import matplotlib.pyplot as plt
import requests, validators
import torch
import pathlib
import numpy as np
from PIL import Image

from transformers import DetrFeatureExtractor, DetrForSegmentation, MaskFormerImageProcessor, MaskFormerForInstanceSegmentation
from transformers.models.detr.feature_extraction_detr import rgb_to_id

TEST_IMAGE = Image.open(r"images/Test_Street_VisDrone.JPG")
MODEL_NAME_DETR = "facebook/detr-resnet-50-panoptic"
MODEL_NAME_MASKFORMER = "facebook/maskformer-swin-large-coco"
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

#######
# Parameters
#######
image = TEST_IMAGE
model_name = MODEL_NAME_MASKFORMER

# Starting with MaskFormer

processor = MaskFormerImageProcessor.from_pretrained(model_name)
model = MaskFormerForInstanceSegmentation.from_pretrained(model_name)

model.to(DEVICE)

# img = np.array(TEST_IMAGE)

inputs = processor(images=image, return_tensors="pt")
inputs.to(DEVICE)


outputs = model(**inputs)