def detect_pnet(pnet, im, thresh, min_face_size=200, scale_factor=0.709):
h, w, c = im.shape
net_size = 12
current_scale = float(net_size) / min_face_size
im_resized = resize_image(im, current_scale)
current_height, current_width, _ = im_resized.shape
all_boxes = list()
while min(current_height, current_width) > net_size:
feed_imgs = []
image_tensor = image_tools.convert_image_to_tensor(im_resized)
feed_imgs.append(image_tensor)
feed_imgs = torch.stack(feed_imgs)
feed_imgs = feed_imgs.float().cuda()
cls_map, reg = pnet(feed_imgs) # (batch, 2, h, w), (batch, 4*2, h, w)
cls_map = torch.sigmoid(cls_map)
# remove the batch dimension, for batch is always 1 for inference.
cls_probability = cls_map.cpu().numpy()[0]
reg_np = reg.cpu().numpy()[0]
boxes = generate_bounding_box(cls_probability.transpose(1, 2, 0),
reg_np.transpose(1, 2, 0), current_scale,
thresh) # num, 10
if len(boxes) != 0:
all_boxes.append(boxes)
current_scale *= scale_factor
im_resized = resize_image(im, current_scale)
current_height, current_width, _ = im_resized.shape
if len(all_boxes) == 0:
return None, None
all_boxes = np.concatenate(all_boxes, axis=0)
bw = all_boxes[:, 2] - all_boxes[:, 0] + 1
bh = all_boxes[:, 3] - all_boxes[:, 1] + 1
align_topx = all_boxes[:, 0] + all_boxes[:, 4] * bw
align_topy = all_boxes[:, 1] + all_boxes[:, 5] * bh
align_bottomx = all_boxes[:, 2] + all_boxes[:, 6] * bw
align_bottomy = all_boxes[:, 3] + all_boxes[:, 7] * bh
# refine the boxes
boxes_align = np.vstack([
align_topx, align_topy, align_bottomx, align_bottomy, all_boxes[:, 8]
])
boxes_align = boxes_align.T
keep = nms(boxes_align, 0.5, 'Union')
return boxes_align[keep]
def train_pnet(annotation_file,
model_store_path,
end_epoch=30,
batch_size=512,
frequent=100,
base_lr=0.001,
use_cuda=True):
imagedb = ImageDB(annotation_file)
gt_imdb = imagedb.load_imdb() # imdb is a list of dict
gt_imdb = imagedb.append_flipped_images(gt_imdb)
if not os.path.exists(model_store_path):
os.makedirs(model_store_path)
net = PNet()
net.train()
if use_cuda:
net.cuda()
optimizer = torch.optim.Adam(net.parameters(), lr=base_lr)
train_data = TrainImageReader(gt_imdb, 12, batch_size, shuffle=True)
lossfn = LossFn()
for cur_epoch in range(1, end_epoch + 1):
train_data.reset()
face_accuracy_list = []
mask_accuracy_list = []
cls_loss_list = []
bbox_loss_list = []
for batch_idx, (image, (gt_label, gt_bbox,
gt_landmark)) in enumerate(train_data):
im_tensor = [
image_tools.convert_image_to_tensor(image[i, ...])
