Upload 6 files

models/detectron2/diver_detector_setup.py

@@ -0,0 +1,37 @@
+import sys, os, distutils.core
+
+# os.system('python -m pip install pyyaml==5.3.1')
+# dist = distutils.core.run_setup("./detectron2/setup.py")
+# temp = ' '.join([f"'{x}'" for x in dist.install_requires])
+# cmd = "python -m pip install {0}".format(temp)
+# os.system(cmd)
+sys.path.insert(0, os.path.abspath('./detectron2'))
+
+import detectron2
+import cv2
+
+from detectron2.utils.logger import setup_logger
+setup_logger()
+
+# from detectron2.modeling import build_model
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.checkpoint import DetectionCheckpointer
+from detectron2.data.datasets import register_coco_instances
+
+def get_diver_detector():
+    cfg = get_cfg()
+    cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
+    cfg.OUTPUT_DIR = "./output/diver/"
+    cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")  # path to the model we just trained
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set a custom testing threshold
+    cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # The "RoIHead batch size". 128 is faster, and good enough for this toy dataset (default: 512)
+    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1  # only has one class (ballon). (see https://detectron2.readthedocs.io/tutorials/datasets.html#update-the-config-for-new-datasets)
+    diver_detector = DefaultPredictor(cfg)
+    return diver_detector
+
+
+

models/detectron2/platform_detector_setup.py

@@ -0,0 +1,51 @@
+import sys, os, distutils.core
+
+# os.system('python -m pip install pyyaml==5.3.1')
+# dist = distutils.core.run_setup("./detectron2/setup.py")
+# temp = ' '.join([f"'{x}'" for x in dist.install_requires])
+# cmd = "python -m pip install {0}".format(temp)
+# os.system(cmd)
+sys.path.insert(0, os.path.abspath('./detectron2'))
+
+import detectron2
+import cv2
+
+from detectron2.utils.logger import setup_logger
+setup_logger()
+
+# from detectron2.modeling import build_model
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.checkpoint import DetectionCheckpointer
+from detectron2.data.datasets import register_coco_instances
+
+def get_platform_detector():
+    cfg = get_cfg()
+    cfg.OUTPUT_DIR = "./output/platform/"
+    # model = build_model(cfg)  # returns a torch.nn.Module
+    cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
+    cfg.DATASETS.TEST = ()
+    cfg.DATALOADER.NUM_WORKERS = 2
+    cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
+    cfg.SOLVER.IMS_PER_BATCH = 2  # This is the real "batch size" commonly known to deep learning people
+    cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
+    cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough for this toy dataset; you will need to train longer for a practical dataset
+    cfg.SOLVER.STEPS = []        # do not decay learning rate
+    cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # The "RoIHead batch size". 128 is faster, and good enough for this toy dataset (default: 512)
+    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+    cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")  # path to the model we just trained
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set a custom testing threshold
+    predictor = DefaultPredictor(cfg)
+    return predictor
+
+# register_coco_instances("springboard_trains", {}, "./coco_annotations/springboard/train.json", "../data/Boards/spring")
+# register_coco_instances("springboard_vals", {}, "./coco_annotations/springboard/val.json", "../data/Boards/spring")
+
+# from detectron2.utils.visualizer import ColorMode
+# splash_metadata = MetadataCatalog.get('springboard_vals')
+# dataset_dicts = DatasetCatalog.get("springboard_vals")
+
+

models/detectron2/splash_detector_setup.py

@@ -0,0 +1,45 @@
+import sys, os, distutils.core
+
+# os.system('python -m pip install pyyaml==5.3.1')
+# dist = distutils.core.run_setup("./detectron2/setup.py")
+# temp = ' '.join([f"'{x}'" for x in dist.install_requires])
+# cmd = "python -m pip install {0}".format(temp)
+# os.system(cmd)
+sys.path.insert(0, os.path.abspath('./detectron2'))
+
+import detectron2
+import cv2
+
+from detectron2.utils.logger import setup_logger
+setup_logger()
+
+# from detectron2.modeling import build_model
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.utils.visualizer import Visualizer
+from detectron2.checkpoint import DetectionCheckpointer
+from detectron2.data.datasets import register_coco_instances
+
+def get_splash_detector():
+    cfg = get_cfg()
+    cfg.OUTPUT_DIR = "./output/splash/"
+    # model = build_model(cfg)  # returns a torch.nn.Module
