diff --git a/pytorch/box_utils.py b/pytorch/box_utils.py
new file mode 100644
index 0000000..67a21e1
--- /dev/null
+++ b/pytorch/box_utils.py
@@ -0,0 +1,328 @@
+import torch
+import numpy as np
+
+
+def point_form(boxes):
+    """ Convert prior_boxes to (xmin, ymin, xmax, ymax)
+    representation for comparison to point form ground truth data.
+    Args:
+        boxes: (tensor) center-size default boxes from priorbox layers.
+    Return:
+        boxes: (tensor) Converted xmin, ymin, xmax, ymax form of boxes.
+    """
+    return torch.cat((boxes[:, :2] - boxes[:, 2:]/2,     # xmin, ymin
+                     boxes[:, :2] + boxes[:, 2:]/2), 1)  # xmax, ymax
+
+
+def center_size(boxes):
+    """ Convert prior_boxes to (cx, cy, w, h)
+    representation for comparison to center-size form ground truth data.
+    Args:
+        boxes: (tensor) point_form boxes
+    Return:
+        boxes: (tensor) Converted xmin, ymin, xmax, ymax form of boxes.
+    """
+    return torch.cat((boxes[:, 2:] + boxes[:, :2])/2,  # cx, cy
+                     boxes[:, 2:] - boxes[:, :2], 1)  # w, h
+
+
+def intersect(box_a, box_b):
+    """ We resize both tensors to [A,B,2] without new malloc:
+    [A,2] -> [A,1,2] -> [A,B,2]
+    [B,2] -> [1,B,2] -> [A,B,2]
+    Then we compute the area of intersect between box_a and box_b.
+    Args:
+      box_a: (tensor) bounding boxes, Shape: [A,4].
+      box_b: (tensor) bounding boxes, Shape: [B,4].
+    Return:
+      (tensor) intersection area, Shape: [A,B].
+    """
+    A = box_a.size(0)
+    B = box_b.size(0)
+    max_xy = torch.min(box_a[:, 2:].unsqueeze(1).expand(A, B, 2),
+                       box_b[:, 2:].unsqueeze(0).expand(A, B, 2))
+    min_xy = torch.max(box_a[:, :2].unsqueeze(1).expand(A, B, 2),
+                       box_b[:, :2].unsqueeze(0).expand(A, B, 2))
+    inter = torch.clamp((max_xy - min_xy), min=0)
+    return inter[:, :, 0] * inter[:, :, 1]
+
+
+def jaccard(box_a, box_b):
+    """Compute the jaccard overlap of two sets of boxes.  The jaccard overlap
+    is simply the intersection over union of two boxes.  Here we operate on
+    ground truth boxes and default boxes.
+    E.g.:
+        A ∩ B / A ∪ B = A ∩ B / (area(A) + area(B) - A ∩ B)
+    Args:
+        box_a: (tensor) Ground truth bounding boxes, Shape: [num_objects,4]
+        box_b: (tensor) Prior boxes from priorbox layers, Shape: [num_priors,4]
+    Return:
+        jaccard overlap: (tensor) Shape: [box_a.size(0), box_b.size(0)]
+    """
+    inter = intersect(box_a, box_b)
+    area_a = ((box_a[:, 2]-box_a[:, 0]) *
+              (box_a[:, 3]-box_a[:, 1])).unsqueeze(1).expand_as(inter)  # [A,B]
+    area_b = ((box_b[:, 2]-box_b[:, 0]) *
+              (box_b[:, 3]-box_b[:, 1])).unsqueeze(0).expand_as(inter)  # [A,B]
+    union = area_a + area_b - inter
+    return inter / union  # [A,B]
+
+
+def matrix_iou(a, b):
+    """
+    return iou of a and b, numpy version for data augenmentation
+    """
+    lt = np.maximum(a[:, np.newaxis, :2], b[:, :2])
+    rb = np.minimum(a[:, np.newaxis, 2:], b[:, 2:])
+
+    area_i = np.prod(rb - lt, axis=2) * (lt < rb).all(axis=2)
+    area_a = np.prod(a[:, 2:] - a[:, :2], axis=1)
+    area_b = np.prod(b[:, 2:] - b[:, :2], axis=1)
+    return area_i / (area_a[:, np.newaxis] + area_b - area_i)
+
+
+def matrix_iof(a, b):
+    """
+    return iof of a and b, numpy version for data augenmentation
+    """
+    lt = np.maximum(a[:, np.newaxis, :2], b[:, :2])
+    rb = np.minimum(a[:, np.newaxis, 2:], b[:, 2:])
+
+    area_i = np.prod(rb - lt, axis=2) * (lt < rb).all(axis=2)
+    area_a = np.prod(a[:, 2:] - a[:, :2], axis=1)
+    return area_i / np.maximum(area_a[:, np.newaxis], 1)
+
+
+def match(threshold, truths, priors, variances, labels, landms, loc_t, conf_t, landm_t, idx):
+    """Match each prior box with the ground truth box of the highest jaccard
+    overlap, encode the bounding boxes, then return the matched indices
+    corresponding to both confidence and location preds.
