Richard

Upload folder using huggingface_hub

0e314eb verified 11 months ago

25 kB

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import sys
import time
from typing import List, Optional, Tuple

import cv2
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.transforms as T
import torchvision.transforms.functional as f
from pydantic import BaseModel

import logging
logger = logging.getLogger(__name__)


class BoundingBox(BaseModel):
    x1: int
    y1: int
    x2: int
    y2: int
    cls_id: int
    conf: float


class TVFrameResult(BaseModel):
    frame_id: int
    boxes: list[BoundingBox]
    keypoints: list[tuple[int, int]]

BatchNorm2d = nn.BatchNorm2d
BN_MOMENTUM = 0.1

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 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = 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 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1,
                               bias=False)
        self.bn3 = 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(inplace=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),
                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),
                        BatchNorm2d(num_inchannels[i], momentum=BN_MOMENTUM)))
                    # 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),
                                BatchNorm2d(num_outchannels_conv3x3, momentum=BN_MOMENTUM)))
                        else:
                            num_outchannels_conv3x3 = num_inchannels[j]
                            conv3x3s.append(nn.Sequential(
                                nn.Conv2d(num_inchannels[j],
                                          num_outchannels_conv3x3,
                                          3, 2, 1, bias=False),
                                BatchNorm2d(num_outchannels_conv3x3,
                                            momentum=BN_MOMENTUM),
                                nn.ReLU(inplace=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]
                elif j > i:
                    y = y + F.interpolate(
                        self.fuse_layers[i][j](x[j]),
                        size=[x[i].shape[2], x[i].shape[3]],
                        mode='bilinear')
                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 HighResolutionNet(nn.Module):

    def __init__(self, config, **kwargs):
        self.inplanes = 64
        extra = config['MODEL']['EXTRA']
        super(HighResolutionNet, self).__init__()

        # stem net
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=2, padding=1,
                               bias=False)
        self.bn1 = BatchNorm2d(self.inplanes, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(self.inplanes, self.inplanes, kernel_size=3, stride=2, padding=1,
                               bias=False)
        self.bn2 = BatchNorm2d(self.inplanes, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.sf = nn.Softmax(dim=1)
        self.layer1 = self._make_layer(Bottleneck, 64, 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=True)

        self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
        final_inp_channels = sum(pre_stage_channels) + self.inplanes

        self.head = nn.Sequential(nn.Sequential(
            nn.Conv2d(
                in_channels=final_inp_channels,
                out_channels=final_inp_channels,
                kernel_size=1),
            BatchNorm2d(final_inp_channels, momentum=BN_MOMENTUM),
            nn.ReLU(inplace=True),
            nn.Conv2d(
                in_channels=final_inp_channels,
                out_channels=config['MODEL']['NUM_JOINTS'],
                kernel_size=extra['FINAL_CONV_KERNEL']),
            nn.Softmax(dim=1)))



    def _make_head(self, x, x_skip):
        x = self.upsample(x)
        x = torch.cat([x, x_skip], dim=1)
        x = self.head(x)

        return x

    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),
                        BatchNorm2d(
                            num_channels_cur_layer[i], momentum=BN_MOMENTUM),
                        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),
                        BatchNorm2d(outchannels, momentum=BN_MOMENTUM),
                        nn.ReLU(inplace=True)))
                transition_layers.append(nn.Sequential(*conv3x3s))

        return nn.ModuleList(transition_layers)

    def _make_layer(self, block, inplanes, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                BatchNorm2d(planes * block.expansion, momentum=BN_MOMENTUM),
            )

        layers = []
        layers.append(block(inplanes, planes, stride, downsample))
        inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(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):
        # h, w = x.size(2), x.size(3)
        x = self.conv1(x)
        x_skip = x.clone()
        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])
        x = self.stage4(x_list)