+    cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
+    cfg.DATASETS.TRAIN = ("splash_trains",)
+    cfg.DATASETS.TEST = ()
+    cfg.DATALOADER.NUM_WORKERS = 2
+    cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
+    cfg.SOLVER.IMS_PER_BATCH = 2  # This is the real "batch size" commonly known to deep learning people
+    cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
+    cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough for this toy dataset; you will need to train longer for a practical dataset
+    cfg.SOLVER.STEPS = []        # do not decay learning rate
+    cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # The "RoIHead batch size". 128 is faster, and good enough for this toy dataset (default: 512)
+    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 2
+    cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")  # path to the model we just trained
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set a custom testing threshold
+    predictor = DefaultPredictor(cfg)
+    return predictor
+

models/detectron2/springboard_detector_setup.py

@@ -0,0 +1,52 @@
+import sys, os, distutils.core
+
+# os.system('python -m pip install pyyaml==5.3.1')
+# dist = distutils.core.run_setup("./detectron2/setup.py")
+# temp = ' '.join([f"'{x}'" for x in dist.install_requires])
+# cmd = "python -m pip install {0}".format(temp)
+# os.system(cmd)
+sys.path.insert(0, os.path.abspath('./detectron2'))
+
+import detectron2
+import cv2
+
+from detectron2.utils.logger import setup_logger
+setup_logger()
+
+# from detectron2.modeling import build_model
+from detectron2 import model_zoo
+from detectron2.engine import DefaultPredictor
+from detectron2.config import get_cfg
+from detectron2.utils.visualizer import Visualizer
+from detectron2.data import MetadataCatalog, DatasetCatalog
+from detectron2.utils.visualizer import Visualizer
+from detectron2.checkpoint import DetectionCheckpointer
+from detectron2.data.datasets import register_coco_instances
+
+def get_springboard_detector():
+    cfg = get_cfg()
+    cfg.OUTPUT_DIR = "./output/springboard/"
+    # model = build_model(cfg)  # returns a torch.nn.Module
+    cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
+    cfg.DATASETS.TEST = ()
+    cfg.DATALOADER.NUM_WORKERS = 2
+    cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
+    cfg.SOLVER.IMS_PER_BATCH = 2  # This is the real "batch size" commonly known to deep learning people
+    cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
+    cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough for this toy dataset; you will need to train longer for a practical dataset
+    cfg.SOLVER.STEPS = []        # do not decay learning rate
+    cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # The "RoIHead batch size". 128 is faster, and good enough for this toy dataset (default: 512)
+    cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1
+    cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")  # path to the model we just trained
+    cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7   # set a custom testing threshold
+    predictor = DefaultPredictor(cfg)
+    return predictor
+
+# register_coco_instances("springboard_trains", {}, "./coco_annotations/springboard/train.json", "../data/Boards/spring")
+# register_coco_instances("springboard_vals", {}, "./coco_annotations/springboard/val.json", "../data/Boards/spring")
+
+# from detectron2.utils.visualizer import ColorMode
+# splash_metadata = MetadataCatalog.get('springboard_vals')
+# dataset_dicts = DatasetCatalog.get("springboard_vals")
+
+

models/pose_estimator/pose_estimator_model_setup.py

@@ -0,0 +1,198 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import argparse
+import csv
+import os
+import shutil
+import sys
+
+from PIL import Image
+import torch
+import torch.nn.parallel
+import torch.backends.cudnn as cudnn
+import torch.optim
+import torch.utils.data
+import torch.utils.data.distributed
+import torchvision.transforms as transforms
+import torchvision
+import cv2
+import numpy as np
+import time
+sys.path.append('./deep-high-resolution-net.pytorch/lib')
+import models
+from config import cfg
+from config import update_config
+from core.function import get_final_preds
+from utils.transforms import get_affine_transform
+
+import distutils.core
+
+# os.system('python -m pip install pyyaml==5.3.1')
+# dist = distutils.core.run_setup("./detectron2/setup.py")
+# temp = ' '.join([f"'{x}'" for x in dist.install_requires])
+# cmd = "python -m pip install {0}".format(temp)
+# os.system(cmd)
+# sys.path.insert(0, os.path.abspath('./detectron2'))
