The funtion of colormap2label may not be effective , the converted label does not correspond.

[lihua7351]

test-rgb2label.pdf
The result for [0,0,128] should be labeled as 4, but got the 0. Hope to get your reply, thank you!
The input image from VOC2012\SegmentationClass\2007_000061.png

[lihua7351]

`
import os
import json
#import cv2
from tqdm import tqdm
import numpy as np
from glob import glob
import tensorflow as tf
import matplotlib.pyplot as plt
import skimage.io as io
from tensorflow.keras.callbacks import Callback
from tensorflow.keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping, LearningRateScheduler
print('TensorFlow', tf.version)

img1 = tf.io.read_file("C:/Users/eadhaw/Desktop/1221/5.png")
img1 = tf.image.decode_png(img1)
print(img1.shape)

VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0],
[0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128],
[64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0],
[64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128],
[0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0],
[0, 64, 128]]
colormap2label = np.zeros(256 ** 3, dtype=np.uint8)

for i, colormap in enumerate(VOC_COLORMAP):
colormap2label[(colormap[0] * 256 + colormap[1]) * 256 + colormap[2]] = i
colormap2label = tf.convert_to_tensor(colormap2label)
def voc_label_indices(colormap, colormap2label):
"""
convert colormap (tf image) to colormap2label (uint8 tensor).
"""
colormap = tf.cast(colormap, dtype=tf.int32)
idx = tf.add(tf.multiply(colormap[:, :, 0], 256), colormap[:, :, 1])
idx = tf.add(tf.multiply(idx, 256), colormap[:, :, 2])
idx = tf.add(idx, colormap[:, :, 2])
return tf.gather_nd(colormap2label, tf.expand_dims(idx, -1))

y = voc_label_indices(img1, colormap2label)

img1[230:240,325:330,:]

y[230:240,325:330]`

[SwordFaith]

Which chapter is this question about ?

[lihua7351]

chapter09_computer-vision/9.9_semantic-segmentation-and-dataset.ipynb/def voc_label_indices(colormap, colormap2label):

[lihua7351]

这个问题是关于哪一章的？
Chapter09_computer-vision / 9.9_semantic-segmentation-and-dataset.ipynb