def extract_features(model, use_gpu, args,test_transform, return_distmat=False,use_cosine = False,draw_tsne=False):
batch_size = 64
def load_dataset():
test_dataset = torchvision.datasets.ImageFolder(
root=args.single_folder,
transform=test_transform
)
test_loader = torch.utils.data.DataLoader(
test_dataset,
batch_size=batch_size,
num_workers=0,
shuffle=False
)
return test_loader, test_dataset
loader, dataset = load_dataset()
model.eval()
with torch.no_grad():
qf = []
for batch_idx, (input) in enumerate(loader):
if not args.draw_tsne:
imgs, _ = input
else:
imgs, _,_ = input
if use_gpu: imgs = imgs.cuda()
end = time.time()
features = model(imgs)
features = features.data.cpu()
qf.append(features)
qf = torch.cat(qf, 0)
m = qf.size(0)
distmat_q_q = torch.pow(qf, 2).sum(dim=1, keepdim=True).expand(m, m) + \
torch.pow(qf, 2).sum(dim=1, keepdim=True).expand(m, m).t()
distmat_q_q.addmm_(1, -2, qf, qf.t())
distmat_q_q = distmat_q_q.numpy()
print("Pairwise distance")
print(distmat_q_q)
model.module.cam = True
grad_cam = GradCam(model = model, target_layer_names = ["35"], use_cuda=True)
for batch_idx, (imgs,_) in enumerate(loader):
for i,(img) in enumerate(imgs):
img_path = dataset.samples[batch_idx*batch_size+i][0]
mask, _ = grad_cam(img.unsqueeze_(0),args, None)
dir = os.path.join(args.save_dir,'heatMaps')
mkdir_if_missing(dir)
orig_img = cv2.imread(img_path,1)
cv_img = np.float32(cv2.resize(orig_img, (args.width, args.height))) / 255
outptut_img = show_cam_on_image(cv_img, mask)
cv2.imwrite(os.path.join(dir,os.path.splitext(os.path.basename(img_path))[0]+'_heatmap.jpg'),outptut_img)
#utils_torch.save_image(img,os.path.join(dir,os.path.splitext(os.path.basename(dataset.query[batch_idx*args.test_batch+i][0]))[0]+'_PIL_gb.jpg'))
cv2.imwrite(os.path.join(dir,os.path.splitext(os.path.basename(img_path))[0]+'.jpg'),orig_img)
model.module.cam = False
def download_data(self):
if osp.exists(self.dataset_dir):
return
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
print('Downloading iLIDS-VID dataset')
urllib.urlretrieve(self.dataset_url, fpath)
print('Extracting files')
tar = tarfile.open(fpath)
tar.extractall(path=self.dataset_dir)
tar.close()
def _download_data(self):
if osp.exists(self.dataset_dir):
print("This dataset has been downloaded.")
return
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
print("Downloading iLIDS-VID dataset")
urllib.urlretrieve(self.dataset_url, fpath)
print("Extracting files")
tar = tarfile.open(fpath)
tar.extractall(path=self.dataset_dir)
tar.close()
def download_data(self):
if osp.exists(self.dataset_dir):
return
print('Creating directory {}'.format(self.dataset_dir))
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
print('Downloading DukeMTMC-VideoReID dataset')
urllib.urlretrieve(self.dataset_url, fpath)
print('Extracting files')
zip_ref = zipfile.ZipFile(fpath, 'r')
zip_ref.extractall(self.dataset_dir)
zip_ref.close()
def download_data(self):
if osp.exists(self.dataset_dir):
return
print('Creating directory {}'.format(self.dataset_dir))
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, 'prid_450s.zip')
print('Downloading PRID450S dataset')
urllib.urlretrieve(self.dataset_url, fpath)
print('Extracting files')
zip_ref = zipfile.ZipFile(fpath, 'r')
zip_ref.extractall(self.dataset_dir)
zip_ref.close()
def _download_data(self):
if osp.exists(self.dataset_dir):
print("This dataset has been downloaded.")
return
print("Creating directory {}".format(self.dataset_dir))
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
print("Downloading DukeMTMC-VideoReID dataset")
urllib.urlretrieve(self.dataset_url, fpath)
print("Extracting files")
zip_ref = zipfile.ZipFile(fpath, 'r')
zip_ref.extractall(self.dataset_dir)
zip_ref.close()
def _download_data(self):
if osp.exists(self.dataset_dir):
print("This dataset has been downloaded.")