for i in range(image.shape[0])
]
im_tensor = torch.stack(im_tensor)
im_tensor = Variable(im_tensor.float())
gt_label = Variable(torch.from_numpy(gt_label).float())
gt_bbox = Variable(torch.from_numpy(gt_bbox).float())
if use_cuda:
im_tensor = im_tensor.cuda()
gt_label = gt_label.cuda()
gt_bbox = gt_bbox.cuda()
conf_logits, box_offset_pred = net(im_tensor)
cls_loss = lossfn.cls_loss(gt_label, conf_logits)
box_offset_loss = lossfn.box_loss(gt_label, gt_bbox,
box_offset_pred)
all_loss = cls_loss * 1.0 + box_offset_loss * 0.5
if batch_idx % frequent == 0:
tn, tp, num_neg, num_pos = metric_hit(
torch.sigmoid(conf_logits), gt_label)
c_loss = cls_loss.data.cpu().numpy()
b_loss = box_offset_loss.data.cpu().numpy()
a_loss = all_loss.data.cpu().numpy()
# print("Epoch: %d, Step: %d, face_hit: %.4f, mask_hit: %.4f, neg_hit: %.4f, cls loss: %s, bbox loss: %s, all_loss: %s, lr:%s " \
# %(cur_epoch,batch_idx, tp[0], tp[1], tn, c_loss, b_loss, a_loss, base_lr))
print("Epoch: %d, Step: %d, pos_hit: %.4f, neg_hit: %.4f, cls loss: %s, bbox loss: %s, all_loss: %s, lr:%s " \
%(cur_epoch,batch_idx, tp, tn, c_loss, b_loss, a_loss, base_lr))
# face_accuracy_list.append(tp[0])
# mask_accuracy_list.append(tp[1])
cls_loss_list.append(c_loss)
bbox_loss_list.append(b_loss)
optimizer.zero_grad()
all_loss.backward()
optimizer.step()
# face_avg = np.mean(face_accuracy_list)
# mask_avg = np.mean(mask_accuracy_list)
cls_loss_avg = np.mean(cls_loss_list)
bbox_loss_avg = np.mean(bbox_loss_list)
print("Epoch: %d, cls loss: %s, bbox loss: %s" %
(cur_epoch, cls_loss_avg, bbox_loss_avg))
torch.save(
net.state_dict(),
os.path.join(model_store_path, "pnet_epoch_%d.pth" % cur_epoch))
def detect_onet(self, im, dets):
"""Get face candidates using onet
Parameters:
----------
im: numpy array
input image array
dets: numpy array
detection results of rnet
Returns:
-------
boxes_align: numpy array
boxes after calibration
landmarks_align: numpy array
landmarks after calibration
"""
h, w, c = im.shape
if dets is None:
return None, None
dets = self.square_bbox(dets)
dets[:, 0:4] = np.round(dets[:, 0:4])
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h)
num_boxes = dets.shape[0]
# cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32)
cropped_ims_tensors = []
for i in range(num_boxes):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
# crop input image
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
crop_im = cv2.resize(tmp, (48, 48))
crop_im_tensor = image_tools.convert_image_to_tensor(crop_im)
# cropped_ims_tensors[i, :, :, :] = crop_im_tensor
cropped_ims_tensors.append(crop_im_tensor)
feed_imgs = Variable(torch.stack(cropped_ims_tensors))
if self.rnet_detector.use_cuda:
feed_imgs = feed_imgs.cuda()
cls_map, reg, landmark = self.onet_detector(feed_imgs)
cls_map = cls_map.cpu().data.numpy()
reg = reg.cpu().data.numpy()
landmark = landmark.cpu().data.numpy()
keep_inds = np.where(cls_map > self.thresh[2])[0]
if len(keep_inds) > 0:
boxes = dets[keep_inds]
cls = cls_map[keep_inds]
reg = reg[keep_inds]
landmark = landmark[keep_inds]
else:
return None, None
keep = core_utils.nms(boxes, 0.7, mode="Minimum")
if len(keep) == 0:
return None, None
keep_cls = cls[keep]
keep_boxes = boxes[keep]
keep_reg = reg[keep]
keep_landmark = landmark[keep]
bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1
bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1
align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw
align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh
