File size: 5,992 Bytes
4ba09fa |
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 |
import argparse
import os
import numpy as np
import torch
from PIL import Image, ImageDraw, ImageFont
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
def plot_boxes_to_image(image_pil, tgt):
H, W = tgt["size"]
boxes = tgt["boxes"]
labels = tgt["labels"]
assert len(boxes) == len(labels), "boxes and labels must have same length"
draw = ImageDraw.Draw(image_pil)
mask = Image.new("L", image_pil.size, 0)
mask_draw = ImageDraw.Draw(mask)
# draw boxes and masks
for box, label in zip(boxes, labels):
# from 0..1 to 0..W, 0..H
box = box * torch.Tensor([W, H, W, H])
# from xywh to xyxy
box[:2] -= box[2:] / 2
box[2:] += box[:2]
# random color
color = tuple(np.random.randint(0, 255, size=3).tolist())
# draw
x0, y0, x1, y1 = box
x0, y0, x1, y1 = int(x0), int(y0), int(x1), int(y1)
draw.rectangle([x0, y0, x1, y1], outline=color, width=6)
# draw.text((x0, y0), str(label), fill=color)
font = ImageFont.load_default()
if hasattr(font, "getbbox"):
bbox = draw.textbbox((x0, y0), str(label), font)
else:
w, h = draw.textsize(str(label), font)
bbox = (x0, y0, w + x0, y0 + h)
# bbox = draw.textbbox((x0, y0), str(label))
draw.rectangle(bbox, fill=color)
draw.text((x0, y0), str(label), fill="white")
mask_draw.rectangle([x0, y0, x1, y1], fill=255, width=6)
return image_pil, mask
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="cpu"):
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, with_logits=True, 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 = []
for logit, box in zip(logits_filt, boxes_filt):
pred_phrase = get_phrases_from_posmap(logit > text_threshold, tokenized, tokenlizer)
if with_logits:
pred_phrases.append(pred_phrase + f"({str(logit.max().item())[:4]})")
else:
pred_phrases.append(pred_phrase)
return boxes_filt, pred_phrases
if __name__ == "__main__":
parser = argparse.ArgumentParser("Grounding DINO example", 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("--input_image", type=str, required=True, help="path to image file")
parser.add_argument("--text_prompt", type=str, required=True, help="text prompt")
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("--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
image_path = args.input_image
text_prompt = args.text_prompt
output_dir = args.output_dir
box_threshold = args.box_threshold
text_threshold = args.box_threshold
device = args.device
# 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 model
boxes_filt, pred_phrases = get_grounding_output(
model, image, text_prompt, box_threshold, text_threshold, device=device
)
# visualize pred
size = image_pil.size
pred_dict = {
"boxes": boxes_filt,
"size": [size[1], size[0]], # H,W
"labels": pred_phrases,
}
# import ipdb; ipdb.set_trace()
image_with_box = plot_boxes_to_image(image_pil, pred_dict)[0]
image_with_box.save(os.path.join(output_dir, "grounding_dino_output.jpg")) |