+    Args:
+        threshold: (float) The overlap threshold used when mathing boxes.
+        truths: (tensor) Ground truth boxes, Shape: [num_obj, 4].
+        priors: (tensor) Prior boxes from priorbox layers, Shape: [n_priors,4].
+        variances: (tensor) Variances corresponding to each prior coord,
+            Shape: [num_priors, 4].
+        labels: (tensor) All the class labels for the image, Shape: [num_obj].
+        landms: (tensor) Ground truth landms, Shape [num_obj, 10].
+        loc_t: (tensor) Tensor to be filled w/ endcoded location targets.
+        conf_t: (tensor) Tensor to be filled w/ matched indices for conf preds.
+        landm_t: (tensor) Tensor to be filled w/ endcoded landm targets.
+        idx: (int) current batch index
+    Return:
+        The matched indices corresponding to 1)location 2)confidence 3)landm preds.
+    """
+    # jaccard index
+    overlaps = jaccard(
+        truths,
+        point_form(priors)
+    )
+    # (Bipartite Matching)
+    # [1,num_objects] best prior for each ground truth
+    best_prior_overlap, best_prior_idx = overlaps.max(1, keepdim=True)
+
+    # ignore hard gt
+    valid_gt_idx = best_prior_overlap[:, 0] >= 0.2
+    best_prior_idx_filter = best_prior_idx[valid_gt_idx, :]
+    if best_prior_idx_filter.shape[0] <= 0:
+        loc_t[idx] = 0
+        conf_t[idx] = 0
+        return
+
+    # [1,num_priors] best ground truth for each prior
+    best_truth_overlap, best_truth_idx = overlaps.max(0, keepdim=True)
+    best_truth_idx.squeeze_(0)
+    best_truth_overlap.squeeze_(0)
+    best_prior_idx.squeeze_(1)
+    best_prior_idx_filter.squeeze_(1)
+    best_prior_overlap.squeeze_(1)
+    best_truth_overlap.index_fill_(0, best_prior_idx_filter, 2)  # ensure best prior
+    # TODO refactor: index  best_prior_idx with long tensor
+    # ensure every gt matches with its prior of max overlap
+    for j in range(best_prior_idx.size(0)):     # 判别此anchor是预测哪一个boxes
+        best_truth_idx[best_prior_idx[j]] = j
+    matches = truths[best_truth_idx]            # Shape: [num_priors,4] 此处为每一个anchor对应的bbox取出来
+    conf = labels[best_truth_idx]               # Shape: [num_priors]      此处为每一个anchor对应的label取出来
+    conf[best_truth_overlap < threshold] = 0    # label as background   overlap<0.35的全部作为负样本
+    loc = encode(matches, priors, variances)
+
+    matches_landm = landms[best_truth_idx]
+    landm = encode_landm(matches_landm, priors, variances)
+    loc_t[idx] = loc    # [num_priors,4] encoded offsets to learn
+    conf_t[idx] = conf  # [num_priors] top class label for each prior
+    landm_t[idx] = landm
+
+
+def encode(matched, priors, variances):
+    """Encode the variances from the priorbox layers into the ground truth boxes
+    we have matched (based on jaccard overlap) with the prior boxes.
+    Args:
+        matched: (tensor) Coords of ground truth for each prior in point-form
+            Shape: [num_priors, 4].