align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw
align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh
align_landmark_topx = keep_boxes[:, 0]
align_landmark_topy = keep_boxes[:, 1]
boxes_align = np.vstack([
align_topx,
align_topy,
align_bottomx,
align_bottomy,
keep_cls[:, 0],
# align_topx + keep_landmark[:, 0] * bw,
# align_topy + keep_landmark[:, 1] * bh,
# align_topx + keep_landmark[:, 2] * bw,
# align_topy + keep_landmark[:, 3] * bh,
# align_topx + keep_landmark[:, 4] * bw,
# align_topy + keep_landmark[:, 5] * bh,
# align_topx + keep_landmark[:, 6] * bw,
# align_topy + keep_landmark[:, 7] * bh,
# align_topx + keep_landmark[:, 8] * bw,
# align_topy + keep_landmark[:, 9] * bh,
])
boxes_align = boxes_align.T
landmark = np.vstack([
align_landmark_topx + keep_landmark[:, 0] * bw,
align_landmark_topy + keep_landmark[:, 1] * bh,
align_landmark_topx + keep_landmark[:, 2] * bw,
align_landmark_topy + keep_landmark[:, 3] * bh,
align_landmark_topx + keep_landmark[:, 4] * bw,
align_landmark_topy + keep_landmark[:, 5] * bh,
align_landmark_topx + keep_landmark[:, 6] * bw,
align_landmark_topy + keep_landmark[:, 7] * bh,
align_landmark_topx + keep_landmark[:, 8] * bw,
align_landmark_topy + keep_landmark[:, 9] * bh,
])
landmark_align = landmark.T
return boxes_align, landmark_align
def detect_rnet(self, im, dets):
"""Get face candidates using rnet
Parameters:
----------
im: numpy array
input image array
dets: numpy array
detection results of pnet
Returns:
-------
boxes: numpy array
detected boxes before calibration
boxes_align: numpy array
boxes after calibration
"""
# im: an input image
h, w, c = im.shape
if dets is None:
return None, None
# (705, 5) = [x1, y1, x2, y2, score, reg]
# print("pnet detection {0}".format(dets.shape))
# time.sleep(5)
# return square boxes
dets = self.square_bbox(dets)
# rounds
dets[:, 0:4] = np.round(dets[:, 0:4])
[dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h)
num_boxes = dets.shape[0]
'''
# helper for setting RNet batch size
batch_size = self.rnet_detector.batch_size
ratio = float(num_boxes) / batch_size
if ratio > 3 or ratio < 0.3:
print "You may need to reset RNet batch size if this info appears frequently, \
face candidates:%d, current batch_size:%d"%(num_boxes, batch_size)
'''
# cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32)
cropped_ims_tensors = []
for i in range(num_boxes):
tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8)
tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1,
x[i]:ex[i] + 1, :]
crop_im = cv2.resize(tmp, (24, 24))
crop_im_tensor = image_tools.convert_image_to_tensor(crop_im)
# cropped_ims_tensors[i, :, :, :] = crop_im_tensor
cropped_ims_tensors.append(crop_im_tensor)
feed_imgs = Variable(torch.stack(cropped_ims_tensors))
if self.rnet_detector.use_cuda:
feed_imgs = feed_imgs.cuda()
cls_map, reg = self.rnet_detector(feed_imgs)
cls_map = cls_map.cpu().data.numpy()
reg = reg.cpu().data.numpy()
# landmark = landmark.cpu().data.numpy()
keep_inds = np.where(cls_map > self.thresh[1])[0]
if len(keep_inds) > 0:
boxes = dets[keep_inds]
cls = cls_map[keep_inds]
reg = reg[keep_inds]
# landmark = landmark[keep_inds]
else:
return None, None
keep = core_utils.nms(boxes, 0.7)
if len(keep) == 0:
return None, None
keep_cls = cls[keep]
keep_boxes = boxes[keep]
keep_reg = reg[keep]
# keep_landmark = landmark[keep]
bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1
bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1
boxes = np.vstack([
