def detect_skimage(cfgfile, weightfile, imgfile):
from skimage import io
from skimage.transform import resize
m = Darknet(cfgfile)
m.print_network()
m.load_weights(weightfile)
print('Loading weights from %s... Done!' % (weightfile))
if m.num_classes == 20:
namesfile = 'data/voc.names'
elif m.num_classes == 80:
namesfile = 'data/coco.names'
else:
namesfile = 'data/names'
use_cuda = 1
if use_cuda:
m.cuda()
img = io.imread(imgfile)
sized = resize(img, (m.width, m.height)) * 255
for i in range(2):
start = time.time()
boxes = do_detect(m, sized, 0.5, 0.4, use_cuda)
finish = time.time()
if i == 1:
print('%s: Predicted in %f seconds.' % (imgfile, (finish - start)))
class_names = load_class_names(namesfile)
plot_boxes_cv2(img,
boxes,
savename='predictions.jpg',
class_names=class_names)
def detect(cfgfile, weightfile, imgfile):
m = Darknet(cfgfile)
m.print_network()
m.load_weights(weightfile)
print('Loading weights from %s... Done!' % (weightfile))
if m.num_classes == 20:
namesfile = 'data/voc.names'
elif m.num_classes == 80:
namesfile = 'data/coco.names'
else:
namesfile = 'data/names'
use_cuda = 1
if use_cuda:
m.cuda()
img = Image.open(imgfile).convert('RGB')
sized = img.resize((m.width, m.height))
for i in range(2):
start = time.time()
boxes = do_detect(m, sized, 0.5, 0.4, use_cuda)
finish = time.time()
if i == 1:
print('%s: Predicted in %f seconds.' % (imgfile, (finish - start)))
class_names = load_class_names(namesfile)
plot_boxes(img, boxes, 'predictions.jpg', class_names)
def demo(cfgfile, weightfile):
m = Darknet(cfgfile)
m.print_network()
m.load_weights(weightfile)
print('Loading weights from %s... Done!' % (weightfile))
if m.num_classes == 20:
namesfile = 'data/voc.names'
elif m.num_classes == 80:
namesfile = 'data/coco.names'
else:
namesfile = 'data/names'
class_names = load_class_names(namesfile)
use_cuda = 1
if use_cuda:
m.cuda()
cap = cv2.VideoCapture(0)
if not cap.isOpened():
print("Unable to open camera")
exit(-1)
while True:
res, img = cap.read()
if res:
sized = cv2.resize(img, (m.width, m.height))
bboxes = do_detect(m, sized, 0.5, 0.4, use_cuda)
print('------')
draw_img = plot_boxes_cv2(img, bboxes, None, class_names)
cv2.imshow(cfgfile, draw_img)
cv2.waitKey(1)
else:
print("Unable to read image")
exit(-1)
def partial(cfgfile, weightfile, outfile, cutoff):
m = Darknet(cfgfile)
m.print_network()
m.load_weights(weightfile)
m.seen = 0
m.save_weights(outfile, cutoff)
print('save %s' % (outfile))
if os.path.getsize(labpath):
tmp = torch.from_numpy(np.loadtxt(labpath))
#tmp = torch.from_numpy(read_truths_args(labpath, 8.0/img.width))
#tmp = torch.from_numpy(read_truths(labpath))
tmp = tmp.view(-1)
tsz = tmp.numel()
#print('labpath = %s , tsz = %d' % (labpath, tsz))
if tsz > 50*5:
label = tmp[0:50*5]
elif tsz > 0:
label[0:tsz] = tmp
label = label.view(1, 50*5)
m = Darknet(cfgfile)
region_loss = m.loss
m.load_weights(weightfile)
print('--- bn weight ---')
print(m.models[0][1].weight)
print('--- bn bias ---')
print(m.models[0][1].bias)
print('--- bn running_mean ---')
print(m.models[0][1].running_mean)
print('--- bn running_var ---')
print(m.models[0][1].running_var)
m.train()
m = m.cuda()
optimizer = optim.SGD(m.parameters(), lr=1e-2, momentum=0.9, weight_decay=0.1)
def eval_list(cfgfile, weightfile, imglist):
#m = TinyYoloFace14Net()
#m.eval()
#m.load_darknet_weights(tiny_yolo_weight)
m = Darknet(cfgfile)
m.eval()
m.load_weights(weightfile)
eval_wid = m.width
eval_hei = m.height
use_cuda = 1
if use_cuda:
m.cuda()
conf_thresh = 0.25
nms_thresh = 0.4
iou_thresh = 0.5
min_box_scale = 8. / m.width
with open(imglist) as fp:
lines = fp.readlines()
total = 0.0
proposals = 0.0
correct = 0.0
lineId = 0
avg_iou = 0.0
for line in lines:
img_path = line.rstrip()
if img_path[0] == '#':
continue
lineId = lineId + 1
lab_path = img_path.replace('images', 'labels')
lab_path = lab_path.replace('JPEGImages', 'labels')
lab_path = lab_path.replace('.jpg', '.txt').replace('.png', '.txt')
