How to create own dataset for FCN with caffe? - dataset

Question

How to convert image to lmdb for fcn with caffe? You know, It's easy create own dataset for image classification with caffe, but how to create own dataset for semantic segment for fcn?

Answer 1

Use this code. Make the necessary path changes. Please read the code carefully before using it.
import caffe
import lmdb
from PIL import Image
import numpy as np
import glob
from random import shuffle
# Initialize the Image set:
NumberTrain = 1111 # Number of Training Images
NumberTest = 1112 # Number of Testing Images
Rheight = 380 # Required Height
Rwidth = 500 # Required Width
LabelHeight = 380 # Downscaled height of the label
LabelWidth = 500 # Downscaled width of the label
# Read the files in the Data Folder
inputs_data_train = sorted(glob.glob("/home/<user>/caffe-with_crop/examples/fcn-32s/TrainData/*.jpg"))
inputs_data_valid = sorted(glob.glob("/home/<user>/caffe-with_crop/examples/fcn-32s/ValData/*.jpg"))
inputs_label = sorted(glob.glob("/home/<user>/caffe-with_crop/examples/fcn-32s/VOC2011/SegmentationClass/*.png"))
shuffle(inputs_data_train) # Shuffle the DataSet
shuffle(inputs_data_valid) # Shuffle the DataSet
inputs_Train = inputs_data_train[:NumberTrain] # Extract the training data from the complete set
inputs_Test = inputs_data_valid[:NumberTest] # Extract the testing data from the complete set
# Creating LMDB for Training Data
print("Creating Training Data LMDB File ..... ")
in_db = lmdb.open('/home/<user>/caffe-with_crop/examples/fcn-32s/TrainVOC_Data_lmdb',map_size=int(1e14))
with in_db.begin(write=True) as in_txn:
for in_idx, in_ in enumerate(inputs_Train):
print in_idx
im = np.array(Image.open(in_)) # or load whatever ndarray you need
Dtype = im.dtype
im = im[:,:,::-1]
im = Image.fromarray(im)
im = im.resize([Rheight, Rwidth], Image.ANTIALIAS)
im = np.array(im,Dtype)
im = im.transpose((2,0,1))
im_dat = caffe.io.array_to_datum(im)
in_txn.put('{:0>10d}'.format(in_idx),im_dat.SerializeToString())
in_db.close()
# Creating LMDB for Training Labels
print("Creating Training Label LMDB File ..... ")
in_db = lmdb.open('/home/<user>/caffe-with_crop/examples/fcn-32s/TrainVOC_Label_lmdb',map_size=int(1e14))
with in_db.begin(write=True) as in_txn:
for in_idx, in_ in enumerate(inputs_Train):
print in_idx
in_label = in_[:-25]+'VOC2011/SegmentationClass/'+in_[-15:-3]+'png' # Change the numbers as per requirement
L = np.array(Image.open(in_)) # or load whatever ndarray you need
Dtype = L.dtype
L = L[:,:,::-1]
Limg = Image.fromarray(L)
Limg = Limg.resize([LabelHeight, LabelWidth],Image.NEAREST) # To resize the Label file to the required size
L = np.array(Limg,Dtype)
L = L.reshape(L.shape[0],L.shape[1],1)
L = L.transpose((2,0,1))
L_dat = caffe.io.array_to_datum(L)
in_txn.put('{:0>10d}'.format(in_idx),L_dat.SerializeToString())
in_db.close()
# Creating LMDB for Testing Data
print("Creating Testing Data LMDB File ..... ")
in_db = lmdb.open('/home/<user>/caffe-with_crop/examples/fcn-32s/TestVOC_Data_lmdb',map_size=int(1e14))
with in_db.begin(write=True) as in_txn:
for in_idx, in_ in enumerate(inputs_Test):
print in_idx
im = np.array(Image.open(in_)) # or load whatever ndarray you need
Dtype = im.dtype
im = im[:,:,::-1]
im = Image.fromarray(im)
im = im.resize([Rheight, Rwidth], Image.ANTIALIAS)
im = np.array(im,Dtype)
im = im.transpose((2,0,1))
im_dat = caffe.io.array_to_datum(im)
in_txn.put('{:0>10d}'.format(in_idx),im_dat.SerializeToString())
in_db.close()
# Creating LMDB for Testing Labels
print("Creating Testing Label LMDB File ..... ")
in_db = lmdb.open('/home/<user>/caffe-with_crop/examples/fcn-32s/TestVOC_Label_lmdb',map_size=int(1e14))
with in_db.begin(write=True) as in_txn:
for in_idx, in_ in enumerate(inputs_Test):
print in_idx
in_label = in_[:-25]+'VOC2011/SegmentationClass/'+in_[-15:-3]+'png' # Change the numbers as per requirement
L = np.array(Image.open(in_)) # or load whatever ndarray you need
Dtype = L.dtype
L = L[:,:,::-1]
Limg = Image.fromarray(L)
Limg = Limg.resize([LabelHeight, LabelWidth],Image.NEAREST) # To resize the Label file to the required size
L = np.array(Limg,Dtype)
L = L.reshape(L.shape[0],L.shape[1],1)
L = L.transpose((2,0,1))
L_dat = caffe.io.array_to_datum(L)
in_txn.put('{:0>10d}'.format(in_idx),L_dat.SerializeToString())
in_db.close()