def main(params):
data = json.load(open(params['input_json'], 'r'))
#imgs = imgs['images']
seed(123) # make reproducible
#shuffle(imgs) # shuffle the order
imgs = data["images"]
prepro_captions(imgs)
# create the vocab
vocab = build_vocab(imgs, params)
itow = {i + 1: w for i, w in enumerate(vocab)} # a 1-indexed vocab translation table
wtoi = {w: i + 1 for i, w in enumerate(vocab)} # inverse table
# done
# assign the splits
assign_splits(imgs, params)
# encode captions in large arrays, ready to ship to hdf5 file
L, label_start_ix, label_end_ix, label_length = encode_captions(imgs, params, wtoi)
import misc.resnet as resnet
resnet_type = 'resnet151'
if resnet_type == 'resnet101':
resnet = resnet.resnet101()
resnet.load_state_dict(torch.load('resnet/resnet101.pth'))
else:
resnet = resnet.resnet152()
resnet.load_state_dict(torch.load('resnet/resnet152.pth'))
my_resnet = myResnet(resnet)
my_resnet.cuda()
my_resnet.eval()
# create output h5 file
N = len(imgs)
f_lb = h5py.File(params['output_h5'] + '_'+ resnet_type +'_label.h5', "w")
f_fc = h5py.File(params['output_h5'] + '_'+ resnet_type +'_fc.h5', "w")
f_att = h5py.File(params['output_h5'] + '_'+ resnet_type +'_att.h5', "w")
f_lb.create_dataset("labels", dtype='uint32', data=L)
f_lb.create_dataset("label_start_ix", dtype='uint32', data=label_start_ix)
f_lb.create_dataset("label_end_ix", dtype='uint32', data=label_end_ix)
f_lb.create_dataset("label_length", dtype='uint32', data=label_length)
f_lb.close()
#exit()
### extract features
dset_fc = f_fc.create_dataset("fc", (N, 2048), dtype='float32')
dset_att = f_att.create_dataset("att", (N, 14, 14, 2048), dtype='float32')
for i, img in enumerate(imgs):
# load the image
real_path = img['filepath'] + "/" + img['filename']
I = skimage.io.imread(os.path.join(params['images_root'],real_path)) # note the path
# handle grayscale input images
if len(I.shape) == 2:
I = I[:, :, np.newaxis]
I = np.concatenate((I, I, I), axis=2)
I = I.astype('float32') / 255.0
I = torch.from_numpy(I.transpose([2, 0, 1])).cuda()
I = Variable(preprocess(I), volatile=True)
tmp_fc, tmp_att = my_resnet(I)
# write to h5
dset_fc[i] = tmp_fc.data.cpu().float().numpy()
dset_att[i] = tmp_att.data.cpu().float().numpy()
if i % 1000 == 0:
print 'processing %d/%d (%.2f%% done)' % (i, N, i * 100.0 / N)
f_fc.close()
f_att.close()
print 'wrote ', params['output_h5']
# create output json file
out = {}
out['ix_to_word'] = itow # encode the (1-indexed) vocab
out['images'] = []
for i, img in enumerate(imgs):
jimg = {}
jimg['split'] = img['split']
if 'filepath' in img: jimg['filepath'] = img['filepath'] # copy it over, might need
if 'id' in img: jimg['id'] = img['id'] # copy over & mantain an id, if present (e.g. coco ids, useful)
out['images'].append(jimg)
json.dump(out, open(params['output_json'], 'w'))
print 'wrote ', params['output_json']
import torch
from torch.autograd import Variable
import skimage
import skimage.io
import scipy.misc
from torchvision import transforms as trn
preprocess = trn.Compose([
#trn.ToTensor(),
trn.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
from misc.resnet_utils import myResnet
import misc.resnet as resnet
resnet = resnet.resnet101()
resnet.load_state_dict(