+
+# import detectron2
+# # from detectron2.modeling import build_model
+# from detectron2 import model_zoo
+# from detectron2.engine import DefaultPredictor
+# from detectron2.config import get_cfg
+# from detectron2.utils.visualizer import Visualizer
+# from detectron2.data import MetadataCatalog, DatasetCatalog
+# from detectron2.utils.visualizer import Visualizer
+# from detectron2.checkpoint import DetectionCheckpointer
+# from detectron2.data.datasets import register_coco_instances
+# from detectron2.utils.visualizer import ColorMode
+from models.detectron2.diver_detector_setup import get_diver_detector
+from models.pose_estimator.pose_hrnet import get_pose_net
+
+
+def box_to_center_scale(box, model_image_width, model_image_height):
+    """convert a box to center,scale information required for pose transformation
+    Parameters
+    ----------
+    box : list of tuple
+        list of length 2 with two tuples of floats representing
+        bottom left and top right corner of a box
+    model_image_width : int
+    model_image_height : int
+
+    Returns
+    -------
+    (numpy array, numpy array)
+        Two numpy arrays, coordinates for the center of the box and the scale of the box
+    """
+    center = np.zeros((2), dtype=np.float32)
+
+    bottom_left_corner = (box[0].data.cpu().item(), box[1].data.cpu().item())
+    top_right_corner = (box[2].data.cpu().item(), box[3].data.cpu().item())
+    box_width = top_right_corner[0]-bottom_left_corner[0]
+    box_height = top_right_corner[1]-bottom_left_corner[1]
+    bottom_left_x = bottom_left_corner[0]
+    bottom_left_y = bottom_left_corner[1]
+    center[0] = bottom_left_x + box_width * 0.5
+    center[1] = bottom_left_y + box_height * 0.5
+
+    aspect_ratio = model_image_width * 1.0 / model_image_height
+    pixel_std = 200
+
+    if box_width > aspect_ratio * box_height:
+        box_height = box_width * 1.0 / aspect_ratio
+    elif box_width < aspect_ratio * box_height:
+        box_width = box_height * aspect_ratio
+    scale = np.array(
+        [box_width * 1.0 / pixel_std, box_height * 1.0 / pixel_std],
+        dtype=np.float32)
+    if center[0] != -1:
+        scale = scale * 1.25
+
+    return center, scale
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='Train keypoints network')
+    # general
+    parser.add_argument('--cfg', type=str, default='./deep-high-resolution-net.pytorch/experiments/mpii/hrnet/w32_256x256_adam_lr1e-3.yaml')
+    parser.add_argument('opts',
+                        help='Modify config options using the command-line',
+                        default=None,
+                        nargs=argparse.REMAINDER)
+
+    args = parser.parse_args()
+
+    # args expected by supporting codebase  
+    args.modelDir = ''
+    args.logDir = ''
+    args.dataDir = ''
+    args.prevModelDir = ''
+    return args
+
+def get_pose_estimation_prediction(pose_model, image, center, scale):
+    rotation = 0
+    trans = get_affine_transform(center, scale, rotation, cfg.MODEL.IMAGE_SIZE)
+    # trans = cv2.getAffineTransform(srcTri, dstTri)
+    transform = transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                             std=[0.229, 0.224, 0.225]),
+    ])
+    model_input = cv2.warpAffine(
+    image,
+    trans,
+    (256, 256),
+    flags=cv2.INTER_LINEAR)
+
+    # pose estimation inference
+    model_input = transform(model_input).unsqueeze(0)
+    # switch to evaluate mode
+    pose_model.eval()
+    with torch.no_grad():
+        # compute output heatmap
+        output = pose_model(model_input)
+        preds, _ = get_final_preds(
+            cfg,
+            output.clone().cpu().numpy(),
+            np.asarray([center]),
+            np.asarray([scale]))
+        return preds
+
+def get_pose_model():
+    CTX = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+    cudnn.benchmark = cfg.CUDNN.BENCHMARK
+    torch.backends.cudnn.deterministic = cfg.CUDNN.DETERMINISTIC
+    torch.backends.cudnn.enabled = cfg.CUDNN.ENABLED
+    args = parse_args()
+    update_config(cfg, args)
+    pose_model = get_pose_net(cfg, is_train=False)
+    if cfg.TEST.MODEL_FILE:
+        print('=> loading model from {}'.format(cfg.TEST.MODEL_FILE))
+        pose_model.load_state_dict(torch.load(cfg.TEST.MODEL_FILE), strict=False)
+    else:
+        print('expected model defined in config at TEST.MODEL_FILE')
+    pose_model = torch.nn.DataParallel(pose_model, device_ids=cfg.GPUS)
+    pose_model.to(CTX)
+    pose_model.eval()
+    return pose_model
+
+
+def get_pose_estimation(filepath, image_bgr=None, diver_detector=None, pose_model=None):