+        priors: (tensor) Prior boxes in center-offset form
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        encoded boxes (tensor), Shape: [num_priors, 4]
+    """
+
+    # dist b/t match center and prior's center
+    g_cxcy = (matched[:, :2] + matched[:, 2:])/2 - priors[:, :2]
+    # encode variance
+    g_cxcy /= (variances[0] * priors[:, 2:])
+    # match wh / prior wh
+    g_wh = (matched[:, 2:] - matched[:, :2]) / priors[:, 2:]
+    g_wh = torch.log(g_wh) / variances[1]
+    # return target for smooth_l1_loss
+    return torch.cat([g_cxcy, g_wh], 1)  # [num_priors,4]
+
+def encode_landm(matched, priors, variances):
+    """Encode the variances from the priorbox layers into the ground truth boxes
+    we have matched (based on jaccard overlap) with the prior boxes.
+    Args:
+        matched: (tensor) Coords of ground truth for each prior in point-form
+            Shape: [num_priors, 10].
+        priors: (tensor) Prior boxes in center-offset form
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        encoded landm (tensor), Shape: [num_priors, 10]
+    """
+
+    # dist b/t match center and prior's center
+    matched = torch.reshape(matched, (matched.size(0), 5, 2))
+    priors_cx = priors[:, 0].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_cy = priors[:, 1].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_w = priors[:, 2].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_h = priors[:, 3].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors = torch.cat([priors_cx, priors_cy, priors_w, priors_h], dim=2)
+    g_cxcy = matched[:, :, :2] - priors[:, :, :2]
+    # encode variance
+    g_cxcy /= (variances[0] * priors[:, :, 2:])
+    # g_cxcy /= priors[:, :, 2:]
+    g_cxcy = g_cxcy.reshape(g_cxcy.size(0), -1)
+    # return target for smooth_l1_loss
+    return g_cxcy
+
+
+# Adapted from https://github.com/Hakuyume/chainer-ssd
+def decode(loc, priors, variances):
+    """Decode locations from predictions using priors to undo
+    the encoding we did for offset regression at train time.
+    Args:
+        loc (tensor): location predictions for loc layers,
+            Shape: [num_priors,4]
+        priors (tensor): Prior boxes in center-offset form.
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        decoded bounding box predictions
+    """
+
+    boxes = torch.cat((
+        priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:],
+        priors[:, 2:] * torch.exp(loc[:, 2:] * variances[1])), 1)
+    boxes[:, :2] -= boxes[:, 2:] / 2
+    boxes[:, 2:] += boxes[:, :2]
+    return boxes
+
+def decode_landm(pre, priors, variances):
+    """Decode landm from predictions using priors to undo
+    the encoding we did for offset regression at train time.
+    Args:
+        pre (tensor): landm predictions for loc layers,
+            Shape: [num_priors,10]
+        priors (tensor): Prior boxes in center-offset form.
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        decoded landm predictions
+    """
+    landms = torch.cat((priors[:, :2] + pre[:, :2] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 2:4] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 4:6] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 6:8] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 8:10] * variances[0] * priors[:, 2:],
+                        ), dim=1)
+    return landms
+
+
+def log_sum_exp(x):
+    """Utility function for computing log_sum_exp while determining
+    This will be used to determine unaveraged confidence loss across
+    all examples in a batch.
+    Args:
+        x (Variable(tensor)): conf_preds from conf layers
+    """
+    x_max = x.data.max()
+    return torch.log(torch.sum(torch.exp(x-x_max), 1, keepdim=True)) + x_max
+
+
+# Original author: Francisco Massa:
+# https://github.com/fmassa/object-detection.torch
+# Ported to PyTorch by Max deGroot (02/01/2017)
+def nms(boxes, scores, overlap=0.5, top_k=200):
+    """Apply non-maximum suppression at test time to avoid detecting too many
+    overlapping bounding boxes for a given object.
+    Args:
+        boxes: (tensor) The location preds for the img, Shape: [num_priors,4].
+        scores: (tensor) The class predscores for the img, Shape:[num_priors].
+        overlap: (float) The overlap thresh for suppressing unnecessary boxes.
+        top_k: (int) The Maximum number of box preds to consider.
+    Return:
+        The indices of the kept boxes with respect to num_priors.
