小编Ram*_*ffo的帖子

我将一些音频文件转换为频谱图并使用以下代码将它们保存到文件中：

import os
from matplotlib import pyplot as plt
import librosa
import librosa.display
import IPython.display as ipd

audio_fpath = "./audios/"
spectrograms_path = "./spectrograms/"
audio_clips = os.listdir(audio_fpath)

def generate_spectrogram(x, sr, save_name):
    X = librosa.stft(x)
    Xdb = librosa.amplitude_to_db(abs(X))
    fig = plt.figure(figsize=(20, 20), dpi=1000, frameon=False)
    ax = fig.add_axes([0, 0, 1, 1], frameon=False)
    ax.axis('off')
    librosa.display.specshow(Xdb, sr=sr, cmap='gray', x_axis='time', y_axis='hz')
    plt.savefig(save_name, quality=100, bbox_inches=0, pad_inches=0)
    librosa.cache.clear()

for i in audio_clips:
    audio_fpath = "./audios/"
    spectrograms_path = "./spectrograms/"
    audio_length = librosa.get_duration(filename=audio_fpath + i)
    j=60
    while j < audio_length: …

我生成带有某些线条的嘈杂图像，如下所示：

我正在尝试使用 OpenCV 检测线条，但出了点问题。

到目前为止，这是我的代码，包括生成嘈杂图像的代码。

import cv2
import numpy as np

def draw_random_lines(img, w, n):
    for i in range(n):
        point1 = (np.random.randint(low = 0, high = w), np.random.randint(low = 0, high = w))
        point2 = (np.random.randint(low = 0, high = w), np.random.randint(low = 0, high = w))
        cv2.line(img,point1,point2,(255,0,0),5)
    x = y = 0
    while(y<w):
        while(x<w):
            if(np.any(img[x, y] != 0)):
                if(np.random.randint(low=0, high=100) < 60):
                    img[x, y] = [255, 255, 255] 
                else:
                    img[x, y] = [0, 0, 0]
            else:
                if(np.random.randint(low=0, high=100) < …

我已经在以 coco 格式标记和导出的自定义数据上训练了 detectorron2 模型，但现在我想应用增强并使用增强数据进行训练。如果我不使用自定义 DataLoader，而是使用 register_coco_instances 函数，我该如何做到这一点。

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
predictor = DefaultPredictor(cfg)
outputs = predictor(im)

train_annotations_path = "./data/cvat-corn-train-coco-1.0/annotations/instances_default.json"
train_images_path = "./data/cvat-corn-train-coco-1.0/images"
validation_annotations_path = "./data/cvat-corn-validation-coco-1.0/annotations/instances_default.json"
validation_images_path = "./data/cvat-corn-validation-coco-1.0/images"

register_coco_instances(
    "train-corn",
    {},
    train_annotations_path,
    train_images_path
)
register_coco_instances(
    "validation-corn",
    {},
    validation_annotations_path,
    validation_images_path
)
metadata_train = MetadataCatalog.get("train-corn")
dataset_dicts = DatasetCatalog.get("train-corn")

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("train-corn",)
cfg.DATASETS.TEST = ("validation-corn",)
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2 …