keep_boxes[:, 0],
keep_boxes[:, 1],
keep_boxes[:, 2],
keep_boxes[:, 3],
keep_cls[:, 0],
# keep_boxes[:,0] + keep_landmark[:, 0] * bw,
# keep_boxes[:,1] + keep_landmark[:, 1] * bh,
# keep_boxes[:,0] + keep_landmark[:, 2] * bw,
# keep_boxes[:,1] + keep_landmark[:, 3] * bh,
# keep_boxes[:,0] + keep_landmark[:, 4] * bw,
# keep_boxes[:,1] + keep_landmark[:, 5] * bh,
# keep_boxes[:,0] + keep_landmark[:, 6] * bw,
# keep_boxes[:,1] + keep_landmark[:, 7] * bh,
# keep_boxes[:,0] + keep_landmark[:, 8] * bw,
# keep_boxes[:,1] + keep_landmark[:, 9] * bh,
])
align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw
align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh
align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw
align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh
boxes_align = np.vstack([
align_topx,
align_topy,
align_bottomx,
align_bottomy,
keep_cls[:, 0],
# align_topx + keep_landmark[:, 0] * bw,
# align_topy + keep_landmark[:, 1] * bh,
# align_topx + keep_landmark[:, 2] * bw,
# align_topy + keep_landmark[:, 3] * bh,
# align_topx + keep_landmark[:, 4] * bw,
# align_topy + keep_landmark[:, 5] * bh,
# align_topx + keep_landmark[:, 6] * bw,
# align_topy + keep_landmark[:, 7] * bh,
# align_topx + keep_landmark[:, 8] * bw,
# align_topy + keep_landmark[:, 9] * bh,
])
boxes = boxes.T
boxes_align = boxes_align.T
return boxes, boxes_align
def detect_pnet(self, im):
"""Get face candidates through pnet
Parameters:
----------
im: numpy array
input image array
one batch
Returns:
-------
boxes: numpy array
detected boxes before calibration
boxes_align: numpy array
boxes after calibration
"""
# im = self.unique_image_format(im)
# original wider face data
h, w, c = im.shape
net_size = 12
current_scale = float(
net_size) / self.min_face_size # find initial scale
# print('imgshape:{0}, current_scale:{1}'.format(im.shape, current_scale))
im_resized = self.resize_image(im, current_scale) # scale = 1.0
current_height, current_width, _ = im_resized.shape
# fcn
all_boxes = list()
i = 0
while min(current_height, current_width) > net_size:
# print(i)
feed_imgs = []
image_tensor = image_tools.convert_image_to_tensor(im_resized)
feed_imgs.append(image_tensor)
feed_imgs = torch.stack(feed_imgs)
feed_imgs = Variable(feed_imgs)
if self.pnet_detector.use_cuda:
feed_imgs = feed_imgs.cuda()
# self.pnet_detector is a trained pnet torch model
# receptive field is 12×12
# 12×12 --> score
# 12×12 --> bounding box
cls_map, reg = self.pnet_detector(feed_imgs)
cls_map_np = image_tools.convert_chwTensor_to_hwcNumpy(
cls_map.cpu())
reg_np = image_tools.convert_chwTensor_to_hwcNumpy(reg.cpu())
# print(cls_map_np.shape, reg_np.shape) # cls_map_np = (1, n, m, 1) reg_np.shape = (1, n, m 4)
# time.sleep(5)
# landmark_np = image_tools.convert_chwTensor_to_hwcNumpy(landmark.cpu())
# self.threshold[0] = 0.6
# print(cls_map_np[0,:,:].shape)
# time.sleep(4)
# boxes = [x1, y1, x2, y2, score, reg]
boxes = self.generate_bounding_box(cls_map_np[0, :, :], reg_np,
current_scale, self.thresh[0])
# generate pyramid images
current_scale *= self.scale_factor # self.scale_factor = 0.709
im_resized = self.resize_image(im, current_scale)
current_height, current_width, _ = im_resized.shape
if boxes.size == 0:
continue
# non-maximum suppresion
keep = core_utils.nms(boxes[:, :5], 0.5, 'Union')
boxes = boxes[keep]
# print(boxes.shape)
all_boxes.append(boxes)
# i+=1
if len(all_boxes) == 0:
return None, None
all_boxes = np.vstack(all_boxes)
