import argparse
import os
import sys
import numpy as np
import json
import torch
from PIL import Image
sys.path.append(os.path.join(os.getcwd(), "GroundingDINO"))
sys.path.append(os.path.join(os.getcwd(), "segment_anything"))
# Grounding DINO
import GroundingDINO.groundingdino.datasets.transforms as T
from GroundingDINO.groundingdino.models import build_model
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 (
sam_model_registry,
sam_hq_model_registry,
SamPredictor
)
import cv2
import numpy as np
import matplotlib.pyplot as plt
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, bert_base_uncased_path, device):
args = SLConfig.fromfile(model_config_path)
args.device = device
args.bert_base_uncased_path = bert_base_uncased_path
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
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)
if __name__ == "__main__":
parser = argparse.ArgumentParser("Grounded-Segment-Anything Demo", add_help=True)
parser.add_argument("--config", type=str, default="./GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py", help="path to config file")
parser.add_argument(
"--grounded_checkpoint", type=str, default="./groundingdino_swint_ogc.pth", help="path to checkpoint file"
)
parser.add_argument(
"--sam_version", type=str, default="vit_h", required=False, help="SAM ViT version: vit_b / vit_l / vit_h"
)
parser.add_argument(
"--sam_checkpoint", type=str, default="./sam_vit_h_4b8939.pth", help="path to sam checkpoint file"
)
parser.add_argument(
"--sam_hq_checkpoint", type=str, default=None, help="path to sam-hq checkpoint file"
)
parser.add_argument(
"--use_sam_hq", action="store_true", help="using sam-hq for prediction"
)
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", 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")
parser.add_argument("--bert_base_uncased_path", type=str, required=False, help="bert_base_uncased model path, 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_version = args.sam_version
sam_checkpoint = args.sam_checkpoint
sam_hq_checkpoint = args.sam_hq_checkpoint
use_sam_hq = args.use_sam_hq
image_path = args.input_image
text_prompt = args.text_prompt
output_dir = args.output_dir
box_threshold = args.box_threshold
text_threshold = args.text_threshold
device = args.device
bert_base_uncased_path = args.bert_base_uncased_path
# 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, bert_base_uncased_path, device=device)
# visualize raw image
image_pil.save(os.path.join(output_dir, "raw_image.jpg"))
# run grounding dino model
boxes_filt, pred_phrases = get_grounding_output(
model, image, text_prompt, box_threshold, text_threshold, device=device
)
# initialize SAM
if use_sam_hq:
predictor = SamPredictor(sam_hq_model_registry[sam_version](checkpoint=sam_hq_checkpoint).to(device))
else:
predictor = SamPredictor(sam_model_registry[sam_version](checkpoint=sam_checkpoint).to(device))
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()
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(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.axis('off')
plt.savefig(
os.path.join(output_dir, "grounded_sam_output.jpg"),
bbox_inches="tight", dpi=300, pad_inches=0.0
)
save_mask_data(output_dir, masks, boxes_filt, pred_phrases)
报错C:\Users\29386\.conda\envs\grounded_sam\python.exe C:\Users\29386\segment-anything\Grounded-Segment-Anything\grounded_sam_demo.py --config GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py --grounded_checkpoint weights/groundingdino_swint_ogc.pth --sam_checkpoint weights/sam_vit_h_4b8939.pth --input_image assets/demo1.jpg --output_dir outputs
C:\Users\29386\.conda\envs\grounded_sam\lib\site-packages\timm\models\layers\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
Traceback (most recent call last):
File "C:\Users\29386\segment-anything\Grounded-Segment-Anything\grounded_sam_demo.py", line 22, in <module>
from segment_anything import (
ImportError: cannot import name 'sam_hq_model_registry' from 'segment_anything' (C:\Users\29386\segment-anything\segment_anything\__init__.py)
进程已结束，退出代码为 1
如何解决
最新发布
本文介绍了一个简单的Windows消息处理示例，包括定义消息常量IDM_EXIT和IDM_ABOUT，以及实现窗口过程函数WndProc和关于框处理函数About。
扫一扫
362
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