+    """
+
+    keep = torch.Tensor(scores.size(0)).fill_(0).long()
+    if boxes.numel() == 0:
+        return keep
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    x2 = boxes[:, 2]
+    y2 = boxes[:, 3]
+    area = torch.mul(x2 - x1, y2 - y1)
+    v, idx = scores.sort(0)  # sort in ascending order
+    # I = I[v >= 0.01]
+    idx = idx[-top_k:]  # indices of the top-k largest vals
+    xx1 = boxes.new()
+    yy1 = boxes.new()
+    xx2 = boxes.new()
+    yy2 = boxes.new()
+    w = boxes.new()
+    h = boxes.new()
+
+    # keep = torch.Tensor()
+    count = 0
+    while idx.numel() > 0:
+        i = idx[-1]  # index of current largest val
+        # keep.append(i)
+        keep[count] = i
+        count += 1
+        if idx.size(0) == 1:
+            break
+        idx = idx[:-1]  # remove kept element from view
+        # load bboxes of next highest vals
+        torch.index_select(x1, 0, idx, out=xx1)
+        torch.index_select(y1, 0, idx, out=yy1)
+        torch.index_select(x2, 0, idx, out=xx2)
+        torch.index_select(y2, 0, idx, out=yy2)
+        # store element-wise max with next highest score
+        xx1 = torch.clamp(xx1, min=x1[i])
+        yy1 = torch.clamp(yy1, min=y1[i])
+        xx2 = torch.clamp(xx2, max=x2[i])
+        yy2 = torch.clamp(yy2, max=y2[i])
+        w.resize_as_(xx2)
+        h.resize_as_(yy2)
+        w = xx2 - xx1
+        h = yy2 - yy1
+        # check sizes of xx1 and xx2.. after each iteration
+        w = torch.clamp(w, min=0.0)
+        h = torch.clamp(h, min=0.0)
+        inter = w*h
+        # IoU = i / (area(a) + area(b) - i)
+        rem_areas = torch.index_select(area, 0, idx)  # load remaining areas)
+        union = (rem_areas - inter) + area[i]
+        IoU = inter/union  # store result in iou
+        # keep only elements with an IoU <= overlap
+        idx = idx[IoU.le(overlap)]
+    return keep, count
diff --git a/pytorch/multibox_loss.py b/pytorch/multibox_loss.py
new file mode 100644
index 0000000..c34b1df
--- /dev/null
+++ b/pytorch/multibox_loss.py
@@ -0,0 +1,122 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.autograd import Variable
+from .box_utils import match, log_sum_exp
+
+class MultiBoxLoss(nn.Module):
+    """SSD Weighted Loss Function
+    Compute Targets:
+        1) Produce Confidence Target Indices by matching  ground truth boxes
+           with (default) 'priorboxes' that have jaccard index > threshold parameter
+           (default threshold: 0.5).
+        2) Produce localization target by 'encoding' variance into offsets of ground
+           truth boxes and their matched  'priorboxes'.
+        3) Hard negative mining to filter the excessive number of negative examples
+           that comes with using a large number of default bounding boxes.
+           (default negative:positive ratio 3:1)
+    Objective Loss:
+        L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N
+        Where, Lconf is the CrossEntropy Loss and Lloc is the SmoothL1 Loss
+        weighted by α which is set to 1 by cross val.
+        Args:
+            c: class confidences,
+            l: predicted boxes,
+            g: ground truth boxes
+            N: number of matched default boxes
+        See: https://arxiv.org/pdf/1512.02325.pdf for more details.
+    """
+
+    def __init__(self, num_classes, overlap_thresh, prior_for_matching, bkg_label, neg_mining, neg_pos, neg_overlap, encode_target):
+        super(MultiBoxLoss, self).__init__()
+        self.num_classes = num_classes
+        self.threshold = overlap_thresh
+        self.background_label = bkg_label
+        self.encode_target = encode_target
+        self.use_prior_for_matching = prior_for_matching
+        self.do_neg_mining = neg_mining
+        self.negpos_ratio = neg_pos
+        self.neg_overlap = neg_overlap
+        self.variance = [0.1, 0.2]
+        self.GPU = False
+
+    def forward(self, predictions, priors, targets):
+        """Multibox Loss
+        Args:
+            predictions (tuple): A tuple containing loc preds, conf preds,
+            and prior boxes from SSD net.
+                conf shape: torch.size(batch_size,num_priors,num_classes)
+                loc shape: torch.size(batch_size,num_priors,4)
+                priors shape: torch.size(num_priors,4)
+            ground_truth (tensor): Ground truth boxes and labels for a batch,
+                shape: [batch_size,num_objs,5] (last idx is the label).