+    if image_bgr is None:
+        image_bgr = cv2.imread(filepath)
+        if image_bgr is None:
+            print("ERROR: image {} does not exist".format(filepath))
+            return None
+    if diver_detector is None:
+        diver_detector = get_diver_detector()
+    
+    if pose_model is None:
+        pose_model = get_pose_model()
+
+    image = image_bgr[:, :, [2, 1, 0]]
+
+    outputs = diver_detector(image_bgr)
+    scores = outputs['instances'].scores
+    pred_boxes = []
+    if len(scores) > 0:
+        pred_boxes = outputs['instances'].pred_boxes           
+    
+    if len(pred_boxes) >= 1:
+        for box in pred_boxes:
+            center, scale = box_to_center_scale(box, cfg.MODEL.IMAGE_SIZE[0], cfg.MODEL.IMAGE_SIZE[1])
+            image_pose = image.copy() if cfg.DATASET.COLOR_RGB else image_bgr.copy()
+            box = box.detach().cpu().numpy()
+            return box, get_pose_estimation_prediction(pose_model, image_pose, center, scale)
+            # print("pose_preds", pose_preds)
+            # draw_bbox(box,image_bgr)
+            # if len(pose_preds)>=1:
+            #     print('drawing preds')
+            #     for kpt in pose_preds:
+            #         draw_pose(kpt,image_bgr) # draw the poses
+            # break # only want to use the box with the highest confidence score
+    return None, None
+
+
+

models/pose_estimator/pose_hrnet.py

@@ -0,0 +1,501 @@
+# ------------------------------------------------------------------------------
+# Copyright (c) Microsoft
+# Licensed under the MIT License.
+# Written by Bin Xiao (Bin.Xiao@microsoft.com)
+# ------------------------------------------------------------------------------
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import os
+import logging
+
+import torch
+import torch.nn as nn
+
+
+BN_MOMENTUM = 0.1
+logger = logging.getLogger(__name__)
+
+
+def conv3x3(in_planes, out_planes, stride=1):
+    """3x3 convolution with padding"""
+    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
+                     padding=1, bias=False)
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None):
+        super(BasicBlock, self).__init__()
+        self.conv1 = conv3x3(inplanes, planes, stride)
+        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = conv3x3(planes, planes)
+        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        residual = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Module):
+    expansion = 4
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None):
+        super(Bottleneck, self).__init__()
+        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
+                               padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes, momentum=BN_MOMENTUM)
+        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1,
+                               bias=False)
+        self.bn3 = nn.BatchNorm2d(planes * self.expansion,
+                                  momentum=BN_MOMENTUM)
+        self.relu = nn.ReLU(inplace=True)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        residual = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        out += residual
+        out = self.relu(out)
+
+        return out
+
+
+class HighResolutionModule(nn.Module):
+    def __init__(self, num_branches, blocks, num_blocks, num_inchannels,
+                 num_channels, fuse_method, multi_scale_output=True):
+        super(HighResolutionModule, self).__init__()
+        self._check_branches(
+            num_branches, blocks, num_blocks, num_inchannels, num_channels)
+
+        self.num_inchannels = num_inchannels
+        self.fuse_method = fuse_method
+        self.num_branches = num_branches
+
+        self.multi_scale_output = multi_scale_output
+
+        self.branches = self._make_branches(
+            num_branches, blocks, num_blocks, num_channels)
+        self.fuse_layers = self._make_fuse_layers()
+        self.relu = nn.ReLU(True)
+
+    def _check_branches(self, num_branches, blocks, num_blocks,
+                        num_inchannels, num_channels):
+        if num_branches != len(num_blocks):
+            error_msg = 'NUM_BRANCHES({}) <> NUM_BLOCKS({})'.format(
+                num_branches, len(num_blocks))
+            logger.error(error_msg)
+            raise ValueError(error_msg)
+
+        if num_branches != len(num_channels):
+            error_msg = 'NUM_BRANCHES({}) <> NUM_CHANNELS({})'.format(
+                num_branches, len(num_channels))
+            logger.error(error_msg)
+            raise ValueError(error_msg)
+
+        if num_branches != len(num_inchannels):