# print("shape of all boxes {0}".format(all_boxes.shape))
# time.sleep(5)
# merge the detection from first stage
keep = core_utils.nms(all_boxes[:, 0:5], 0.7, 'Union')
all_boxes = all_boxes[keep]
# boxes = all_boxes[:, :5]
# x2 - x1
# y2 - y1
bw = all_boxes[:, 2] - all_boxes[:, 0] + 1
bh = all_boxes[:, 3] - all_boxes[:, 1] + 1
# landmark_keep = all_boxes[:, 9:].reshape((5,2))
boxes = np.vstack([
all_boxes[:, 0],
all_boxes[:, 1],
all_boxes[:, 2],
all_boxes[:, 3],
all_boxes[:, 4],
# all_boxes[:, 0] + all_boxes[:, 9] * bw,
# all_boxes[:, 1] + all_boxes[:,10] * bh,
# all_boxes[:, 0] + all_boxes[:, 11] * bw,
# all_boxes[:, 1] + all_boxes[:, 12] * bh,
# all_boxes[:, 0] + all_boxes[:, 13] * bw,
# all_boxes[:, 1] + all_boxes[:, 14] * bh,
# all_boxes[:, 0] + all_boxes[:, 15] * bw,
# all_boxes[:, 1] + all_boxes[:, 16] * bh,
# all_boxes[:, 0] + all_boxes[:, 17] * bw,
# all_boxes[:, 1] + all_boxes[:, 18] * bh
])
boxes = boxes.T
# boxes = boxes = [x1, y1, x2, y2, score, reg] reg= [px1, py1, px2, py2] (in prediction)
align_topx = all_boxes[:, 0] + all_boxes[:, 5] * bw
align_topy = all_boxes[:, 1] + all_boxes[:, 6] * bh
align_bottomx = all_boxes[:, 2] + all_boxes[:, 7] * bw
align_bottomy = all_boxes[:, 3] + all_boxes[:, 8] * bh
# refine the boxes
boxes_align = np.vstack([
align_topx,
align_topy,
align_bottomx,
align_bottomy,
all_boxes[:, 4],
# align_topx + all_boxes[:,9] * bw,
# align_topy + all_boxes[:,10] * bh,
# align_topx + all_boxes[:,11] * bw,
# align_topy + all_boxes[:,12] * bh,
# align_topx + all_boxes[:,13] * bw,
# align_topy + all_boxes[:,14] * bh,
# align_topx + all_boxes[:,15] * bw,
# align_topy + all_boxes[:,16] * bh,
# align_topx + all_boxes[:,17] * bw,
# align_topy + all_boxes[:,18] * bh,
])
boxes_align = boxes_align.T
return boxes, boxes_align
def detect_pnet(self, im):
"""Get face candidates through pnet
Parameters:
----------
im: numpy array
input image array
Returns:
-------
boxes: numpy array
detected boxes before calibration
boxes_align: numpy array
boxes after calibration
"""
# im = self.unique_image_format(im)
h, w, c = im.shape
net_size = 12
current_scale = float(
net_size) / self.min_face_size # find initial scale
im_resized = self.resize_image(im, current_scale)
current_height, current_width, _ = im_resized.shape
# fcn
all_boxes = list()
while min(current_height, current_width) > net_size:
feed_imgs = []
image_tensor = image_tools.convert_image_to_tensor(im_resized)
feed_imgs.append(image_tensor)
feed_imgs = torch.stack(feed_imgs)
feed_imgs = Variable(feed_imgs)
if self.pnet_detector.use_cuda:
feed_imgs = feed_imgs.cuda()
cls_map, reg = self.pnet_detector(feed_imgs)
cls_map_np = image_tools.convert_chwTensor_to_hwcNumpy(
cls_map.cpu())
reg_np = image_tools.convert_chwTensor_to_hwcNumpy(reg.cpu())
# landmark_np = image_tools.convert_chwTensor_to_hwcNumpy(landmark.cpu())
boxes = self.generate_bounding_box(cls_map_np[0, :, :], reg_np,
current_scale, self.thresh[0])
current_scale *= self.scale_factor
im_resized = self.resize_image(im, current_scale)
current_height, current_width, _ = im_resized.shape
if boxes.size == 0:
continue
keep = utils.nms(boxes[:, :5], 0.5, 'Union')
boxes = boxes[keep]
all_boxes.append(boxes)
if len(all_boxes) == 0:
return None, None
all_boxes = np.vstack(all_boxes)
# merge the detection from first stage
keep = utils.nms(all_boxes[:, 0:5], 0.7, 'Union')
all_boxes = all_boxes[keep]
# boxes = all_boxes[:, :5]
bw = all_boxes[:, 2] - all_boxes[:, 0] + 1
bh = all_boxes[:, 3] - all_boxes[:, 1] + 1
# landmark_keep = all_boxes[:, 9:].reshape((5,2))
boxes = np.vstack([
