在caffe中使用分类时出错

Question

我在python中使用caffe进行分类。我从 here 获取代码。在这里，我只使用简单的代码，例如

plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
mean_filename='./mean.binaryproto'
proto_data = open(mean_filename, "rb").read()
a = caffe.io.caffe_pb2.BlobProto.FromString(proto_data)
mean = caffe.io.blobproto_to_array(a)[0]
age_net_pretrained='./age_net.caffemodel'
age_net_model_file='./deploy_age.prototxt'
age_net = caffe.Classifier(age_net_model_file, age_net_pretrained,
mean=mean,
channel_swap=(2,1,0),
raw_scale=255,
image_dims=(256, 256))

但是，我得到了诸如

之类的错误

Traceback (most recent call last):
File "cnn_age_gender_demo.py", line 25, in 
image_dims=(256, 256))
File "/home/john/Downloads/caffe/python/caffe/classifier.py", line 34, in init
self.transformer.set_mean(in_, mean)
File "/home/john/Downloads/caffe/python/caffe/io.py", line 255, in set_mean
raise ValueError('Mean shape incompatible with input shape.')
ValueError: Mean shape incompatible with input shape.

你能帮我重新爱一下吗？谢谢

Answer 1

让我们去caffe/python/caffe/io.py中的第253-254行替换

if ms != self.inputs[in_][1:]:
    raise ValueError('Mean shape incompatible with input shape.')

来自

if ms != self.inputs[in_][1:]:
    print(self.inputs[in_])
    in_shape = self.inputs[in_][1:]
    m_min, m_max = mean.min(), mean.max()
    normal_mean = (mean - m_min) / (m_max - m_min)
    mean = resize_image(normal_mean.transpose((1,2,0)),in_shape[1:]).transpose((2,0,1)) * (m_max - m_min) + m_min
    #raise ValueError('Mean shape incompatible with input shape.')

重建。希望对你有帮助

Answer 2

我遇到了同样的问题，基于 imagenet 网络演示，我使用这种方式修改了脚本以在第 95 行加载平均文件

mean = np.load(args.mean_file).mean(1).mean(1)

Answer 3

我很害怕重建代码，因为 caffe 安装对我来说并不容易。但是要修复，调整大小的解决方案意味着需要 in_shape（user8264 的响应），这是在 caffe/classifier.py

内部设置的

无论如何，我调试并找到 in_shape = (3, 227, 227) for age_net.caffemodel

的值

因此用于年龄和性别预测的模型将发生以下变化：

age_net_pretrained='./age_net.caffemodel'
age_net_model_file='./deploy_age.prototxt'
age_net = caffe.Classifier(age_net_model_file, age_net_pretrained,
                   mean=mean,
                   channel_swap=(2,1,0),
                   raw_scale=255,
                   image_dims=(227, 227))

但是mean需要先修改：

m_min, m_max = mean.min(), mean.max()
normal_mean = (mean - m_min) / (m_max - m_min)
in_shape=(227, 227)
mean = caffe.io.resize_image(normal_mean.transpose((1,2,0)),in_shape)
                            .transpose((2,0,1)) * (m_max - m_min) + m_min

这将摆脱 "ValueError: Mean shape incompatible with input shape"。但是我不确定准确性。显然，对我来说，跳过均值参数可以更好地预测年龄 :)

Answer 4

编辑 deploy_gender.prototxt 并设置： input_dim: 256 input_dim: 256

不知道为什么写错了...

在caffe中使用分类时出错

Error when using classify in caffe

python

python-2.7

caffe