# Based on https://huggingface.co/spaces/akhaliq/Detic/tree/main Thanks!
import os 
os.system("pip install gradio==2.4.6")
import sys
import gradio as gr

os.system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.9/index.html')

# clone and install Detic
os.system("git clone https://github.com/facebookresearch/Detic.git --recurse-submodules")
os.chdir("Detic")

# Install detectron2
import torch

# Some basic setup:
# Setup detectron2 logger
import detectron2
from detectron2.utils.logger import setup_logger
setup_logger()

# import some common libraries
import sys
import numpy as np
import os, json, cv2, random

# import some common detectron2 utilities
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog, DatasetCatalog

# Detic libraries
sys.path.insert(0, 'third_party/CenterNet2/projects/CenterNet2/')
from centernet.config import add_centernet_config
from detic.config import add_detic_config
from detic.modeling.utils import reset_cls_test
from detic.modeling.text.text_encoder import build_text_encoder

from PIL import Image

# Build the detector and download our pretrained weights
cfg = get_cfg()
add_centernet_config(cfg)
add_detic_config(cfg)
cfg.MODEL.DEVICE='cpu'
cfg.merge_from_file("configs/Detic_LCOCOI21k_CLIP_SwinB_896b32_4x_ft4x_max-size.yaml")
cfg.MODEL.WEIGHTS = 'https://dl.fbaipublicfiles.com/detic/Detic_LCOCOI21k_CLIP_SwinB_896b32_4x_ft4x_max-size.pth'
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.MODEL.ROI_BOX_HEAD.ZEROSHOT_WEIGHT_PATH = 'rand'
cfg.MODEL.ROI_HEADS.ONE_CLASS_PER_PROPOSAL = True # For better visualization purpose. Set to False for all classes.
predictor = DefaultPredictor(cfg)

# Setup the model's vocabulary using build-in datasets

BUILDIN_CLASSIFIER = {
    'lvis': 'datasets/metadata/lvis_v1_clip_a+cname.npy',
    'objects365': 'datasets/metadata/o365_clip_a+cnamefix.npy',
    'openimages': 'datasets/metadata/oid_clip_a+cname.npy',
    'coco': 'datasets/metadata/coco_clip_a+cname.npy',
}

BUILDIN_METADATA_PATH = {
    'lvis': 'lvis_v1_val',
    'objects365': 'objects365_v2_val',
    'openimages': 'oid_val_expanded',
    'coco': 'coco_2017_val',
}

text_encoder = build_text_encoder(pretrain=True)
text_encoder.eval()

def get_clip_embeddings(vocabulary, prompt='a '):
    texts = [prompt + x for x in vocabulary]
    emb = text_encoder(texts).detach().permute(1, 0).contiguous().cpu()
    return emb

def update_test_score_thresh(predictor, test_score_thresh):
    for box_predictor in predictor.model.roi_heads.box_predictor:
        box_predictor.test_score_thresh = test_score_thresh

def inference(custom_vocabulary, thresh, img):
    update_test_score_thresh(predictor, test_score_thresh=thresh)

    metadata = MetadataCatalog.get("__unused")
    metadata.thing_classes = custom_vocabulary.split(',')
    classifier = get_clip_embeddings(metadata.thing_classes)
    num_classes = len(metadata.thing_classes)

    reset_cls_test(predictor.model, classifier, num_classes)

    im = cv2.imread(img)

    outputs = predictor(im)
    v = Visualizer(im[:, :, ::-1], metadata)
    out = v.draw_instance_predictions(outputs["instances"].to("cpu"))

    MetadataCatalog.remove("__unused")

    return Image.fromarray(np.uint8(out.get_image())).convert('RGB')
    
title = "Detic"

description = "Gradio demo for Detic: Detecting Twenty-thousand Classes using Image-level Supervision. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."

article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2201.02605' target='_blank'>Detecting Twenty-thousand Classes using Image-level Supervision</a> | <a href='https://github.com/facebookresearch/Detic' target='_blank'>Github Repo</a></p>"

examples = [
    ['dog,cat'                 , 0.500, 'examples/dogs-and-cats.jpeg'],
    ['a boy jumping in the air', 0.037, 'examples/jump.jpeg'],
]

gr.Interface(inference,
    inputs=[
        gr.inputs.Textbox(placeholder="Type a class or text to find", default="dog,cat"),
        gr.inputs.Slider(minimum=0.001, maximum=0.999, step=0.001, default=0.5),
        gr.inputs.Image(type="filepath")
    ],
    outputs=gr.outputs.Image(type="pil"),
    title=title,
    description=description,
    article=article,
    examples=examples,
    enable_queue=True
    ).launch()