        # Head Part
        height, width = x[0].size(2), x[0].size(3)
        x1 = F.interpolate(x[1], size=(height, width), mode='bilinear', align_corners=False)
        x2 = F.interpolate(x[2], size=(height, width), mode='bilinear', align_corners=False)
        x3 = F.interpolate(x[3], size=(height, width), mode='bilinear', align_corners=False)
        x = torch.cat([x[0], x1, x2, x3], 1)
        x = self._make_head(x, x_skip)

        return x

    def init_weights(self, pretrained=''):
        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)
                #nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
        if pretrained != '':
            if os.path.isfile(pretrained):
                pretrained_dict = torch.load(pretrained)
                model_dict = self.state_dict()
                pretrained_dict = {k: v for k, v in pretrained_dict.items()
                                   if k in model_dict.keys()}
                model_dict.update(pretrained_dict)
                self.load_state_dict(model_dict)
            else:
                sys.exit(f'Weights {pretrained} not found.')


def get_cls_net(config, pretrained='', **kwargs):
    """Create keypoint detection model with softmax activation"""
    model = HighResolutionNet(config, **kwargs)
    model.init_weights(pretrained)
    return model


def get_cls_net_l(config, pretrained='', **kwargs):
    """Create line detection model with sigmoid activation"""
    model = HighResolutionNet(config, **kwargs)
    model.init_weights(pretrained)
    
    # After loading weights, replace just the activation function
    # The saved model expects the nested Sequential structure
    inner_seq = model.head[0]
    # Replace softmax (index 4) with sigmoid
    model.head[0][4] = nn.Sigmoid()
    
    return model

# Simplified utility functions - removed complex Gaussian generation functions
# These were mainly used for training data generation, not inference



# generate_gaussian_array_vectorized_dist_l function removed - not used in current implementation
@torch.inference_mode()
def run_inference(model, input_tensor: torch.Tensor, device):
    input_tensor = input_tensor.to(device).to(memory_format=torch.channels_last)
    output = model.module().forward(input_tensor)
    return output

def preprocess_batch_fast(frames):
    """Ultra-fast batch preprocessing using optimized tensor operations"""
    target_size = (540, 960)  # H, W format for model input
    batch = []
    for i, frame in enumerate(frames):
        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
        img = cv2.resize(frame_rgb, (target_size[1], target_size[0]))
        img = img.astype(np.float32) / 255.0
        img = np.transpose(img, (2, 0, 1))  # HWC -> CHW
        batch.append(img)
    batch = torch.from_numpy(np.stack(batch)).float()

    return batch

def extract_keypoints_from_heatmap(heatmap: torch.Tensor, scale: int = 2, max_keypoints: int = 1):
    """Optimized keypoint extraction from heatmaps"""
    batch_size, n_channels, height, width = heatmap.shape
    
    # Find local maxima using max pooling (keep on GPU)
    kernel = 3
    pad = 1
    max_pooled = F.max_pool2d(heatmap, kernel, stride=1, padding=pad)
    local_maxima = (max_pooled == heatmap)
    heatmap = heatmap * local_maxima
    
    # Get top keypoints (keep on GPU longer)
    scores, indices = torch.topk(heatmap.view(batch_size, n_channels, -1), max_keypoints, sorted=False)
    y_coords = torch.div(indices, width, rounding_mode="floor")
    x_coords = indices % width
    
    # Optimized tensor operations
    x_coords = x_coords * scale
    y_coords = y_coords * scale
    
    # Create result tensor directly on GPU
    results = torch.stack([x_coords.float(), y_coords.float(), scores], dim=-1)
    
    return results


def extract_keypoints_from_heatmap_fast(heatmap: torch.Tensor, scale: int = 2, max_keypoints: int = 1):
    """Ultra-fast keypoint extraction optimized for speed"""
    batch_size, n_channels, height, width = heatmap.shape
    
    # Simplified local maxima detection (faster but slightly less accurate)
    max_pooled = F.max_pool2d(heatmap, 3, stride=1, padding=1)
    local_maxima = (max_pooled == heatmap)
    
    # Apply mask and get top keypoints in one go
    masked_heatmap = heatmap * local_maxima
    flat_heatmap = masked_heatmap.view(batch_size, n_channels, -1)
    scores, indices = torch.topk(flat_heatmap, max_keypoints, dim=-1, sorted=False)
    