#truths = read_truths(lab_path)
truths = read_truths_args(lab_path, min_box_scale)
#print(truths)
img = Image.open(img_path).convert('RGB').resize((eval_wid, eval_hei))
boxes = do_detect(m, img, conf_thresh, nms_thresh, use_cuda)
if False:
savename = "tmp/%06d.jpg" % (lineId)
print("save %s" % savename)
plot_boxes(img, boxes, savename)
total = total + truths.shape[0]
for i in range(len(boxes)):
if boxes[i][4] > conf_thresh:
proposals = proposals + 1
for i in range(truths.shape[0]):
box_gt = [
truths[i][1], truths[i][2], truths[i][3], truths[i][4], 1.0
]
best_iou = 0
for j in range(len(boxes)):
iou = bbox_iou(box_gt, boxes[j], x1y1x2y2=False)
best_iou = max(iou, best_iou)
if best_iou > iou_thresh:
avg_iou += best_iou
correct = correct + 1
precision = 1.0 * correct / proposals
recall = 1.0 * correct / total
fscore = 2.0 * precision * recall / (precision + recall)
print("%d IOU: %f, Recal: %f, Precision: %f, Fscore: %f\n" %
(lineId - 1, avg_iou / correct, recall, precision, fscore))
backupdir = cfg.backup
print('logging to ' + backupdir)
if not os.path.exists(backupdir):
os.mkdir(backupdir)
###############
torch.manual_seed(seed)
if use_cuda:
os.environ['CUDA_VISIBLE_DEVICES'] = gpus
torch.cuda.manual_seed(seed)
model = Darknet(cfgfile)
region_loss = model.loss
model.load_weights(weightfile)
model.print_network()
# Prepare dataset
if cfg.yolo_joint:
trainlist = dataset.loadlines(trainlist)
n_bef = len(set(trainlist))
metalist = dataset.loadlines(data_options['meta'], checkvalid=False)
trainlist = sorted(list(set(trainlist + metalist)))
n_aft = len(trainlist)
print("number of samples: {} to {}".format(n_bef, n_aft))
trainlist *= cfg.repeat
else:
trainlist = dataset.loadlines(trainlist) * cfg.repeat
nsamples = len(trainlist)
def valid(datacfg, cfgfile, weightfile, outfile):
options = read_data_cfg(datacfg)
valid_images = options['valid']
# backup = cfg.backup
backup = weightfile.split('/')[-2]
ckpt = weightfile.split('/')[-1].split('.')[0]
prefix = 'results/' + backup.split('/')[-1] + '/e' + ckpt
print('saving to: ' + prefix)
names = cfg.classes
with open(valid_images) as fp:
tmp_files = fp.readlines()
valid_files = [item.rstrip() for item in tmp_files]
m = Darknet(cfgfile)
m.print_network()
m.load_weights(weightfile)
m.cuda()
m.eval()
valid_dataset = dataset.listDataset(valid_images, shape=(m.width, m.height),
shuffle=False,
transform=transforms.Compose([
transforms.ToTensor(),
]))
valid_batchsize = 2
assert(valid_batchsize > 1)
kwargs = {'num_workers': 4, 'pin_memory': True}
valid_loader = torch.utils.data.DataLoader(
valid_dataset, batch_size=valid_batchsize, shuffle=False, **kwargs)
fps = [0]*m.num_classes
if not os.path.exists(prefix):
# os.mkdir(prefix)
os.makedirs(prefix)
for i in range(m.num_classes):
buf = '%s/%s%s.txt' % (prefix, outfile, names[i])
fps[i] = open(buf, 'w')
lineId = -1
conf_thresh = 0.005
nms_thresh = 0.45
for batch_idx, (data, target) in enumerate(valid_loader):
data = data.cuda()
data = Variable(data, volatile = True)
output = m(data).data
batch_boxes = get_region_boxes(output, conf_thresh, m.num_classes, m.anchors, m.num_anchors, 0, 1)
for i in range(output.size(0)):
lineId = lineId + 1
fileId = os.path.basename(valid_files[lineId]).split('.')[0]
width, height = get_image_size(valid_files[lineId])
print(valid_files[lineId])
boxes = batch_boxes[i]
boxes = nms(boxes, nms_thresh)
for box in boxes:
x1 = (box[0] - box[2]/2.0) * width
y1 = (box[1] - box[3]/2.0) * height
x2 = (box[0] + box[2]/2.0) * width
y2 = (box[1] + box[3]/2.0) * height
det_conf = box[4]
# import pdb
# pdb.set_trace()
for j in range((len(box)-5)/2):
cls_conf = box[5+2*j]
cls_id = box[6+2*j]
prob =det_conf * cls_conf
fps[cls_id].write('%s %f %f %f %f %f\n' % (fileId, prob, x1, y1, x2, y2))
# fps[cls_id].write('%s %f %f %f %f %f %f\n' % (fileId, det_conf, cls_conf, x1, y1, x2, y2))
for i in range(m.num_classes):
fps[i].close()