Cosface

.vscode/settings.json

@@ -0,0 +1,4 @@
+{
+ "python.linting.pylintEnabled": true,
+ "python.linting.enabled": true
+}

Experiment-AGW-market.sh

@@ -8,5 +8,5 @@
 # weight regularized triplet loss
 # generalized mean pooling
 # non local blocks
-python3 tools/main.py --config_file='configs/AGW_baseline.yml' MODEL.DEVICE_ID "('3')" \
-DATASETS.NAMES "('market1501')" OUTPUT_DIR "('./log/market1501/Experiment-AGW-baseline')"
+python3 tools/main.py --config_file='configs/AGW_baseline.yml' MODEL.DEVICE_ID "('0')" \
+DATASETS.NAMES "('market1501')" OUTPUT_DIR "('./log/market1501/cosface-1')"

config/defaults.py

@@ -22,7 +22,7 @@
 # ID number of GPU
 _C.MODEL.DEVICE_ID = '0'
 # Name of backbone
-_C.MODEL.NAME = 'resnet50'
+_C.MODEL.BACKBONE = 'resnet50'
 # Last stride of backbone
 _C.MODEL.LAST_STRIDE = 1
 # Path to pretrained model of backbone
@@ -36,9 +36,14 @@
 _C.MODEL.CENTER_FEAT_DIM = 2048
 # If train with weighted regularized triplet loss, options: 'on', 'off'
 _C.MODEL.WEIGHT_REGULARIZED_TRIPLET = 'off'
-# If train with generalized mean pooling, options: 'on', 'off'
-_C.MODEL.GENERALIZED_MEAN_POOL = 'off'
-
+# custom config
+_C.MODEL.POOL_TYPE = 'avg'
+_C.MODEL.COSINE_LOSS_TYPE = ''
+_C.MODEL.SCALING_FACTOR = 60.0
+_C.MODEL.MARGIN = 0.35
+_C.MODEL.USE_BNBIAS = False 
+_C.MODEL.USE_DROPOUT = True
+_C.MODEL.USE_SESTN = False 
 
 # -----------------------------------------------------------------------------
 # INPUT

configs/AGW_baseline.yml

@@ -1,13 +1,19 @@
 MODEL:
- PRETRAIN_CHOICE: 'self'
- PRETRAIN_PATH: "/content/drive/Shared drives/REID/ReId-Survey-Paper/ReID-Survey/log/market1501/Experiment-AGW-baseline/resnet50_nl_model_160.pth"
- # PRETRAIN_PATH: 'C:/Users/60310249/.torch/models/resnet50-19c8e357.pth'
+ PRETRAIN_CHOICE: 'imagenet'
+ # PRETRAIN_PATH: "/content/drive/Shared drives/REID/ReId-Survey-Paper/ReID-Survey/log/market1501/local-AGW-baseline/resnet50_nl_model_120.pth"
+ PRETRAIN_PATH: '/home/thanit456/torch/weights/resnet50-19c8e357.pth'
  TRANSFER_MODE : 'off'
  CENTER_LOSS: 'on'
  CENTER_FEAT_DIM: 2048
- NAME: 'resnet50_nl'
+ BACKBONE: 'resnet50_nl'
  WEIGHT_REGULARIZED_TRIPLET: 'on'
- GENERALIZED_MEAN_POOL: 'on'
+ POOL_TYPE: 'avg'
+ COSINE_LOSS_TYPE: 'CosFace'
+ SCALING_FACTOR: 60.0
+ MARGIN: 0.35
+ USE_BNBIAS: False 
+ USE_DROPOUT: False
+ USE_SESTN: False 
 
 INPUT:
  IMG_SIZE: [256, 128]
@@ -32,6 +38,8 @@ SOLVER:
 
  WEIGHT_DECAY: 0.0005
  IMS_PER_BATCH: 64
+ # IMS_PER_BATCH: 32
+
 
  STEPS: [40, 70]
  GAMMA: 0.1

evaluate/__init__.py

@@ -0,0 +1,12 @@
+import torch 
+
+from .eval_reid import eval_func
+
+def euclidean_dist(x, y):
+ m, n = x.size(0), y.size(0)
+ xx = torch.pow(x, 2).sum(1, keepdim=True).expand(m, n)
+ yy = torch.pow(y, 2).sum(1, keepdim=True).expand(n, m).t()
+ dist = xx + yy
+ dist.addmm_(1, -2, x, y.t())
+ dist = dist.clamp(min=1e-12).sqrt()
+ return dist