+            error_msg = 'NUM_BRANCHES({}) <> NUM_INCHANNELS({})'.format(
+                num_branches, len(num_inchannels))
+            logger.error(error_msg)
+            raise ValueError(error_msg)
+
+    def _make_one_branch(self, branch_index, block, num_blocks, num_channels,
+                         stride=1):
+        downsample = None
+        if stride != 1 or \
+           self.num_inchannels[branch_index] != num_channels[branch_index] * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2d(
+                    self.num_inchannels[branch_index],
+                    num_channels[branch_index] * block.expansion,
+                    kernel_size=1, stride=stride, bias=False
+                ),
+                nn.BatchNorm2d(
+                    num_channels[branch_index] * block.expansion,
+                    momentum=BN_MOMENTUM
+                ),
+            )
+
+        layers = []
+        layers.append(
+            block(
+                self.num_inchannels[branch_index],
+                num_channels[branch_index],
+                stride,
+                downsample
+            )
+        )
+        self.num_inchannels[branch_index] = \
+            num_channels[branch_index] * block.expansion
+        for i in range(1, num_blocks[branch_index]):
+            layers.append(
+                block(
+                    self.num_inchannels[branch_index],
+                    num_channels[branch_index]
+                )
+            )
+
+        return nn.Sequential(*layers)
+
+    def _make_branches(self, num_branches, block, num_blocks, num_channels):
+        branches = []
+
+        for i in range(num_branches):
+            branches.append(
+                self._make_one_branch(i, block, num_blocks, num_channels)
+            )
+
+        return nn.ModuleList(branches)
+
+    def _make_fuse_layers(self):
+        if self.num_branches == 1:
+            return None
+
+        num_branches = self.num_branches
+        num_inchannels = self.num_inchannels
+        fuse_layers = []
+        for i in range(num_branches if self.multi_scale_output else 1):
+            fuse_layer = []
+            for j in range(num_branches):
+                if j > i:
+                    fuse_layer.append(
+                        nn.Sequential(
+                            nn.Conv2d(
+                                num_inchannels[j],
+                                num_inchannels[i],
+                                1, 1, 0, bias=False
+                            ),
+                            nn.BatchNorm2d(num_inchannels[i]),
+                            nn.Upsample(scale_factor=2**(j-i), mode='nearest')
+                        )
+                    )
+                elif j == i:
+                    fuse_layer.append(None)
+                else:
+                    conv3x3s = []
+                    for k in range(i-j):
+                        if k == i - j - 1:
+                            num_outchannels_conv3x3 = num_inchannels[i]
+                            conv3x3s.append(
+                                nn.Sequential(
+                                    nn.Conv2d(
+                                        num_inchannels[j],
+                                        num_outchannels_conv3x3,
+                                        3, 2, 1, bias=False
+                                    ),
+                                    nn.BatchNorm2d(num_outchannels_conv3x3)
+                                )
+                            )
+                        else:
+                            num_outchannels_conv3x3 = num_inchannels[j]
+                            conv3x3s.append(
+                                nn.Sequential(
+                                    nn.Conv2d(
+                                        num_inchannels[j],
+                                        num_outchannels_conv3x3,
+                                        3, 2, 1, bias=False
+                                    ),
+                                    nn.BatchNorm2d(num_outchannels_conv3x3),
+                                    nn.ReLU(True)
+                                )
+                            )
+                    fuse_layer.append(nn.Sequential(*conv3x3s))
+            fuse_layers.append(nn.ModuleList(fuse_layer))
+
+        return nn.ModuleList(fuse_layers)
+
+    def get_num_inchannels(self):
+        return self.num_inchannels
+
+    def forward(self, x):
+        if self.num_branches == 1:
+            return [self.branches[0](x[0])]
+
+        for i in range(self.num_branches):
+            x[i] = self.branches[i](x[i])
+
+        x_fuse = []
