efficientService.py

# Author: Zylo117

"""
Simple Inference Script of EfficientDet-Pytorch
"""
import random

import cv2
import numpy as np
import torch
from torch.backends import cudnn

from backbone import EfficientDetBackbone
from efficientdet.utils import BBoxTransform, ClipBoxes
from utils.utils import invert_affine, postprocess, aspectaware_resize_padding

compound_coef = 0
force_input_size = None  # set None to use default size

# replace this part with your project's anchor config
anchor_ratios = [(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]
anchor_scales = [2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)]

threshold = 0.2
iou_threshold = 0.2

use_cuda = True
use_float16 = False
cudnn.fastest = True
cudnn.benchmark = True

obj_list = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
            'fire hydrant', '', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
            'cow', 'elephant', 'bear', 'zebra', 'giraffe', '', 'backpack', 'umbrella', '', '', 'handbag', 'tie',
            'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
            'skateboard', 'surfboard', 'tennis racket', 'bottle', '', 'wine glass', 'cup', 'fork', 'knife', 'spoon',
            'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut',
            'cake', 'chair', 'couch', 'potted plant', 'bed', '', 'dining table', '', '', 'toilet', '', 'tv',
            'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
            'refrigerator', '', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
            'toothbrush']

# tf bilinear interpolation is different from any other's, just make do
input_sizes = [512, 640, 768, 896, 1024, 1280, 1280, 1536]
input_size = input_sizes[compound_coef] if force_input_size is None else force_input_size

model = EfficientDetBackbone(compound_coef=compound_coef, num_classes=len(obj_list),
                             ratios=anchor_ratios, scales=anchor_scales)
model.load_state_dict(torch.load(f'weights/efficientdet-d{compound_coef}.pth'))
model.requires_grad_(False)
model.eval()

if use_cuda:
    model = model.cuda()
if use_float16:
    model = model.half()


def detect(image):
    # convert image to array
    frame = np.array(image)

    # convert to cv format
    frames = frame[:, :, ::-1]

    ori_imgs, framed_imgs, framed_metas = image_preprocess(frames, max_size=input_size)

    if use_cuda:
        x = torch.stack([torch.from_numpy(fi).cuda() for fi in framed_imgs], 0)
    else:
        x = torch.stack([torch.from_numpy(fi) for fi in framed_imgs], 0)

    x = x.to(torch.float32 if not use_float16 else torch.float16).permute(0, 3, 1, 2)

    with torch.no_grad():
        features, regression, classification, anchors = model(x)

        regressBoxes = BBoxTransform()
        clipBoxes = ClipBoxes()

        out = postprocess(x,
                          anchors, regression, classification,
                          regressBoxes, clipBoxes,
                          threshold, iou_threshold)

        out = invert_affine(framed_metas, out)
        render_frame = display(out, frame, imshow=True, imwrite=False)
        return render_frame


def image_preprocess(image_path, max_size=512, mean=(0.406, 0.456, 0.485), std=(0.225, 0.224, 0.229)):
    ori_imgs = [image_path]
    normalized_imgs = [(img / 255 - mean) / std for img in ori_imgs]
    imgs_meta = [aspectaware_resize_padding(img[..., ::-1], max_size, max_size,
                                            means=None) for img in normalized_imgs]
    framed_imgs = [img_meta[0] for img_meta in imgs_meta]
    framed_metas = [img_meta[1:] for img_meta in imgs_meta]

    return ori_imgs, framed_imgs, framed_metas


def display(preds, imgs, imshow=True, imwrite=False):
    imgs = [imgs]
    for i in range(len(imgs)):
        if len(preds[i]['rois']) == 0:
            continue

        for j in range(len(preds[i]['rois'])):
            (x1, y1, x2, y2) = preds[i]['rois'][j].astype(np.int)
            color = [random.randint(0, 255) for _ in range(3)]
            cv2.rectangle(imgs[i], (x1, y1), (x2, y2), color, 2)
            obj = obj_list[preds[i]['class_ids'][j]]
            score = float(preds[i]['scores'][j])

            label = obj
            label_size = cv2.getTextSize(label, 0, fontScale=2 / 3, thickness=1)[0]
            cv2.rectangle(imgs[i], (x1, y1), (x1 + label_size[0], y1 - label_size[1] - 3), color, -1)
            # cv2.putText(imgs[i], '{}, {:.3f}'.format(obj, score),
            #             (x1, y1 + 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
            #             [225, 255, 255], 1, lineType=cv2.LINE_AA)
            cv2.putText(imgs[i], label, (x1, y1 - 8), 0, 2 / 3, [225, 255, 255], thickness=1,
                        lineType=cv2.LINE_AA)

        return imgs[i]