File size: 8,907 Bytes
2cd560a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
import argparse
import os
import copy

import numpy as np
import json
import torch
import torchvision
from PIL import Image, ImageDraw, ImageFont

# Grounding DINO
import GroundingDINO.groundingdino.datasets.transforms as T
from GroundingDINO.groundingdino.models import build_model
from GroundingDINO.groundingdino.util import box_ops
from GroundingDINO.groundingdino.util.slconfig import SLConfig
from GroundingDINO.groundingdino.util.utils import clean_state_dict, get_phrases_from_posmap

# segment anything
from segment_anything import build_sam, SamPredictor 
import cv2
import numpy as np
import matplotlib.pyplot as plt

# whisper
import whisper


def load_image(image_path):
    # load image
    image_pil = Image.open(image_path).convert("RGB")  # load image

    transform = T.Compose(
        [
            T.RandomResize([800], max_size=1333),
            T.ToTensor(),
            T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
        ]
    )
    image, _ = transform(image_pil, None)  # 3, h, w
    return image_pil, image


def load_model(model_config_path, model_checkpoint_path, device):
    args = SLConfig.fromfile(model_config_path)
    args.device = device
    model = build_model(args)
    checkpoint = torch.load(model_checkpoint_path, map_location="cpu")
    load_res = model.load_state_dict(clean_state_dict(checkpoint["model"]), strict=False)
    print(load_res)
    _ = model.eval()
    return model


def get_grounding_output(model, image, caption, box_threshold, text_threshold,device="cpu"):
    caption = caption.lower()
    caption = caption.strip()
    if not caption.endswith("."):
        caption = caption + "."
    model = model.to(device)
    image = image.to(device)
    with torch.no_grad():
        outputs = model(image[None], captions=[caption])
    logits = outputs["pred_logits"].cpu().sigmoid()[0]  # (nq, 256)
    boxes = outputs["pred_boxes"].cpu()[0]  # (nq, 4)
    logits.shape[0]

    # filter output
    logits_filt = logits.clone()
    boxes_filt = boxes.clone()
    filt_mask = logits_filt.max(dim=1)[0] > box_threshold
    logits_filt = logits_filt[filt_mask]  # num_filt, 256
    boxes_filt = boxes_filt[filt_mask]  # num_filt, 4
    logits_filt.shape[0]

    # get phrase
    tokenlizer = model.tokenizer
    tokenized = tokenlizer(caption)
    # build pred
    pred_phrases = []
    scores = []
    for logit, box in zip(logits_filt, boxes_filt):
        pred_phrase = get_phrases_from_posmap(logit > text_threshold, tokenized, tokenlizer)
        pred_phrases.append(pred_phrase + f"({str(logit.max().item())[:4]})")
        scores.append(logit.max().item())

    return boxes_filt, torch.Tensor(scores), pred_phrases

def show_mask(mask, ax, random_color=False):
    if random_color:
        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
    else:
        color = np.array([30/255, 144/255, 255/255, 0.6])
    h, w = mask.shape[-2:]
    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
    ax.imshow(mask_image)


def show_box(box, ax, label):
    x0, y0 = box[0], box[1]
    w, h = box[2] - box[0], box[3] - box[1]
    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2)) 
    ax.text(x0, y0, label)


def save_mask_data(output_dir, mask_list, box_list, label_list):
    value = 0  # 0 for background

    mask_img = torch.zeros(mask_list.shape[-2:])
    for idx, mask in enumerate(mask_list):
        mask_img[mask.cpu().numpy()[0] == True] = value + idx + 1
    plt.figure(figsize=(10, 10))
    plt.imshow(mask_img.numpy())
    plt.axis('off')
    plt.savefig(os.path.join(output_dir, 'mask.jpg'), bbox_inches="tight", dpi=300, pad_inches=0.0)

    json_data = [{
        'value': value,
        'label': 'background'
    }]
    for label, box in zip(label_list, box_list):
        value += 1
        name, logit = label.split('(')
        logit = logit[:-1] # the last is ')'
        json_data.append({
            'value': value,
            'label': name,
            'logit': float(logit),
            'box': box.numpy().tolist(),
        })
    with open(os.path.join(output_dir, 'mask.json'), 'w') as f:
        json.dump(json_data, f)
    

def speech_recognition(speech_file, model):
    # whisper
    # load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(speech_file)
    audio = whisper.pad_or_trim(audio)