evaluate/eval_reid.py

@@ -0,0 +1,65 @@
+import numpy as np
+
+def eval_func(distmat, q_pids, g_pids, q_camids, g_camids, max_rank=200):
+ """Evaluation with market1501 metric
+ Key: for each query identity, its gallery images from the same camera view are discarded.
+ """
+ num_q, num_g = distmat.shape
+ if num_g < max_rank:
+ max_rank = num_g
+ print("Note: number of gallery samples is quite small, got {}".format(num_g))
+ indices = np.argsort(distmat, axis=1)
+ matches = (g_pids[indices] == q_pids[:, np.newaxis]).astype(np.int32)
+
+ # compute cmc curve for each query
+ all_cmc = []
+ all_AP = []
+ num_valid_q = 0. # number of valid query
+ for q_idx in range(num_q):
+ # get query pid and camid
+ q_pid = q_pids[q_idx]
+ q_camid = q_camids[q_idx]
+
+ # remove gallery samples that have the same pid and camid with query
+ order = indices[q_idx]
+ remove = (g_pids[order] == q_pid) & (g_camids[order] == q_camid)
+ keep = np.invert(remove)
+
+ # compute cmc curve
+ # binary vector, positions with value 1 are correct matches
+ orig_cmc = matches[q_idx][keep]
+ if not np.any(orig_cmc):
+ # this condition is true when query identity does not appear in gallery
+ # [update:20191029] divide by query
+ all_AP.append(0)
+ continue
+
+ cmc = orig_cmc.cumsum()
+ cmc[cmc > 1] = 1
+
+ all_cmc.append(cmc[:max_rank])
+ num_valid_q += 1.
+
+ # compute average precision
+ # reference: https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Average_precision
+ # [update:20191029] support for map@max_rank
+ orig_cmc = orig_cmc[:max_rank]
+ if not np.any(orig_cmc):
+ all_AP.append(0)
+ continue
+ num_rel = orig_cmc.sum()
+ tmp_cmc = orig_cmc.cumsum()
+ tmp_cmc = [x / (i + 1.) for i, x in enumerate(tmp_cmc)]
+ tmp_cmc = np.asarray(tmp_cmc) * orig_cmc
+ AP = tmp_cmc.sum() / num_rel
+ all_AP.append(AP)
+
+ # assert num_valid_q > 0, "Error: all query identities do not appear in gallery"
+
+ all_cmc = np.asarray(all_cmc).astype(np.float32)
+ # [update:20191029] divide by query
+ all_cmc = all_cmc.sum(0) / num_q
+
+ mAP = np.mean(all_AP)
+
+ return all_cmc, mAP,all_AP

modeling/__init__.py

@@ -3,6 +3,16 @@
 from .baseline import Baseline
 
 def build_model(cfg, num_classes):
- model = Baseline(num_classes, cfg.MODEL.LAST_STRIDE, cfg.MODEL.PRETRAIN_PATH, cfg.MODEL.NAME,
- cfg.MODEL.GENERALIZED_MEAN_POOL, cfg.MODEL.PRETRAIN_CHOICE)
+ model = Baseline(num_classes=num_classes, 
+ last_stride=cfg.MODEL.LAST_STRIDE, 
+ model_path=cfg.MODEL.PRETRAIN_PATH,
+ backbone=cfg.MODEL.BACKBONE,
+ pool_type=cfg.MODEL.POOL_TYPE,
+ use_dropout=cfg.MODEL.USE_DROPOUT,
+ cosine_loss_type=cfg.MODEL.COSINE_LOSS_TYPE,
+ s=cfg.MODEL.SCALING_FACTOR,
+ m=cfg.MODEL.MARGIN,
+ use_bnbias=cfg.MODEL.USE_BNBIAS,
+ use_sestn=cfg.MODEL.USE_SESTN,
+ pretrain_choice=cfg.MODEL.PRETRAIN_CHOICE)
  return model

modeling/backbones/resnet_ibn_a.py

@@ -3,6 +3,7 @@
 import math
 import torch.utils.model_zoo as model_zoo
 
+from ..layer.attention import SESTNLayer
 
 __all__ = ['ResNet_IBN', 'resnet50_ibn_a', 'resnet101_ibn_a',
  'resnet152_ibn_a']
@@ -76,7 +77,7 @@ def forward(self, x):
 
 class ResNet_IBN(nn.Module):
 
- def __init__(self, last_stride, block, layers, num_classes=1000):
+ def __init__(self, last_stride, block, layers, num_classes=1000, use_sestn=False):
  scale = 64
  self.inplanes = scale
  super(ResNet_IBN, self).__init__()
@@ -92,6 +93,11 @@ def __init__(self, last_stride, block, layers, num_classes=1000):
  self.avgpool = nn.AvgPool2d(7)
  self.fc = nn.Linear(scale * 8 * block.expansion, num_classes)
 
+ self.use_sestn = use_sestn
+ if use_sestn:
+ self.sestn1 = SESTNLayer(256, 16)
+ self.sestn2 = SESTNLayer(512, 32)
+
  for m in self.modules():
  if isinstance(m, nn.Conv2d):
  n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
@@ -130,7 +136,15 @@ def forward(self, x):
  x = self.maxpool(x)
 
  x = self.layer1(x)
+
+ if self.use_sestn:
+ x = self.sestn1(x)
+
  x = self.layer2(x)
+
+ if self.use_sestn:
+ x = self.sestn2(x)
+
  x = self.layer3(x)
  x = self.layer4(x)