+        """
+
+        loc_data, conf_data, landm_data = predictions
+        priors = priors
+        num = loc_data.size(0)
+        num_priors = (priors.size(0))
+
+        # match priors (default boxes) and ground truth boxes
+        loc_t = torch.Tensor(num, num_priors, 4)
+        landm_t = torch.Tensor(num, num_priors, 10)
+        conf_t = torch.LongTensor(num, num_priors)
+        for idx in range(num):
+            truths = targets[idx][:, :4].data
+            labels = targets[idx][:, -1].data
+            landms = targets[idx][:, 4:14].data
+            defaults = priors.data
+            match(self.threshold, truths, defaults, self.variance, labels, landms, loc_t, conf_t, landm_t, idx)
+        if self.GPU:
+            loc_t = loc_t.cuda()
+            conf_t = conf_t.cuda()
+            landm_t = landm_t.cuda()
+
+        zeros = torch.tensor(0).cuda()
+        # landm Loss (Smooth L1)
+        # Shape: [batch,num_priors,10]
+        pos1 = conf_t > zeros
+        num_pos_landm = pos1.long().sum(1, keepdim=True)
+        N1 = max(num_pos_landm.data.sum().float(), 1)
+        pos_idx1 = pos1.unsqueeze(pos1.dim()).expand_as(landm_data)
+        landm_p = landm_data[pos_idx1].view(-1, 10)
+        landm_t = landm_t[pos_idx1].view(-1, 10)
+        loss_landm = F.smooth_l1_loss(landm_p, landm_t, reduction='sum')
+
+
+        pos = conf_t != zeros
+        conf_t[pos] = 1
+
+        # Localization Loss (Smooth L1)
+        # Shape: [batch,num_priors,4]
+        pos_idx = pos.unsqueeze(pos.dim()).expand_as(loc_data)
+        loc_p = loc_data[pos_idx].view(-1, 4)
+        loc_t = loc_t[pos_idx].view(-1, 4)
+        loss_l = F.smooth_l1_loss(loc_p, loc_t, reduction='sum')
+
+        # Compute max conf across batch for hard negative mining
+        batch_conf = conf_data.view(-1, self.num_classes)
+        loss_c = log_sum_exp(batch_conf) - batch_conf.gather(1, conf_t.view(-1, 1))
+
+        # Hard Negative Mining
+        loss_c[pos.view(-1, 1)] = 0 # filter out pos boxes for now
+        loss_c = loss_c.view(num, -1)
+        _, loss_idx = loss_c.sort(1, descending=True)
+        _, idx_rank = loss_idx.sort(1)
+        num_pos = pos.long().sum(1, keepdim=True)
+        num_neg = torch.clamp(self.negpos_ratio*num_pos, max=pos.size(1)-1)
+        neg = idx_rank < num_neg.expand_as(idx_rank)
+
+        # Confidence Loss Including Positive and Negative Examples
+        pos_idx = pos.unsqueeze(2).expand_as(conf_data)
+        neg_idx = neg.unsqueeze(2).expand_as(conf_data)
+        conf_p = conf_data[(pos_idx+neg_idx).gt(0)].view(-1,self.num_classes)
+        targets_weighted = conf_t[(pos+neg).gt(0)]
+        loss_c = F.cross_entropy(conf_p, targets_weighted, reduction='sum')
+
+        # Sum of losses: L(x,c,l,g) = (Lconf(x, c) + αLloc(x,l,g)) / N N = max(num_pos.data.sum().float(), 1)
+        loss_l /= N
+        loss_c /= N
+        loss_landm /= N1
+
+        return loss_l, loss_c, loss_landm
diff --git a/retinaface_training_yaml.yaml b/retinaface_training_yaml.yaml
new file mode 100644
index 0000000..34129b5
--- /dev/null
+++ b/retinaface_training_yaml.yaml
@@ -0,0 +1,25 @@
+device:
+  device_str: null
+  n_gpu: -1
+  sync_bn: true
+metrics:
+  metric: Accuracy
+train:
+  batch_size: 32
+  overwrite_output_dir: true
+  epoch_num: 2
+learning:
+  optimizer:
+    name_: SGD
+    lr: 0.04
+    momentum: 0.001
+  loss:
+    name_: CrossEntropyLoss
+    ignore_index: -1
+logging:
+  print_steps: 2
+#learning:
+#  optimizer:
+#    name_: Adam
+#    lr: 0.02
+#    eps: 0.001
diff --git a/train.py b/train.py
new file mode 100644
index 0000000..23d52ca