    # make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    # detect the spoken language
    _, probs = model.detect_language(mel)
    speech_language = max(probs, key=probs.get)

    # decode the audio
    options = whisper.DecodingOptions()
    result = whisper.decode(model, mel, options)

    # print the recognized text
    speech_text = result.text
    return speech_text, speech_language

if __name__ == "__main__":

    parser = argparse.ArgumentParser("Grounded-Segment-Anything Demo", add_help=True)
    parser.add_argument("--config", type=str, required=True, help="path to config file")
    parser.add_argument(
        "--grounded_checkpoint", type=str, required=True, help="path to checkpoint file"
    )
    parser.add_argument(
        "--sam_checkpoint", type=str, required=True, help="path to checkpoint file"
    )
    parser.add_argument("--input_image", type=str, required=True, help="path to image file")
    parser.add_argument("--speech_file", type=str, required=True, help="speech file")
    parser.add_argument(
        "--output_dir", "-o", type=str, default="outputs", required=True, help="output directory"
    )

    parser.add_argument("--box_threshold", type=float, default=0.3, help="box threshold")
    parser.add_argument("--text_threshold", type=float, default=0.25, help="text threshold")
    parser.add_argument("--iou_threshold", type=float, default=0.5, help="iou threshold")

    parser.add_argument("--device", type=str, default="cpu", help="running on cpu only!, default=False")
    args = parser.parse_args()

    # cfg
    config_file = args.config  # change the path of the model config file
    grounded_checkpoint = args.grounded_checkpoint  # change the path of the model
    sam_checkpoint = args.sam_checkpoint
    image_path = args.input_image
    output_dir = args.output_dir
    box_threshold = args.box_threshold
    text_threshold = args.text_threshold
    iou_threshold = args.iou_threshold
    device = args.device

    # load speech
    whisper_model = whisper.load_model("base")
    speech_text, speech_language = speech_recognition(args.speech_file, whisper_model)
    print(f"speech_text: {speech_text}")
    print(f"speech_language: {speech_language}")

    # make dir
    os.makedirs(output_dir, exist_ok=True)
    # load image
    image_pil, image = load_image(image_path)
    # load model
    model = load_model(config_file, grounded_checkpoint, device=device)

    # visualize raw image
    image_pil.save(os.path.join(output_dir, "raw_image.jpg"))

    # run grounding dino model
    text_prompt = speech_text
    boxes_filt, scores, pred_phrases = get_grounding_output(
        model, image, text_prompt, box_threshold, text_threshold, device=device
    )

    # initialize SAM
    sam = build_sam(checkpoint=sam_checkpoint)
    sam.to(device=device)
    predictor = SamPredictor(sam)
    image = cv2.imread(image_path)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    predictor.set_image(image)

    size = image_pil.size
    H, W = size[1], size[0]
    for i in range(boxes_filt.size(0)):
        boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
        boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
        boxes_filt[i][2:] += boxes_filt[i][:2]

    boxes_filt = boxes_filt.cpu()
    # use NMS to handle overlapped boxes
    print(f"Before NMS: {boxes_filt.shape[0]} boxes")
    nms_idx = torchvision.ops.nms(boxes_filt, scores, iou_threshold).numpy().tolist()
    boxes_filt = boxes_filt[nms_idx]
    pred_phrases = [pred_phrases[idx] for idx in nms_idx]
    print(f"After NMS: {boxes_filt.shape[0]} boxes")

    transformed_boxes = predictor.transform.apply_boxes_torch(boxes_filt, image.shape[:2]).to(device)

    masks, _, _ = predictor.predict_torch(
        point_coords = None,
        point_labels = None,
        boxes = transformed_boxes.to(args.device),
        multimask_output = False,
    )
    
    # draw output image
    plt.figure(figsize=(10, 10))
    plt.imshow(image)
    for mask in masks:
        show_mask(mask.cpu().numpy(), plt.gca(), random_color=True)
    for box, label in zip(boxes_filt, pred_phrases):
        show_box(box.numpy(), plt.gca(), label)
    
    plt.title(speech_text)
    plt.axis('off')
    plt.savefig(
        os.path.join(output_dir, "grounded_sam_whisper_output.jpg"), 
        bbox_inches="tight", dpi=300, pad_inches=0.0
    )


    save_mask_data(output_dir, masks, boxes_filt, pred_phrases)