""" 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 # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/ https://colab.research.google.com/github/NielsRogge/Transformers-Tutorials/blob/master/DETR/DETR_panoptic_segmentation_minimal_example_(with_DetrFeatureExtractor).ipynb https://arxiv.org/abs/2005.12872 Additions - add shown labels as strings - show only animal masks (ask an nlp model?) """ from transformers import DetrFeatureExtractor, DetrForSegmentation from PIL import Image import gradio as gr import numpy as np import torch import torchvision # Returns a list with a color per ADE class (150 classes) # from https://huggingface.co/spaces/chansung/segformer-tf-transformers/blob/main/app.py 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], ] def predict_animal_mask(im, gr_slider_confidence): image = Image.fromarray(im) # im: numpy array 3d: 480, 640, 3: to PIL Image image = image.resize((200,200)) # PIL image # could I upsample output instead? better? # encoding is a dict with pixel_values and pixel_mask encoding = feature_extractor(images=image, return_tensors="pt") #pt=Pytorch, tf=TensorFlow outputs = model(**encoding) # odict with keys: ['logits', 'pred_boxes', 'pred_masks', 'last_hidden_state', 'encoder_last_hidden_state'] logits = outputs.logits # torch.Size([1, 100, 251]); why 251? bboxes = outputs.pred_boxes masks = outputs.pred_masks # torch.Size([1, 100, 200, 200]); for every pixel, score in each of the 100 classes? there is a mask per class # keep only the masks with high confidence?-------------------------------- # compute the prob per mask (i.e., class), excluding the "no-object" class (the last one) prob_per_query = outputs.logits.softmax(-1)[..., :-1].max(-1)[0] # why logits last dim 251? # threshold the confidence keep = prob_per_query > gr_slider_confidence/100.0 # postprocess the mask (numpy arrays) label_per_pixel = torch.argmax(masks[keep].squeeze(),dim=0).detach().numpy() # from the masks per class, select the highest per pixel color_mask = np.zeros(image.size+(3,)) for lbl, color in enumerate(ade_palette()): color_mask[label_per_pixel==lbl,:] = color # Show image + mask pred_img = np.array(image.convert('RGB'))*0.5 + color_mask*0.5 pred_img = pred_img.astype(np.uint8) return pred_img ####################################### # get models from hugging face feature_extractor = DetrFeatureExtractor.from_pretrained('facebook/detr-resnet-50-panoptic') model = DetrForSegmentation.from_pretrained('facebook/detr-resnet-50-panoptic') # gradio components -inputs gr_image_input = gr.inputs.Image() gr_slider_confidence = gr.inputs.Slider(0,100,5,85, label='Set confidence threshold for masks') # gradio outputs gr_image_output = gr.outputs.Image() #################################################### # Create user interface and launch gr.Interface(predict_animal_mask, inputs = [gr_image_input,gr_slider_confidence], outputs = gr_image_output, title = 'Image segmentation with varying confidence', description = "An image segmentation webapp using DETR (End-to-End Object Detection) model with ResNet-50 backbone").launch() #################################### # url = "http://images.cocodataset.org/val2017/000000039769.jpg" # image = Image.open(requests.get(url, stream=True).raw) # inputs = feature_extractor(images=image, return_tensors="pt") # outputs = model(**inputs) # logits = outputs.logits # shape (batch_size, num_labels, height/4, width/4)