def eval(net, test_num=10000):
net.eval()
def transform(img, boxes, labels):
img, boxes = resize(img, boxes, size=(opt.img_size, opt.img_size))
img = transforms.Compose([transforms.ToTensor(), caffe_normalize])(img)
return img, boxes, labels
dataset = ListDataset(root=opt.eval_img_root,
list_file=opt.eval_img_list,
transform=transform)
box_coder = SSDBoxCoder(net.module)
pred_boxes = []
pred_labels = []
pred_scores = []
gt_boxes = []
gt_labels = []
# with open('torchcv/datasets/voc/voc07_test_difficult.txt') as f:
# gt_difficults = []
# for line in f.readlines():
# line = line.strip().split()
# d = np.array([int(x) for x in line[1:]])
# gt_difficults.append(d)
nums_img = dataset.__len__()
for i in tqdm(range(nums_img)):
inputs, box_targets, label_targets = dataset.__getitem__(i)
gt_boxes.append(box_targets)
gt_labels.append(label_targets)
inputs = inputs.unsqueeze(0)
with torch.no_grad():
loc_preds, cls_preds = net(Variable(inputs.cuda()))
box_preds, label_preds, score_preds = box_coder.decode(
loc_preds.cpu().data.squeeze(),
F.softmax(cls_preds.squeeze(), dim=1).cpu().data,
score_thresh=0.1)
pred_boxes.append(box_preds)
pred_labels.append(label_preds)
pred_scores.append(score_preds)
aps = (voc_eval(pred_boxes,
pred_labels,
pred_scores,
gt_boxes,
gt_labels,
gt_difficults=None,
iou_thresh=0.5,
use_07_metric=False))
net.train()
return aps
# bgr and 0-255
])(x)
def transform(img, boxes, labels):
img, boxes = resize(img, boxes, size=(opt.img_size, opt.img_size))
img = transforms.Compose([
transforms.ToTensor(),
caffe_normalize
])(img)
return img, boxes, labels
dataset = ListDataset(root=opt.eval_img_root, list_file=opt.eval_img_list, transform=transform)
box_coder = SSDBoxCoder(net.module)
nums_img = dataset.__len__()
idx = random.randint(0, nums_img)
inputs, _, _ = dataset.__getitem__(idx)
inputs = inputs.unsqueeze(0)
with torch.no_grad():
loc_preds, cls_preds = net(Variable(inputs.cuda()))
boxes, labels, scores = box_coder.decode(
loc_preds.cpu().data.squeeze(), F.softmax(cls_preds.squeeze(), dim=1).cpu().data, score_thresh=0.5)
img = Image.open(opt.eval_img_root + dataset.fnames[idx])
sw = float(img.size[0])/float(opt.img_size)
sh = float(img.size[1])/float(opt.img_size)
boxes = boxes.type(torch.FloatTensor) * torch.tensor([sw, sh, sw, sh])
draw = ImageDraw.Draw(img)
nums_boxes = boxes.size()[0]
for i in range(nums_boxes):
draw.rectangle(list(boxes[i]), outline='red')
draw.text((boxes[i][0], boxes[i][1]), 'category: %s' % labels[i].item(), 'yellow')
pred_labels = []
pred_scores = []
gt_boxes = []
gt_labels = []
#with open('torchcv/datasets/voc/voc07_test_difficult.txt') as f:
# gt_difficults = []
# for line in f.readlines():
# line = line.strip().split()
# d = np.array([int(x) for x in line[1:]])
# gt_difficults.append(d)
print('Processing img..')
nums_img = dataset.__len__()
for i in tqdm(range(nums_img)):
inputs, box_targets, label_targets = dataset.__getitem__(i)
gt_boxes.append(box_targets)
gt_labels.append(label_targets)
inputs = inputs.unsqueeze(0)
with torch.no_grad():
loc_preds, cls_preds = net(Variable(inputs.cuda()))
box_preds, label_preds, score_preds = box_coder.decode(
loc_preds.cpu().data.squeeze(),
F.softmax(cls_preds.squeeze(), dim=1).cpu().data,
score_thresh=0.1)
pred_boxes.append(box_preds)
pred_labels.append(label_preds)
pred_scores.append(score_preds)