+
+        for i in range(len(self.fuse_layers)):
+            y = x[0] if i == 0 else self.fuse_layers[i][0](x[0])
+            for j in range(1, self.num_branches):
+                if i == j:
+                    y = y + x[j]
+                else:
+                    y = y + self.fuse_layers[i][j](x[j])
+            x_fuse.append(self.relu(y))
+
+        return x_fuse
+
+
+blocks_dict = {
+    'BASIC': BasicBlock,
+    'BOTTLENECK': Bottleneck
+}
+
+
+class PoseHighResolutionNet(nn.Module):
+
+    def __init__(self, cfg, **kwargs):
+        self.inplanes = 64
+        extra = cfg['MODEL']['EXTRA']
+        super(PoseHighResolutionNet, self).__init__()
+
+        # stem net
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1,
+                               bias=False)
+        self.bn1 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
+        self.conv2 = nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1,
+                               bias=False)
+        self.bn2 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
+        self.relu = nn.ReLU(inplace=True)
+        self.layer1 = self._make_layer(Bottleneck, 64, 4)
+
+        self.stage2_cfg = extra['STAGE2']
+        num_channels = self.stage2_cfg['NUM_CHANNELS']
+        block = blocks_dict[self.stage2_cfg['BLOCK']]
+        num_channels = [
+            num_channels[i] * block.expansion for i in range(len(num_channels))
+        ]
+        self.transition1 = self._make_transition_layer([256], num_channels)
+        self.stage2, pre_stage_channels = self._make_stage(
+            self.stage2_cfg, num_channels)
+
+        self.stage3_cfg = extra['STAGE3']
+        num_channels = self.stage3_cfg['NUM_CHANNELS']
+        block = blocks_dict[self.stage3_cfg['BLOCK']]
+        num_channels = [
+            num_channels[i] * block.expansion for i in range(len(num_channels))
+        ]
+        self.transition2 = self._make_transition_layer(
+            pre_stage_channels, num_channels)
+        self.stage3, pre_stage_channels = self._make_stage(
+            self.stage3_cfg, num_channels)
+
+        self.stage4_cfg = extra['STAGE4']
+        num_channels = self.stage4_cfg['NUM_CHANNELS']
+        block = blocks_dict[self.stage4_cfg['BLOCK']]
+        num_channels = [
+            num_channels[i] * block.expansion for i in range(len(num_channels))
+        ]
+        self.transition3 = self._make_transition_layer(
+            pre_stage_channels, num_channels)
+        self.stage4, pre_stage_channels = self._make_stage(
+            self.stage4_cfg, num_channels, multi_scale_output=False)
+
+        self.final_layer = nn.Conv2d(
+            in_channels=pre_stage_channels[0],
+            out_channels=cfg['MODEL']['NUM_JOINTS'],
+            kernel_size=extra['FINAL_CONV_KERNEL'],
+            stride=1,
+            padding=1 if extra['FINAL_CONV_KERNEL'] == 3 else 0
+        )
+
+        self.pretrained_layers = extra['PRETRAINED_LAYERS']
+
+    def _make_transition_layer(
+            self, num_channels_pre_layer, num_channels_cur_layer):
+        num_branches_cur = len(num_channels_cur_layer)
+        num_branches_pre = len(num_channels_pre_layer)
+
+        transition_layers = []
+        for i in range(num_branches_cur):
+            if i < num_branches_pre:
+                if num_channels_cur_layer[i] != num_channels_pre_layer[i]:
+                    transition_layers.append(
+                        nn.Sequential(
+                            nn.Conv2d(
+                                num_channels_pre_layer[i],
+                                num_channels_cur_layer[i],
+                                3, 1, 1, bias=False
+                            ),
+                            nn.BatchNorm2d(num_channels_cur_layer[i]),
+                            nn.ReLU(inplace=True)
+                        )
+                    )
+                else:
+                    transition_layers.append(None)
+            else:
+                conv3x3s = []
+                for j in range(i+1-num_branches_pre):
+                    inchannels = num_channels_pre_layer[-1]
+                    outchannels = num_channels_cur_layer[i] \
+                        if j == i-num_branches_pre else inchannels
+                    conv3x3s.append(
+                        nn.Sequential(
+                            nn.Conv2d(
+                                inchannels, outchannels, 3, 2, 1, bias=False
+                            ),
+                            nn.BatchNorm2d(outchannels),
+                            nn.ReLU(inplace=True)
+                        )
+                    )