    # Vectorized coordinate calculation
    y_coords = torch.div(indices, width, rounding_mode="floor") * scale
    x_coords = (indices % width) * scale
    
    # Stack results efficiently
    results = torch.stack([x_coords.float(), y_coords.float(), scores], dim=-1)
    return results


def process_keypoints_vectorized(kp_coords, kp_threshold, w, h, batch_size):
    """Ultra-fast vectorized keypoint processing"""
    batch_results = []
    
    # Convert to numpy once for faster CPU operations
    kp_np = kp_coords.cpu().numpy()
    
    for batch_idx in range(batch_size):
        kp_dict = {}
        # Vectorized threshold check
        valid_kps = kp_np[batch_idx, :, 0, 2] > kp_threshold
        valid_indices = np.where(valid_kps)[0]
        
        for ch_idx in valid_indices:
            x = float(kp_np[batch_idx, ch_idx, 0, 0]) / w
            y = float(kp_np[batch_idx, ch_idx, 0, 1]) / h
            p = float(kp_np[batch_idx, ch_idx, 0, 2])
            kp_dict[ch_idx + 1] = {'x': x, 'y': y, 'p': p}
        
        batch_results.append(kp_dict)
    
    return batch_results

def inference_batch(frames, model, kp_threshold, device, batch_size=8):
    """Optimized batch inference for multiple frames"""
    results = []
    num_frames = len(frames)
    
    # Get the device from the model itself
    model_device = next(model.parameters()).device
    
    # Process all frames in optimally-sized batches
    for i in range(0, num_frames, batch_size):
        current_batch_size = min(batch_size, num_frames - i)
        batch_frames = frames[i:i + current_batch_size]
        
        # Fast preprocessing - create on CPU first
        batch = preprocess_batch_fast(batch_frames)
        b, c, h, w = batch.size()
        
        # Move batch to model device
        batch = batch.to(model_device)

        with torch.no_grad():
            heatmaps = model(batch)

        # Ultra-fast keypoint extraction
        kp_coords = extract_keypoints_from_heatmap_fast(heatmaps[:,:-1,:,:], scale=2, max_keypoints=1)
        
        # Vectorized batch processing - no loops
        batch_results = process_keypoints_vectorized(kp_coords, kp_threshold, 960, 540, current_batch_size)
        results.extend(batch_results)
        
        # Minimal cleanup
        del heatmaps, kp_coords, batch
    
    return results

# Keypoint mapping from detection indices to standard football pitch keypoint IDs
map_keypoints = {
    1: 1, 2: 14, 3: 25, 4: 2, 5: 10, 6: 18, 7: 26, 8: 3, 9: 7, 10: 23, 
    11: 27, 20: 4, 21: 8, 22: 24, 23: 28, 24: 5, 25: 13, 26: 21, 27: 29, 
    28: 6, 29: 17, 30: 30, 31: 11, 32: 15, 33: 19, 34: 12, 35: 16, 36: 20, 
    45: 9, 50: 31, 52: 32, 57: 22
}

def get_mapped_keypoints(kp_points):
    """Apply keypoint mapping to detection results"""
    mapped_points = {}
    for key, value in kp_points.items():
        if key in map_keypoints:
            mapped_key = map_keypoints[key]
            mapped_points[mapped_key] = value
        # else:
            # Keep unmapped keypoints with original key
            # mapped_points[key] = value
    return mapped_points

def process_batch_input(frames, model, kp_threshold, device, batch_size=16):
    """Process multiple input images in batch"""
    # Batch inference
    kp_results = inference_batch(frames, model, kp_threshold, device, batch_size)
    kp_results = [get_mapped_keypoints(kp) for kp in kp_results]

    return kp_results

	from __future__ import absolute_import
	from __future__ import division
	from __future__ import print_function

	import os
	import sys
	import time
	from typing import List, Optional, Tuple

	import cv2
	import numpy as np
	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torchvision.transforms as T
	import torchvision.transforms.functional as f
	from pydantic import BaseModel

	import logging
	logger = logging.getLogger(__name__)


	class BoundingBox(BaseModel):
	x1: int
	y1: int
	x2: int
	y2: int
	cls_id: int
	conf: float


	class TVFrameResult(BaseModel):
	frame_id: int
	boxes: list[BoundingBox]
	keypoints: list[tuple[int, int]]

