FCN:Check failed: outer_num_ * inner_num_ == bottom[1]->count() - machine-learning

Question

I design a net the same as FCN.Input data is 1*224*224,Input label is 1*224*224.but I meet error:
F0502 07:57:30.032742 18127 softmax_loss_layer.cpp:47] Check failed: outer_num_ * inner_num_ == bottom[1]->count() (50176 vs. 1) Number of labels must match number of predictions; e.g., if softmax axis == 1 and prediction shape is (N, C, H, W), label count (number of labels) must be N*H*W, with integer values in {0, 1, ..., C-1}.
here is the input structure:
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
image_data_param {
ource: "/home/zhaimo/fcn-master/mo/train.txt"
batch_size: 1
shuffle: true
}
}
the softmax layers:
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "upscore1"
bottom: "label"
top: "loss"
loss_param {
ignore_label: 255
normalize: false
}
}
the train.txt file:
/home/zhaimo/fcn-master/data/vessel/train/original/01.png /home/zhaimo/SegNet/data/vessel/train/label/01.png
/home/zhaimo/fcn-master/data/vessel/train/original/02.png /home/zhaimo/SegNet/data/vessel/train/label/02.png
/home/zhaimo/fcn-master/data/vessel/train/original/03.png /home/zhaimo/SegNet/data/vessel/train/label/03.png
/home/zhaimo/fcn-master/data/vessel/train/original/04.png /home/zhaimo/SegNet/data/vessel/train/label/04.png
the first file name is input data and the second one is its label.
===========================update=======================================
I tried to use two ImageData layer as input:
layer {
name: "data"
type: "ImageData"
top: "data"
image_data_param {
source: "/home/zhaimo/fcn-master/mo/train_o.txt"
batch_size: 1
shuffle: false
}
}
layer {
name: "label"
type: "ImageData"
top: "label"
image_data_param {
source: "/home/zhaimo/fcn-master/mo/train_l.txt"
batch_size: 1
shuffle: false
}
}
but meet another error:
I0502 08:34:46.429774 19100 layer_factory.hpp:77] Creating layer data
I0502 08:34:46.429808 19100 net.cpp:100] Creating Layer data
I0502 08:34:46.429816 19100 net.cpp:408] data -> data
F0502 08:34:46.429834 19100 layer.hpp:389] Check failed: ExactNumTopBlobs() == top.size() (2 vs. 1) ImageData Layer produces 2 top blob(s) as output.
*** Check failure stack trace: ***
Aborted (core dumped)
train_o.txt:
/home/zhaimo/fcn-master/data/vessel/train/original/01.png
/home/zhaimo/fcn-master/data/vessel/train/original/02.png
/home/zhaimo/fcn-master/data/vessel/train/original/03.png
/home/zhaimo/fcn-master/data/vessel/train/original/04.png
/home/zhaimo/fcn-master/data/vessel/train/original/05.png
train_l.txt:
/home/zhaimo/SegNet/data/vessel/train/label/01.png
/home/zhaimo/SegNet/data/vessel/train/label/02.png
/home/zhaimo/SegNet/data/vessel/train/label/03.png
/home/zhaimo/SegNet/data/vessel/train/label/04.png
/home/zhaimo/SegNet/data/vessel/train/label/05.png
===============================Update2===================================
if I use two ImageData layers,how to modify the deploy.prototxt?
here is the file I wrote:
layer {
name: "data"
type: "ImageData"
top: "data"
top: "tmp0"
input_param { shape: { dim: 1 dim: 1 dim: 224 dim: 224 } }
}
and the forward.py file:
import numpy as np
from PIL import Image
caffe_root = '/home/zhaimo/'
import sys
sys.path.insert(0, caffe_root + 'caffe-master/python')
import caffe
# load image, switch to BGR, subtract mean, and make dims C x H x W for Caffe
im = Image.open('/home/zhaimo/fcn-master/data/vessel/test/13.png')
in_ = np.array(im, dtype=np.float32)
#in_ = in_[:,:,::-1]
#in_ -= np.array((104.00698793,116.66876762,122.67891434))
#in_ = in_.transpose((2,0,1))
# load net
net = caffe.Net('/home/zhaimo/fcn-master/mo/deploy.prototxt', '/home/zhaimo/fcn-master/mo/snapshot/train/_iter_200000.caffemodel', caffe.TEST)
# shape for input (data blob is N x C x H x W), set data
net.blobs['data'].reshape(1, *in_.shape)
net.blobs['data'].data[...] = in_
# run net and take argmax for prediction
net.forward()
out = net.blobs['score'].data[0].argmax(axis=0)
plt.axis('off')
plt.savefig('/home/zhaimo/fcn-master/mo/result/13.png')
but I meet the error:
F0504 08:16:46.423981 3383 layer.hpp:389] Check failed: ExactNumTopBlobs() == top.size() (2 vs. 1) ImageData Layer produces 2 top blob(s) as output.
how to modify the forward.py file,please?

Answer 1

Your problem is with the data top blob numbers. For two imagedata layer use this:
layer {
name: "data"
type: "ImageData"
top: "data"
top: "tmp"
image_data_param {
source: "/home/zhaimo/fcn-master/mo/train_o.txt"
batch_size: 1
shuffle: false
}
}
layer {
name: "label"
type: "ImageData"
top: "label"
top: "tmp1"
image_data_param {
// you probably also need
//is_color: false
source: "/home/zhaimo/fcn-master/mo/train_l.txt"
batch_size: 1
shuffle: false
}
}
In the text file just set all label to 0. You are not going to use tmp/tmp1 so it doesn't matter.