
description = "An animal* segmentation image webapp using DETR (End-to-End Object Detection) model with ResNet-50 backbone").launch() |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|