	BatchNorm2d = nn.BatchNorm2d
	BN_MOMENTUM = 0.1

	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 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
	self.relu = nn.ReLU(inplace=True)
	self.conv2 = conv3x3(planes, planes)
	self.bn2 = 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 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
	self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
	padding=1, bias=False)
	self.bn2 = BatchNorm2d(planes, momentum=BN_MOMENTUM)
	self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1,
	bias=False)
	self.bn3 = 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(inplace=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),
	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),
	BatchNorm2d(num_inchannels[i], momentum=BN_MOMENTUM)))
	# 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),
	BatchNorm2d(num_outchannels_conv3x3, momentum=BN_MOMENTUM)))
	else:
	num_outchannels_conv3x3 = num_inchannels[j]
	conv3x3s.append(nn.Sequential(
	nn.Conv2d(num_inchannels[j],
	num_outchannels_conv3x3,
	3, 2, 1, bias=False),
	BatchNorm2d(num_outchannels_conv3x3,
	momentum=BN_MOMENTUM),
	nn.ReLU(inplace=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]
	elif j > i:
	y = y + F.interpolate(
	self.fuse_layers[i][j](x[j]),
	size=[x[i].shape[2], x[i].shape[3]],
	mode='bilinear')
	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 HighResolutionNet(nn.Module):

	def __init__(self, config, **kwargs):
	self.inplanes = 64
	extra = config['MODEL']['EXTRA']
	super(HighResolutionNet, self).__init__()

	# stem net
	self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=2, padding=1,
	bias=False)
	self.bn1 = BatchNorm2d(self.inplanes, momentum=BN_MOMENTUM)
	self.conv2 = nn.Conv2d(self.inplanes, self.inplanes, kernel_size=3, stride=2, padding=1,
	bias=False)
	self.bn2 = BatchNorm2d(self.inplanes, momentum=BN_MOMENTUM)
	self.relu = nn.ReLU(inplace=True)
	self.sf = nn.Softmax(dim=1)
	self.layer1 = self._make_layer(Bottleneck, 64, 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=True)

	self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
	final_inp_channels = sum(pre_stage_channels) + self.inplanes

	self.head = nn.Sequential(nn.Sequential(
	nn.Conv2d(
	in_channels=final_inp_channels,
	out_channels=final_inp_channels,
	kernel_size=1),
	BatchNorm2d(final_inp_channels, momentum=BN_MOMENTUM),
	nn.ReLU(inplace=True),
	nn.Conv2d(
	in_channels=final_inp_channels,
	out_channels=config['MODEL']['NUM_JOINTS'],
	kernel_size=extra['FINAL_CONV_KERNEL']),
	nn.Softmax(dim=1)))



	def _make_head(self, x, x_skip):
	x = self.upsample(x)
	x = torch.cat([x, x_skip], dim=1)
	x = self.head(x)

	return x

	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),
	BatchNorm2d(
	num_channels_cur_layer[i], momentum=BN_MOMENTUM),
	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),
	BatchNorm2d(outchannels, momentum=BN_MOMENTUM),
	nn.ReLU(inplace=True)))
	transition_layers.append(nn.Sequential(*conv3x3s))

	return nn.ModuleList(transition_layers)

	def _make_layer(self, block, inplanes, planes, blocks, stride=1):
	downsample = None
	if stride != 1 or inplanes != planes * block.expansion:
	downsample = nn.Sequential(
	nn.Conv2d(inplanes, planes * block.expansion,
	kernel_size=1, stride=stride, bias=False),
	BatchNorm2d(planes * block.expansion, momentum=BN_MOMENTUM),
	)

	layers = []
	layers.append(block(inplanes, planes, stride, downsample))
	inplanes = planes * block.expansion
	for i in range(1, blocks):
	layers.append(block(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):
	# h, w = x.size(2), x.size(3)
	x = self.conv1(x)
	x_skip = x.clone()
	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])
	x = self.stage4(x_list)

