File size: 6,410 Bytes
8b8fc21
72648b6
 
 
8b8fc21
6e14436
 
 
8b8fc21
 
 
6e14436
 
8b8fc21
 
 
6e14436
 
 
 
 
 
 
 
 
8b8fc21
6e14436
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b8fc21
 
6e14436
 
 
 
 
 
 
 
 
 
8b8fc21
6e14436
8b8fc21
6e14436
8b8fc21
 
 
 
6e14436
 
 
 
 
8b8fc21
 
 
 
6e14436
 
 
8b8fc21
 
 
 
6e14436
 
72648b6
 
 
 
 
 
 
 
 
 
 
 
 
6e14436
8b8fc21
85d4eb3
 
 
 
 
6e14436
 
 
 
 
 
 
8b8fc21
72648b6
 
8b8fc21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72648b6
 
 
8b8fc21
72648b6
 
 
8b8fc21
72648b6
 
 
 
8b8fc21
6e14436
85d4eb3
72648b6
d7d0980
 
85d4eb3
 
 
 
d7d0980
85d4eb3
 
 
 
 
72648b6
85d4eb3
 
 
 
 
 
 
 
72648b6
85d4eb3
72648b6
85d4eb3
99abd69
6e14436
85d4eb3
6e14436
72648b6
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
import os
from pyChatGPT import ChatGPT

os.system("pip install -U gradio")

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/")
sys.path.insert(0, "third_party/CenterNet2/")
from centernet.config import add_centernet_config
from detic.config import add_detic_config
from detic.modeling.utils import reset_cls_test

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",
}

session_token = os.environ.get("SessionToken")


def get_response_from_chatbot(text):
    try:
        api = ChatGPT(session_token)
        resp = api.send_message(text)
        api.refresh_auth()
        api.reset_conversation()
        response = resp["message"]
    except:
        response = "Sorry, I'm busy. Try again later."
    return response


def inference(img, vocabulary):
    metadata = MetadataCatalog.get(BUILDIN_METADATA_PATH[vocabulary])
    classifier = BUILDIN_CLASSIFIER[vocabulary]
    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"))

    detected_objects = []
    object_list_str = []

    box_locations = outputs["instances"].pred_boxes
    box_loc_screen = box_locations.tensor.cpu().numpy()

    for i, box_coord in enumerate(box_loc_screen):
        x0, y0, x1, y1 = box_coord
        width = x1 - x0
        height = y1 - y0
        predicted_label = metadata.thing_classes[outputs["instances"].pred_classes[i]]
        detected_objects.append(
            {
                "prediction": predicted_label,
                "x": int(x0),
                "y": int(y0),
                "w": int(width),
                "h": int(height),
            }
        )
        object_list_str.append(
            f"{predicted_label} - X:({int(x0)} Y: {int(y0)} Width {int(width)} Height: {int(height)})"
        )

    chat_gpt_response = get_response_from_chatbot(
        f"You are an intelligent image captioner. I will hand you the objects and their position, and you should give me a detailed description for the photo. In this photo we have the following objects\n{object_list_str}"
    )

    return (
        Image.fromarray(np.uint8(out.get_image())).convert("RGB"),
        chat_gpt_response,
    )


# create a gradio block for image classification
with gr.Blocks() as demo:
    gr.Markdown("# Detic + ChatGPT")
    gr.Markdown("### New DEMO using LangChain: [Image Captioning using LangChain (GPT3.5) 🦜️🔗](https://huggingface.co/spaces/taesiri/Langchain-Imagecaptioner)")
    gr.Markdown(
        "Use Detic to detect objects in an image and then use ChatGPT to describe the image."
    )
    gr.HTML(
        "<p>You need to duplicating this space and use your own session token: <a style='display:inline-block' href='https://huggingface.co/spaces/yizhangliu/chatGPT?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a></p>"
    )
    gr.HTML(
        "<p> Instruction on how to get session token can be seen in video <a style='display:inline-block' href='https://www.youtube.com/watch?v=TdNSj_qgdFk'><font style='color:blue;weight:bold;'>here</font></a>. Add your session token by going to settings and add under secrets. </p>"
    )

    with gr.Column():
        with gr.Row():
            inp = gr.Image(label="Input Image", type="filepath")
            vocab = gr.Dropdown(
                ["lvis", "objects365", "openimages", "coco"],
                label="Vocabulary",
                value="lvis",
            )

        btn_detic = gr.Button("Run Detic+ChatGPT")
    with gr.Row():
        outviz = gr.Image(label="Visualization", type="pil")
        output_desc = gr.Textbox(label="ChatGPT Description", lines=5)
        # outputjson = gr.JSON(label="Detected Objects")

    btn_detic.click(fn=inference, inputs=[inp, vocab], outputs=[outviz, output_desc])

demo.launch()