我正在研究CK +数据集以进行面部表情识别,并且正在通过datagen.flow_from_directory
传递面部图像和标签以提取面部特征并映射到标签。
标签以分类值的形式传递,并且范围从0到7。相同的符号似乎以一键编码形式传递。我的问题是我可以将标签值广播为一键编码的值。
我收到以下错误:
ValueError: could not broadcast input array from shape (32,8) into shape (32)
代码如下:
import scipy
import os, shutil
from tensorflow.keras.preprocessing.image import ImageDataGenerator
img_width, img_height = 224, 224
datagen = ImageDataGenerator(rescale=1./255)
batch_size = 32
def extract_features(directory, sample_count):
features = np.zeros(shape=(sample_count, 7, 7, 512)) # Must be equal to the output of the convolutional base
labels = np.zeros(shape=(sample_count))
print(sample_count, 7, 7, 512)
# Preprocess data - flow_from_directory allows us to extract
#... features and labels directly from a directory
generator = datagen.flow_from_directory(directory,
target_size=(img_width,img_height),
batch_size = batch_size,
class_mode='categorical')
i = 0
for inputs_batch, labels_batch in generator:
features_batch = conv_base.predict(inputs_batch)
features[i * batch_size: (i + 1) * batch_size] = features_batch
labels[i * batch_size: (i + 1) * batch_size] = labels_batch
i += 1
if i * batch_size >= sample_count:
break
return features, labels
我得到以下形状:
Found 209 images belonging to 8 classes.
Input batch shape: (32, 224, 224, 3)
Features batch shape: (32, 7, 7, 512)
Features shape: (209, 7, 7, 512)
Labels batch shape: (32, 8)
所以我对为什么可以广播features_batch
而不能广播labels_batch
感到困惑。
我尝试了几件事,其中包括:
1)使标签数组变平-这没有意义,只是为了查看,我得到了 32 * 8 = 259 的行和列的完整元素计数(如预期的那样)。
2)我尝试仅使用labels[i]=labels_batch
和labels=labels_batch
来返回最后几个标签
(17,从209-(6 * 32)= 17剩下来)。
3)我还尝试从this question插入另一个解决方案。 通过这样做:
for c in range(0,7):
labels[i * batch_size: (i + 1) * batch_size, [c]] = labels_batch
但是出现以下错误:
ValueError: Error when checking input: expected input_3 to have 4 dimensions, but got array with shape (32, 8)
我觉得我所缺少的很简单,但是我似乎无法弄清楚。可能有人有什么想法吗?
谢谢!
答案 0 :(得分:1)
您的标签应为labels = np.zeros(shape=(sample_count, num_classes))
而不是labels = np.zeros(shape=(sample_count))
并应从生成器分配标签
labels[i * batch_size: (i + 1) * batch_size,:] = labels_batch