all_boxes[:, 0],
all_boxes[:, 1],
all_boxes[:, 2],
all_boxes[:, 3],
all_boxes[:, 4],
# all_boxes[:, 0] + all_boxes[:, 9] * bw,
# all_boxes[:, 1] + all_boxes[:,10] * bh,
# all_boxes[:, 0] + all_boxes[:, 11] * bw,
# all_boxes[:, 1] + all_boxes[:, 12] * bh,
# all_boxes[:, 0] + all_boxes[:, 13] * bw,
# all_boxes[:, 1] + all_boxes[:, 14] * bh,
# all_boxes[:, 0] + all_boxes[:, 15] * bw,
# all_boxes[:, 1] + all_boxes[:, 16] * bh,
# all_boxes[:, 0] + all_boxes[:, 17] * bw,
# all_boxes[:, 1] + all_boxes[:, 18] * bh
])
boxes = boxes.T
align_topx = all_boxes[:, 0] + all_boxes[:, 5] * bw
align_topy = all_boxes[:, 1] + all_boxes[:, 6] * bh
align_bottomx = all_boxes[:, 2] + all_boxes[:, 7] * bw
align_bottomy = all_boxes[:, 3] + all_boxes[:, 8] * bh
# refine the boxes
boxes_align = np.vstack([
align_topx,
align_topy,
align_bottomx,
align_bottomy,
all_boxes[:, 4],
# align_topx + all_boxes[:,9] * bw,
# align_topy + all_boxes[:,10] * bh,
# align_topx + all_boxes[:,11] * bw,
# align_topy + all_boxes[:,12] * bh,
# align_topx + all_boxes[:,13] * bw,
# align_topy + all_boxes[:,14] * bh,
# align_topx + all_boxes[:,15] * bw,
# align_topy + all_boxes[:,16] * bh,
# align_topx + all_boxes[:,17] * bw,
# align_topy + all_boxes[:,18] * bh,
])
boxes_align = boxes_align.T
return boxes, boxes_align
def train_pnet(model_store_path,
end_epoch,
imdb,
batch_size,
frequent=10,
base_lr=0.01,
use_cuda=True):
if not os.path.exists(model_store_path):
os.makedirs(model_store_path)
lossfn = LossFn()
net = PNet(is_train=True, use_cuda=use_cuda)
net.train()
if use_cuda:
net.cuda()
optimizer = torch.optim.Adam(net.parameters(), lr=base_lr)
train_data = TrainImageReader(imdb, 12, batch_size, shuffle=True)
frequent = 10
for cur_epoch in range(1, end_epoch + 1):
train_data.reset() # shuffle
for batch_idx, (image, (gt_label, gt_bbox,
gt_landmark)) in enumerate(train_data):
im_tensor = [
image_tools.convert_image_to_tensor(image[i, :, :, :])
for i in range(image.shape[0])
]
im_tensor = torch.stack(im_tensor)
im_tensor = Variable(im_tensor)
gt_label = Variable(torch.from_numpy(gt_label).float())
gt_bbox = Variable(torch.from_numpy(gt_bbox).float())
# gt_landmark = Variable(torch.from_numpy(gt_landmark).float())
if use_cuda:
im_tensor = im_tensor.cuda()
gt_label = gt_label.cuda()
gt_bbox = gt_bbox.cuda()
# gt_landmark = gt_landmark.cuda()
cls_pred, box_offset_pred = net(im_tensor)
# all_loss, cls_loss, offset_loss = lossfn.loss(gt_label=label_y,gt_offset=bbox_y, pred_label=cls_pred, pred_offset=box_offset_pred)
cls_loss = lossfn.cls_loss(gt_label, cls_pred)
box_offset_loss = lossfn.box_loss(gt_label, gt_bbox,
box_offset_pred)
# landmark_loss = lossfn.landmark_loss(gt_label,gt_landmark,landmark_offset_pred)
all_loss = cls_loss * 1.0 + box_offset_loss * 0.5
if batch_idx % frequent == 0:
accuracy = compute_accuracy(cls_pred, gt_label)
show1 = accuracy.data.cpu().numpy()
show2 = cls_loss.data.cpu().numpy()
show3 = box_offset_loss.data.cpu().numpy()
# show4 = landmark_loss.data.cpu().numpy()
show5 = all_loss.data.cpu().numpy()
print(
"%s : Epoch: %d, Step: %d, accuracy: %s, det loss: %s, bbox loss: %s, all_loss: %s, lr:%s "
% (datetime.datetime.now(), cur_epoch, batch_idx, show1,
show2, show3, show5, base_lr))
optimizer.zero_grad()
all_loss.backward()
optimizer.step()
torch.save(
net.state_dict(),
os.path.join(model_store_path, "pnet_epoch_%d.pt" % cur_epoch))
torch.save(
net,
os.path.join(model_store_path,
"pnet_epoch_model_%d.pkl" % cur_epoch))
