Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions egs/cifar/v1/local/prepare_data.sh
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,11 @@ else
wget -P $dl_dir $cifar10_url || exit 1;
fi
tar -xvzf $dl_dir/cifar-10-binary.tar.gz -C $dl_dir || exit 1;
echo Done downaloding and extracting CIFAR-10
echo Done downloading and extracting CIFAR-10
fi

mkdir -p data/cifar10_{train,test}/data
seq 0 9 | paste -d' ' data/dl/cifar-10-batches-bin/batches.meta.txt - | grep '\S' >data/cifar10_train/classes.txt
seq 0 9 | paste -d' ' $cifar10/batches.meta.txt - | grep '\S' >data/cifar10_train/classes.txt
cp data/cifar10_{train,test}/classes.txt
echo 3 > data/cifar10_train/num_channels
echo 3 > data/cifar10_test/num_channels
Expand All @@ -51,7 +51,7 @@ else
wget -P $dl_dir $cifar100_url || exit 1;
fi
tar -xvzf $dl_dir/cifar-100-binary.tar.gz -C $dl_dir || exit 1;
echo Done downloadding and extracting CIFAR-100
echo Done downloading and extracting CIFAR-100
fi

mkdir -p data/cifar100_{train,test}/data
Expand All @@ -66,10 +66,10 @@ cp data/cifar100_{train,test}/classes.txt
echo 3 > data/cifar100_train/num_channels
echo 3 > data/cifar100_test/num_channels

local/process_data.py --dataset train $cifar100 data/cifar100_train/ | \
local/process_data.py --cifar-version CIFAR-100 --dataset train $cifar100 data/cifar100_train/ | \
copy-feats --compress=true --compression-method=7 \
ark:- ark,scp:data/cifar100_train/data/images.ark,data/cifar100_train/images.scp || exit 1

local/process_data.py --dataset test $cifar100 data/cifar100_test/ | \
local/process_data.py --cifar-version CIFAR-100 --dataset test $cifar100 data/cifar100_test/ | \
copy-feats --compress=true --compression-method=7 \
ark:- ark,scp:data/cifar100_test/data/images.ark,data/cifar100_test/images.scp || exit 1
11 changes: 6 additions & 5 deletions egs/cifar/v1/local/process_data.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
default='data/dl/cifar-10-batches-bin',
help='path to downloaded cifar data (binary version)')
parser.add_argument('dir', type=str, help='output dir')
parser.add_argument('--cifar-version', type=str, default='CIFAR-10', choices=['CIFAR-10', 'CIFAR-100'])
parser.add_argument('--dataset', type=str, default='train', choices=['train', 'test'])
parser.add_argument('--out-ark', type=str, default='-', help='where to write output feature data')

Expand Down Expand Up @@ -60,11 +61,11 @@ def load_cifar100_data_batch(datafile, num_images_in_batch):

def image_to_feat_matrix(img):
mat = [0]*H # 32 * 96
for row in range(H):
mat[row] = [0]*C*W
for i in range(W):
mat[i] = [0]*C*H
for ch in range(C):
for col in range(W):
mat[row][col*C+ch] = img[ch][row][col]
for j in range(H):
mat[i][j*C+ch] = img[ch][j][i]
return mat

def write_kaldi_matrix(file_handle, matrix, key):
Expand All @@ -91,7 +92,7 @@ def zeropad(x, length):
return s

### main ###
cifar10 = (args.database.find('cifar-100') == -1)
cifar10 = (args.cifar_version.lower() == 'cifar-10')
if args.out_ark == '-':
out_fh = sys.stdout # output file handle to write the feats to
else:
Expand Down