	# Head Part
	height, width = x[0].size(2), x[0].size(3)
	x1 = F.interpolate(x[1], size=(height, width), mode='bilinear', align_corners=False)
	x2 = F.interpolate(x[2], size=(height, width), mode='bilinear', align_corners=False)
	x3 = F.interpolate(x[3], size=(height, width), mode='bilinear', align_corners=False)
	x = torch.cat([x[0], x1, x2, x3], 1)
	x = self._make_head(x, x_skip)

	return x

	def init_weights(self, pretrained=''):
	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)
	#nn.init.constant_(m.bias, 0)
	elif isinstance(m, nn.BatchNorm2d):
	nn.init.constant_(m.weight, 1)
	nn.init.constant_(m.bias, 0)
	if pretrained != '':
	if os.path.isfile(pretrained):
	pretrained_dict = torch.load(pretrained)
	model_dict = self.state_dict()
	pretrained_dict = {k: v for k, v in pretrained_dict.items()
	if k in model_dict.keys()}
	model_dict.update(pretrained_dict)
	self.load_state_dict(model_dict)
	else:
	sys.exit(f'Weights {pretrained} not found.')


	def get_cls_net(config, pretrained='', **kwargs):
	"""Create keypoint detection model with softmax activation"""
	model = HighResolutionNet(config, **kwargs)
	model.init_weights(pretrained)
	return model


	def get_cls_net_l(config, pretrained='', **kwargs):
	"""Create line detection model with sigmoid activation"""
	model = HighResolutionNet(config, **kwargs)
	model.init_weights(pretrained)

	# After loading weights, replace just the activation function
	# The saved model expects the nested Sequential structure
	inner_seq = model.head[0]
	# Replace softmax (index 4) with sigmoid
	model.head[0][4] = nn.Sigmoid()

	return model

	# Simplified utility functions - removed complex Gaussian generation functions
	# These were mainly used for training data generation, not inference



	# generate_gaussian_array_vectorized_dist_l function removed - not used in current implementation
	@torch.inference_mode()
	def run_inference(model, input_tensor: torch.Tensor, device):
	input_tensor = input_tensor.to(device).to(memory_format=torch.channels_last)
	output = model.module().forward(input_tensor)
	return output

	def preprocess_batch_fast(frames):
	"""Ultra-fast batch preprocessing using optimized tensor operations"""
	target_size = (540, 960) # H, W format for model input
	batch = []
	for i, frame in enumerate(frames):
	frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
	img = cv2.resize(frame_rgb, (target_size[1], target_size[0]))
	img = img.astype(np.float32) / 255.0
	img = np.transpose(img, (2, 0, 1)) # HWC -> CHW
	batch.append(img)
	batch = torch.from_numpy(np.stack(batch)).float()

	return batch

	def extract_keypoints_from_heatmap(heatmap: torch.Tensor, scale: int = 2, max_keypoints: int = 1):
	"""Optimized keypoint extraction from heatmaps"""
	batch_size, n_channels, height, width = heatmap.shape

	# Find local maxima using max pooling (keep on GPU)
	kernel = 3
	pad = 1
	max_pooled = F.max_pool2d(heatmap, kernel, stride=1, padding=pad)
	local_maxima = (max_pooled == heatmap)
	heatmap = heatmap * local_maxima

	# Get top keypoints (keep on GPU longer)
	scores, indices = torch.topk(heatmap.view(batch_size, n_channels, -1), max_keypoints, sorted=False)
	y_coords = torch.div(indices, width, rounding_mode="floor")
	x_coords = indices % width

	# Optimized tensor operations
	x_coords = x_coords * scale
	y_coords = y_coords * scale

	# Create result tensor directly on GPU
	results = torch.stack([x_coords.float(), y_coords.float(), scores], dim=-1)

	return results


	def extract_keypoints_from_heatmap_fast(heatmap: torch.Tensor, scale: int = 2, max_keypoints: int = 1):
	"""Ultra-fast keypoint extraction optimized for speed"""
	batch_size, n_channels, height, width = heatmap.shape