return
print("Creating directory {}".format(self.dataset_dir))
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, 'prid_450s.zip')
print("Downloading PRID450S dataset")
urllib.request.urlretrieve(self.dataset_url, fpath)
print("Extracting files")
zip_ref = zipfile.ZipFile(fpath, 'r')
zip_ref.extractall(self.dataset_dir)
zip_ref.close()
def _download_data(self):
if osp.exists(self.dataset_dir):
print('This dataset has been downloaded.')
return
print('Creating directory {}'.format(self.dataset_dir))
mkdir_if_missing(self.dataset_dir)
fpath = osp.join(self.dataset_dir, osp.basename(self.dataset_url))
print('Downloading VIPeR dataset')
urllib.urlretrieve(self.dataset_url, fpath)
print('Extracting files')
zip_ref = zipfile.ZipFile(fpath, 'r')
zip_ref.extractall(self.dataset_dir)
zip_ref.close()
def _preprocess(self):
"""
This function is a bit complex and ugly, what it does is
1. Extract data from cuhk-03.mat and save as png images.
2. Create 20 classic splits. (Li et al. CVPR'14)
3. Create new split. (Zhong et al. CVPR'17)
"""
print("Note: if root path is changed, the previously generated json files need to be re-generated (delete them first)")
if osp.exists(self.imgs_labeled_dir) and \
osp.exists(self.imgs_detected_dir) and \
osp.exists(self.split_classic_det_json_path) and \
osp.exists(self.split_classic_lab_json_path) and \
osp.exists(self.split_new_det_json_path) and \
osp.exists(self.split_new_lab_json_path):
return
mkdir_if_missing(self.imgs_detected_dir)
mkdir_if_missing(self.imgs_labeled_dir)
print("Extract image data from {} and save as png".format(self.raw_mat_path))
mat = h5py.File(self.raw_mat_path, 'r')
def _deref(ref):
return mat[ref][:].T
def _process_images(img_refs, campid, pid, save_dir):
img_paths = [] # Note: some persons only have images for one view
for imgid, img_ref in enumerate(img_refs):
img = _deref(img_ref)
# skip empty cell
if img.size == 0 or img.ndim < 3: continue
# images are saved with the following format, index-1 (ensure uniqueness)
# campid: index of camera pair (1-5)
# pid: index of person in 'campid'-th camera pair
# viewid: index of view, {1, 2}
# imgid: index of image, (1-10)
viewid = 1 if imgid < 5 else 2
img_name = '{:01d}_{:03d}_{:01d}_{:02d}.png'.format(campid+1, pid+1, viewid, imgid+1)
img_path = osp.join(save_dir, img_name)
if not osp.isfile(img_path):
cv2.imwrite(img_path, img)
img_paths.append(img_path)
return img_paths
def _extract_img(name):
print("Processing {} images (extract and save) ...".format(name))
meta_data = []
imgs_dir = self.imgs_detected_dir if name == 'detected' else self.imgs_labeled_dir
for campid, camp_ref in enumerate(mat[name][0]):
camp = _deref(camp_ref)
num_pids = camp.shape[0]
for pid in range(num_pids):
img_paths = _process_images(camp[pid,:], campid, pid, imgs_dir)
assert len(img_paths) > 0, "campid{}-pid{} has no images".format(campid, pid)
meta_data.append((campid+1, pid+1, img_paths))
print("- done camera pair {} with {} identities".format(campid+1, num_pids))
return meta_data
meta_detected = _extract_img('detected')
meta_labeled = _extract_img('labeled')
def _extract_classic_split(meta_data, test_split):
train, test = [], []
num_train_pids, num_test_pids = 0, 0
num_train_imgs, num_test_imgs = 0, 0
for i, (campid, pid, img_paths) in enumerate(meta_data):
if [campid, pid] in test_split:
for img_path in img_paths:
camid = int(osp.basename(img_path).split('_')[2]) - 1 # make it 0-based
test.append((img_path, num_test_pids, camid))
num_test_pids += 1
num_test_imgs += len(img_paths)
else:
for img_path in img_paths:
camid = int(osp.basename(img_path).split('_')[2]) - 1 # make it 0-based
train.append((img_path, num_train_pids, camid))
num_train_pids += 1
num_train_imgs += len(img_paths)
return train, num_train_pids, num_train_imgs, test, num_test_pids, num_test_imgs
print("Creating classic splits (# = 20) ...")