torch.load('/datadrive/resnet_pretrianed_t7/resnet101.pth'))
my_resnet = myResnet(resnet)
my_resnet.cuda()
my_resnet.eval()
class DataLoaderRaw():
def __init__(self, opt):
self.opt = opt
self.coco_json = opt.get('coco_json', '')
self.folder_path = opt.get('folder_path', '')
self.batch_size = opt.get('batch_size', 1)
self.seq_per_img = 1
def main(params):
data = json.load(open(params['input_json'], 'r'))
#imgs = imgs['images']
seed(123) # make reproducible
#shuffle(imgs) # shuffle the order
imgs = data["images"]
prepro_captions(imgs)
# create the vocab
vocab = build_vocab(imgs, params)
itow = {i + 1: w
for i, w in enumerate(vocab)
} # a 1-indexed vocab translation table
wtoi = {w: i + 1 for i, w in enumerate(vocab)} # inverse table
# done
# assign the splits
assign_splits(imgs, params)
# encode captions in large arrays, ready to ship to hdf5 file
L, label_start_ix, label_end_ix, label_length = encode_captions(
imgs, params, wtoi)
import misc.resnet as resnet
resnet_type = 'resnet101'
if resnet_type == 'resnet101':
resnet = resnet.resnet101()
resnet.load_state_dict(torch.load('resnet/resnet101.pth'))
else:
resnet = resnet.resnet152()
resnet.load_state_dict(torch.load('resnet/resnet152.pth'))
my_resnet = myResnet(resnet)
my_resnet.cuda()
my_resnet.eval()
# create output h5 file
N = len(imgs)
f_lb = h5py.File(params['output_h5'] + '_' + resnet_type + '_label.h5',
"w")
f_fc = h5py.File(params['output_h5'] + '_' + resnet_type + '_fc.h5', "w")
f_att = h5py.File(params['output_h5'] + '_' + resnet_type + '_att.h5', "w")
f_lb.create_dataset("labels", dtype='uint32', data=L)
f_lb.create_dataset("label_start_ix", dtype='uint32', data=label_start_ix)
f_lb.create_dataset("label_end_ix", dtype='uint32', data=label_end_ix)
f_lb.create_dataset("label_length", dtype='uint32', data=label_length)
f_lb.close()
#exit()
### extract features
dset_fc = f_fc.create_dataset("fc", (N, 2048), dtype='float32')
dset_att = f_att.create_dataset("att", (N, 14, 14, 2048), dtype='float32')
for i, img in enumerate(imgs):
# load the image
real_path = img['filepath'] + "/" + img['filename']
I = skimage.io.imread(os.path.join(params['images_root'],
real_path)) # note the path
# handle grayscale input images
if len(I.shape) == 2:
I = I[:, :, np.newaxis]
I = np.concatenate((I, I, I), axis=2)
I = I.astype('float32') / 255.0
I = torch.from_numpy(I.transpose([2, 0, 1])).cuda()
I = Variable(preprocess(I), volatile=True)
tmp_fc, tmp_att = my_resnet(I)
# write to h5
dset_fc[i] = tmp_fc.data.cpu().float().numpy()
dset_att[i] = tmp_att.data.cpu().float().numpy()
if i % 1000 == 0:
print 'processing %d/%d (%.2f%% done)' % (i, N, i * 100.0 / N)
f_fc.close()
f_att.close()
print 'wrote ', params['output_h5']
# create output json file
out = {}
out['ix_to_word'] = itow # encode the (1-indexed) vocab
out['images'] = []
for i, img in enumerate(imgs):
jimg = {}
jimg['split'] = img['split']
if 'filepath' in img:
jimg['filepath'] = img['filepath'] # copy it over, might need
if 'id' in img:
jimg['id'] = img[
'id'] # copy over & mantain an id, if present (e.g. coco ids, useful)
out['images'].append(jimg)
json.dump(out, open(params['output_json'], 'w'))
print 'wrote ', params['output_json']