	# Simplified local maxima detection (faster but slightly less accurate)
	max_pooled = F.max_pool2d(heatmap, 3, stride=1, padding=1)
	local_maxima = (max_pooled == heatmap)

	# Apply mask and get top keypoints in one go
	masked_heatmap = heatmap * local_maxima
	flat_heatmap = masked_heatmap.view(batch_size, n_channels, -1)
	scores, indices = torch.topk(flat_heatmap, max_keypoints, dim=-1, sorted=False)

	# Vectorized coordinate calculation
	y_coords = torch.div(indices, width, rounding_mode="floor") * scale
	x_coords = (indices % width) * scale

	# Stack results efficiently
	results = torch.stack([x_coords.float(), y_coords.float(), scores], dim=-1)
	return results


	def process_keypoints_vectorized(kp_coords, kp_threshold, w, h, batch_size):
	"""Ultra-fast vectorized keypoint processing"""
	batch_results = []

	# Convert to numpy once for faster CPU operations
	kp_np = kp_coords.cpu().numpy()

	for batch_idx in range(batch_size):
	kp_dict = {}
	# Vectorized threshold check
	valid_kps = kp_np[batch_idx, :, 0, 2] > kp_threshold
	valid_indices = np.where(valid_kps)[0]

	for ch_idx in valid_indices:
	x = float(kp_np[batch_idx, ch_idx, 0, 0]) / w
	y = float(kp_np[batch_idx, ch_idx, 0, 1]) / h
	p = float(kp_np[batch_idx, ch_idx, 0, 2])
	kp_dict[ch_idx + 1] = {'x': x, 'y': y, 'p': p}

	batch_results.append(kp_dict)

	return batch_results

	def inference_batch(frames, model, kp_threshold, device, batch_size=8):
	"""Optimized batch inference for multiple frames"""
	results = []
	num_frames = len(frames)

	# Get the device from the model itself
	model_device = next(model.parameters()).device

	# Process all frames in optimally-sized batches
	for i in range(0, num_frames, batch_size):
	current_batch_size = min(batch_size, num_frames - i)
	batch_frames = frames[i:i + current_batch_size]

	# Fast preprocessing - create on CPU first
	batch = preprocess_batch_fast(batch_frames)
	b, c, h, w = batch.size()

	# Move batch to model device
	batch = batch.to(model_device)

	with torch.no_grad():
	heatmaps = model(batch)

	# Ultra-fast keypoint extraction
	kp_coords = extract_keypoints_from_heatmap_fast(heatmaps[:,:-1,:,:], scale=2, max_keypoints=1)

	# Vectorized batch processing - no loops
	batch_results = process_keypoints_vectorized(kp_coords, kp_threshold, 960, 540, current_batch_size)
	results.extend(batch_results)

	# Minimal cleanup
	del heatmaps, kp_coords, batch

	return results

	# Keypoint mapping from detection indices to standard football pitch keypoint IDs
	map_keypoints = {
	1: 1, 2: 14, 3: 25, 4: 2, 5: 10, 6: 18, 7: 26, 8: 3, 9: 7, 10: 23,
	11: 27, 20: 4, 21: 8, 22: 24, 23: 28, 24: 5, 25: 13, 26: 21, 27: 29,
	28: 6, 29: 17, 30: 30, 31: 11, 32: 15, 33: 19, 34: 12, 35: 16, 36: 20,
	45: 9, 50: 31, 52: 32, 57: 22
	}

	def get_mapped_keypoints(kp_points):
	"""Apply keypoint mapping to detection results"""
	mapped_points = {}
	for key, value in kp_points.items():
	if key in map_keypoints:
	mapped_key = map_keypoints[key]
	mapped_points[mapped_key] = value
	# else:
	# Keep unmapped keypoints with original key
	# mapped_points[key] = value
	return mapped_points

	def process_batch_input(frames, model, kp_threshold, device, batch_size=16):
	"""Process multiple input images in batch"""
	# Batch inference
	kp_results = inference_batch(frames, model, kp_threshold, device, batch_size)
	kp_results = [get_mapped_keypoints(kp) for kp in kp_results]

	return kp_results