+                transition_layers.append(nn.Sequential(*conv3x3s))
+
+        return nn.ModuleList(transition_layers)
+
+    def _make_layer(self, block, planes, blocks, stride=1):
+        downsample = None
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                nn.Conv2d(
+                    self.inplanes, planes * block.expansion,
+                    kernel_size=1, stride=stride, bias=False
+                ),
+                nn.BatchNorm2d(planes * block.expansion, momentum=BN_MOMENTUM),
+            )
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks):
+            layers.append(block(self.inplanes, planes))
+
+        return nn.Sequential(*layers)
+
+    def _make_stage(self, layer_config, num_inchannels,
+                    multi_scale_output=True):
+        num_modules = layer_config['NUM_MODULES']
+        num_branches = layer_config['NUM_BRANCHES']
+        num_blocks = layer_config['NUM_BLOCKS']
+        num_channels = layer_config['NUM_CHANNELS']
+        block = blocks_dict[layer_config['BLOCK']]
+        fuse_method = layer_config['FUSE_METHOD']
+
+        modules = []
+        for i in range(num_modules):
+            # multi_scale_output is only used last module
+            if not multi_scale_output and i == num_modules - 1:
+                reset_multi_scale_output = False
+            else:
+                reset_multi_scale_output = True
+
+            modules.append(
+                HighResolutionModule(
+                    num_branches,
+                    block,
+                    num_blocks,
+                    num_inchannels,
+                    num_channels,
+                    fuse_method,
+                    reset_multi_scale_output
+                )
+            )
+            num_inchannels = modules[-1].get_num_inchannels()
+
+        return nn.Sequential(*modules), num_inchannels
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.bn1(x)
+        x = self.relu(x)
+        x = self.conv2(x)
+        x = self.bn2(x)
+        x = self.relu(x)
+        x = self.layer1(x)
+
+        x_list = []
+        for i in range(self.stage2_cfg['NUM_BRANCHES']):
+            if self.transition1[i] is not None:
+                x_list.append(self.transition1[i](x))
+            else:
+                x_list.append(x)
+        y_list = self.stage2(x_list)
+
+        x_list = []
+        for i in range(self.stage3_cfg['NUM_BRANCHES']):
+            if self.transition2[i] is not None:
+                x_list.append(self.transition2[i](y_list[-1]))
+            else:
+                x_list.append(y_list[i])
+        y_list = self.stage3(x_list)
+
+        x_list = []
+        for i in range(self.stage4_cfg['NUM_BRANCHES']):
+            if self.transition3[i] is not None:
+                x_list.append(self.transition3[i](y_list[-1]))
+            else:
+                x_list.append(y_list[i])
+        y_list = self.stage4(x_list)
+
+        x = self.final_layer(y_list[0])
+
+        return x
+
+    def init_weights(self, pretrained=''):
+        logger.info('=> init weights from normal distribution')
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+                nn.init.normal_(m.weight, std=0.001)
+                for name, _ in m.named_parameters():
+                    if name in ['bias']:
+                        nn.init.constant_(m.bias, 0)
+            elif isinstance(m, nn.BatchNorm2d):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+            elif isinstance(m, nn.ConvTranspose2d):
+                nn.init.normal_(m.weight, std=0.001)
+                for name, _ in m.named_parameters():
+                    if name in ['bias']:
+                        nn.init.constant_(m.bias, 0)
+
+        if os.path.isfile(pretrained):
+            pretrained_state_dict = torch.load(pretrained)
+            logger.info('=> loading pretrained model {}'.format(pretrained))
+
+            need_init_state_dict = {}
+            for name, m in pretrained_state_dict.items():
+                if name.split('.')[0] in self.pretrained_layers \
+                   or self.pretrained_layers[0] is '*':
+                    need_init_state_dict[name] = m
+            self.load_state_dict(need_init_state_dict, strict=False)
+        elif pretrained:
+            logger.error('=> please download pre-trained models first!')
+            raise ValueError('{} is not exist!'.format(pretrained))
+
+
+def get_pose_net(cfg, is_train, **kwargs):
+    model = PoseHighResolutionNet(cfg, **kwargs)
+
+    if is_train and cfg['MODEL']['INIT_WEIGHTS']:
+        model.init_weights(cfg['MODEL']['PRETRAINED'])
+
+    return model