--- /dev/null
+++ b/train.py
@@ -0,0 +1,84 @@
+import numpy as np
+from torch.optim import AdamW
+from torchvision import transforms
+from torchvision.transforms import RandomResizedCrop, Lambda
+from towhee.trainer.modelcard import ModelCard
+
+from towhee.trainer.training_config import TrainingConfig
+from towhee.trainer.dataset import get_dataset
+from resnet_image_embedding import ResnetImageEmbedding
+from towhee.types import Image
+from towhee.trainer.training_config import dump_default_yaml
+from PIL import Image as PILImage
+from timm.models.resnet import ResNet
+from torch import nn
+
+if __name__ == '__main__':
+    dump_default_yaml(yaml_path='default_config.yaml')
+    # img = torch.rand([1, 3, 224, 224])
+    img_path = './ILSVRC2012_val_00049771.JPEG'
+    # # logo_path = os.path.join(Path(__file__).parent.parent.parent.parent.resolve(), 'towhee_logo.png')
+    img = PILImage.open(img_path)
+    img_bytes = img.tobytes()
+    img_width = img.width
+    img_height = img.height
+    img_channel = len(img.split())
+    img_mode = img.mode
+    img_array = np.array(img)
+    array_size = np.array(img).shape
+    towhee_img = Image(img_bytes, img_width, img_height, img_channel, img_mode, img_array)
+
+    op = ResnetImageEmbedding('resnet34')
+    # op.model_card = ModelCard(model_details="resnet test modelcard", training_data="use resnet test data")
+    # old_out = op(towhee_img)
+    # print(old_out.feature_vector[0])
+
+    training_config = TrainingConfig()
+    yaml_path = 'resnet_training_yaml.yaml'
+    # dump_default_yaml(yaml_path=yaml_path)
+    training_config.load_from_yaml(yaml_path)
+    #     output_dir='./temp_output',
+    #     overwrite_output_dir=True,
+    #     epoch_num=2,
+    #     per_gpu_train_batch_size=16,
+    #     prediction_loss_only=True,
+    #     metric='Accuracy'
+    #     # device_str='cuda',
+    #     # n_gpu=4
+    # )
+
+    mnist_transform = transforms.Compose([transforms.ToTensor(),
+                                          RandomResizedCrop(224),
+                                          Lambda(lambda x: x.repeat(3, 1, 1)),
+                                          transforms.Normalize(mean=[0.5], std=[0.5])])
+    train_data = get_dataset('mnist', transform=mnist_transform, download=True, root='data', train=True)
+    eval_data = get_dataset('mnist', transform=mnist_transform, download=True, root='data', train=False)
+    # fake_transform = transforms.Compose([transforms.ToTensor(),
+    #                                       RandomResizedCrop(224),])
+    # train_data = get_dataset('fake', size=20, transform=fake_transform)
+
+    op.change_before_train(10)
+    trainer = op.setup_trainer()
+    # my_optimimzer = AdamW(op.get_model().parameters(), lr=0.002, betas=(0.91, 0.98), eps=1e-08, weight_decay=0.01, amsgrad=False)
+    # op.setup_trainer()
+
+    # trainer.add_callback()
+    # trainer.set_optimizer()
+
+    # op.trainer.set_optimizer(my_optimimzer)
+    # trainer.configs.save_to_yaml('changed_optimizer_yaml.yaml')
+
+    # my_loss = nn.BCELoss()
+    # trainer.set_loss(my_loss, 'my_loss111')
+    # trainer.configs.save_to_yaml('chaned_loss_yaml.yaml')
+    # op.trainer._create_optimizer()
+    # op.trainer.set_optimizer()
+    op.train(training_config, train_dataset=train_data, eval_dataset=eval_data)
+    # training_config.num_epoch = 3
+    # op.train(training_config, train_dataset=train_data, resume_checkpoint_path=training_config.output_dir + '/epoch_2')
+
+    # op.save('./test_save')
+    # op.load('./test_save')
+    # new_out = op(towhee_img)
+
+    # assert (new_out[0]!=old_out[0]).all()