splits_classic_det, splits_classic_lab = [], []
for split_ref in mat['testsets'][0]:
test_split = _deref(split_ref).tolist()
# create split for detected images
train, num_train_pids, num_train_imgs, test, num_test_pids, num_test_imgs = \
_extract_classic_split(meta_detected, test_split)
splits_classic_det.append({
'train': train, 'query': test, 'gallery': test,
'num_train_pids': num_train_pids, 'num_train_imgs': num_train_imgs,
'num_query_pids': num_test_pids, 'num_query_imgs': num_test_imgs,
'num_gallery_pids': num_test_pids, 'num_gallery_imgs': num_test_imgs,
})
# create split for labeled images
train, num_train_pids, num_train_imgs, test, num_test_pids, num_test_imgs = \
_extract_classic_split(meta_labeled, test_split)
splits_classic_lab.append({
'train': train, 'query': test, 'gallery': test,
'num_train_pids': num_train_pids, 'num_train_imgs': num_train_imgs,
'num_query_pids': num_test_pids, 'num_query_imgs': num_test_imgs,
'num_gallery_pids': num_test_pids, 'num_gallery_imgs': num_test_imgs,
})
write_json(splits_classic_det, self.split_classic_det_json_path)
write_json(splits_classic_lab, self.split_classic_lab_json_path)
def _extract_set(filelist, pids, pid2label, idxs, img_dir, relabel):
tmp_set = []
unique_pids = set()
for idx in idxs:
img_name = filelist[idx][0]
camid = int(img_name.split('_')[2]) - 1 # make it 0-based
pid = pids[idx]
if relabel: pid = pid2label[pid]
img_path = osp.join(img_dir, img_name)
tmp_set.append((img_path, int(pid), camid))
unique_pids.add(pid)
return tmp_set, len(unique_pids), len(idxs)
def _extract_new_split(split_dict, img_dir):
train_idxs = split_dict['train_idx'].flatten() - 1 # index-0
pids = split_dict['labels'].flatten()
train_pids = set(pids[train_idxs])
pid2label = {pid: label for label, pid in enumerate(train_pids)}
query_idxs = split_dict['query_idx'].flatten() - 1
gallery_idxs = split_dict['gallery_idx'].flatten() - 1
filelist = split_dict['filelist'].flatten()
train_info = _extract_set(filelist, pids, pid2label, train_idxs, img_dir, relabel=True)
query_info = _extract_set(filelist, pids, pid2label, query_idxs, img_dir, relabel=False)
gallery_info = _extract_set(filelist, pids, pid2label, gallery_idxs, img_dir, relabel=False)
return train_info, query_info, gallery_info
print("Creating new splits for detected images (767/700) ...")
train_info, query_info, gallery_info = _extract_new_split(
loadmat(self.split_new_det_mat_path),
self.imgs_detected_dir,
)
splits = [{
'train': train_info[0], 'query': query_info[0], 'gallery': gallery_info[0],
'num_train_pids': train_info[1], 'num_train_imgs': train_info[2],
'num_query_pids': query_info[1], 'num_query_imgs': query_info[2],
'num_gallery_pids': gallery_info[1], 'num_gallery_imgs': gallery_info[2],
}]
write_json(splits, self.split_new_det_json_path)
print("Creating new splits for labeled images (767/700) ...")
train_info, query_info, gallery_info = _extract_new_split(
loadmat(self.split_new_lab_mat_path),
self.imgs_labeled_dir,
)
splits = [{
'train': train_info[0], 'query': query_info[0], 'gallery': gallery_info[0],
'num_train_pids': train_info[1], 'num_train_imgs': train_info[2],
'num_query_pids': query_info[1], 'num_query_imgs': query_info[2],
'num_gallery_pids': gallery_info[1], 'num_gallery_imgs': gallery_info[2],
}]
write_json(splits, self.split_new_lab_json_path)
