Hugging Face's logo

HoyerChou
/
MultiAugs

Model card Files Community
HoyerChou commited on
Commit
d304cbc
·
verified ·
1 Parent(s): 5042daf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -7
README.md CHANGED
@@ -12,20 +12,28 @@ Code link: https://github.com/hnuzhy/MultiAugs
12
  **COCO1K / COCO5K / COCO10K**
13
 
14
  *trained on `partly labeled (1k, 5k or 10k) COCO train-set` and `left unlabeled COCO train-set`*
15
- * **ResNet-18 (256x192, COCO1K, 30 epochs)**
16
- * **ResNet-18 (256x192, COCO5K, 70 epochs)**
17
- * **ResNet-18 (256x192, COCO10K, 100 epochs)**
 
 
 
 
18
 
19
  **COCOall + COCOunlabel**
20
 
21
  *trained on `labeled COCO train-set` and `unlabeled COCO unlabeled-set`*
22
- * **ResNet-50 (256x192, 400 epochs)**
23
- * **ResNet-101 (256x192, 400 epochs)**
24
- * **HRNet-W48 (384x288, 400 epochs)**
 
 
 
 
25
 
26
  **MPII + AIC**
27
 
28
  *trained on `labeled MPII train-set` and `unlabeled AIC train-set`*
29
- * **HRNet-W32 (256x256, 400 epochs)**
30
 
31
 
 
12
  **COCO1K / COCO5K / COCO10K**
13
 
14
  *trained on `partly labeled (1k, 5k or 10k) COCO train-set` and `left unlabeled COCO train-set`*
15
+ * **ResNet-18 (Pose_Cons using single network)(256x192, COCO1K, 30 epochs)**: [pose_cons_18-COCO1K_e30-model_best.pth.tar](./pose_cons_18-COCO1K_e30-model_best.pth.tar)
16
+ * **ResNet-18 (Pose_Cons using single network)(256x192, COCO5K, 70 epochs)**: [pose_cons_18-COCO5K_e70-model_best.pth.tar](./pose_cons_18-COCO5K_e70-model_best.pth.tar)
17
+ * **ResNet-18 (Pose_Cons using single network)(256x192, COCO10K, 100 epochs)**: [pose_cons_18-COCO10K_e100-model_best.pth.tar](./pose_cons_18-COCO10K_e100-model_best.pth.tar)
18
+ * **ResNet-18 (Pose_Dual using dual networks)(256x192, COCO1K, 30 epochs)**: [pose_dual_18-COCO1K_e30-model_best.pth.tar](./pose_dual_18-COCO1K_e30-model_best.pth.tar)
19
+ * **ResNet-18 (Pose_Dual using dual networks)(256x192, COCO5K, 70 epochs)**: [pose_dual_18-COCO5K_e70-model_best.pth.tar](./pose_dual_18-COCO5K_e70-model_best.pth.tar)
20
+ * **ResNet-18 (Pose_Dual using dual networks)(256x192, COCO10K, 100 epochs)**: [pose_dual_18-COCO10K_e100-model_best.pth.tar](./pose_dual_18-COCO10K_e100-model_best.pth.tar)
21
+
22
 
23
  **COCOall + COCOunlabel**
24
 
25
  *trained on `labeled COCO train-set` and `unlabeled COCO unlabeled-set`*
26
+ * **ResNet-50 (Pose_Cons) (256x192, 400 epochs)**: [pose_cons_50-COCO_COCOunlabel_e400-model_best.pth.tar](./pose_cons_50-COCO_COCOunlabel_e400-model_best.pth.tar)
27
+ * **ResNet-101 (Pose_Cons) (256x192, 400 epochs)**: [pose_cons_101-COCO_COCOunlabel_e400-model_best.pth.tar](./pose_cons_101-COCO_COCOunlabel_e400-model_best.pth.tar)
28
+ * **HRNet-w48 (Pose_Cons) (384x288, 300 epochs)**: [pose_cons_w48-COCO_COCOunlabel_e300-model_best.pth.tar](./pose_cons_w48-COCO_COCOunlabel_e300-model_best.pth.tar)
29
+ * **ResNet-50 (Pose_Dual) (256x192, 400 epochs)**: [pose_dual_50-COCO_COCOunlabel_e400-model_best.pth.tar](./pose_dual_50-COCO_COCOunlabel_e400-model_best.pth.tar)
30
+ * **ResNet-101 (Pose_Dual) (256x192, 400 epochs)**: [pose_dual_101-COCO_COCOunlabel_e400-model_best.pth.tar](./pose_dual_101-COCO_COCOunlabel_e400-model_best.pth.tar)
31
+ * **HRNet-w48 (Pose_Dual) (384x288, 300 epochs)**: [pose_dual_w48-COCO_COCOunlabel_e300-model_best.pth.tar](./pose_dual_w48-COCO_COCOunlabel_e300-model_best.pth.tar)
32
+
33
 
34
  **MPII + AIC**
35
 
36
  *trained on `labeled MPII train-set` and `unlabeled AIC train-set`*
37
+ * **HRNet-w32 (Pose_Dual) (256x256, 400 epochs)** [We are sorry that it cannot be released due to company copyright issues]
38
 
39