Tony607

from tensorflow.keras import backend as K


def smooth_dice_coeff(smooth=1.):

    smooth = float(smooth)

    # IOU or dice coeff calculation
    def IOU_calc(y_true, y_pred):
            y_true_f = K.flatten(y_true)

Tony607

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D, Lambda, Conv2DTranspose, concatenate

def get_small_unet():
    inputs = Input((img_rows, img_cols, 1))
    inputs_norm = Lambda(lambda x: x/127.5 - 1.)
    conv1 = Conv2D(16, (3, 3), activation='relu', padding='same')(inputs)
    conv1 = Conv2D(16, (3, 3), activation='relu', padding='same')(conv1)
    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

Tony607

import time
times = []
for i in range(20):
    start_time = time.time()
    outputs = predictor(im)
    delta = time.time() - start_time
    times.append(delta)
mean_delta = np.array(times).mean()
fps = 1 / mean_delta
print("Average(sec):{:.2f},fps:{:.2f}".format(mean_delta, fps))

Tony607

from detectron2.utils.visualizer import ColorMode

for d in random.sample(dataset_dicts, 3):    
    im = cv2.imread(d["file_name"])
    outputs = predictor(im)
    v = Visualizer(im[:, :, ::-1],
                   metadata=fruits_nuts_metadata, 
                   scale=0.8, 
                   instance_mode=ColorMode.IMAGE_BW   # remove the colors of unsegmented pixels
    )

Tony607

cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5   # set the testing threshold for this model
cfg.DATASETS.TEST = ("fruits_nuts", )
predictor = DefaultPredictor(cfg)

Tony607

from detectron2.engine import DefaultTrainer
from detectron2.config import get_cfg
import os

cfg = get_cfg()
cfg.merge_from_file(
    "./detectron2_repo/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"
)
cfg.DATASETS.TRAIN = ("fruits_nuts",)
cfg.DATASETS.TEST = ()  # no metrics implemented for this dataset

Tony607

import random
from detectron2.utils.visualizer import Visualizer

for d in random.sample(dataset_dicts, 3):
    img = cv2.imread(d["file_name"])
    visualizer = Visualizer(img[:, :, ::-1], metadata=fruits_nuts_metadata, scale=0.5)
    vis = visualizer.draw_dataset_dict(d)
    cv2_imshow(vis.get_image()[:, :, ::-1])

Tony607

from detectron2.data.datasets import register_coco_instances
register_coco_instances("fruits_nuts", {}, "./data/trainval.json", "./data/images")

Tony607

# download, decompress the data
!wget https://github.com/Tony607/detectron2_instance_segmentation_demo/releases/download/V0.1/data.zip
!unzip data.zip > /dev/null

Tony607

!pip install -U torch torchvision
!pip install git+https://github.com/facebookresearch/fvcore.git
!git clone https://github.com/facebookresearch/detectron2 detectron2_repo
!pip install -e detectron2_repo