update CIE model and model links in doc

chenzhongwang9811 · Aug 3, 2021 · 41e7f10 · 41e7f10
1 parent 450bc48
commit 41e7f10
Show file tree

Hide file tree

Showing 7 changed files with 122 additions and 41 deletions.
diff --git a/README.md b/README.md
@@ -61,33 +61,34 @@ _ThinkMatch_ currently contains pytorch source code of the following deep graph
 
 ### PascalVOC - 2GM
 
-| model                  | year | aero   | bike   | bird   | boat   | bottle | bus    | car    | cat    | chair  | cow    | table  | dog    | horse  | mbkie  | person | plant  | sheep  | sofa   | train  | tv     | mean   |
-| ---------------------- | ---- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
-| [GMN](/models/GMN)     | 2018 | 0.4163 | 0.5964 | 0.6027 | 0.4795 | 0.7918 | 0.7020 | 0.6735 | 0.6488 | 0.3924 | 0.6128 | 0.6693 | 0.5976 | 0.6106 | 0.5975 | 0.3721 | 0.7818 | 0.6800 | 0.4993 | 0.8421 | 0.9141 | 0.6240 |
-| [PCA-GM](/models/PCA)  | 2019 | 0.4979 | 0.6193 | 0.6531 | 0.5715 | 0.7882 | 0.7556 | 0.6466 | 0.6969 | 0.4164 | 0.6339 | 0.5073 | 0.6705 | 0.6671 | 0.6164 | 0.4447 | 0.8116 | 0.6782 | 0.5922 | 0.7845 | 0.9042 | 0.6478 |
-| [NGM](/models/NGM)     | 2019 | 0.5010 | 0.6350 | 0.5790 | 0.5340 | 0.7980 | 0.7710 | 0.7360 | 0.6820 | 0.4110 | 0.6640 | 0.4080 | 0.6030 | 0.6190 | 0.6350 | 0.4560 | 0.7710 | 0.6930 | 0.6550 | 0.7920 | 0.8820 | 0.6413 |
-| [NHGM](/models/NGM)    | 2019 | 0.5240 | 0.6220 | 0.5830 | 0.5570 | 0.7870 | 0.7770 | 0.7440 | 0.7070 | 0.4200 | 0.6460 | 0.5380 | 0.6100 | 0.6190 | 0.6080 | 0.4680 | 0.7910 | 0.6680 | 0.5510 | 0.8090 | 0.8870 | 0.6458 |
-| [IPCA-GM](/models/PCA) | 2020 | 0.5378 | 0.6622 | 0.6714 | 0.6120 | 0.8039 | 0.7527 | 0.7255 | 0.7252 | 0.4455 | 0.6524 | 0.5430 | 0.6724 | 0.6790 | 0.6421 | 0.4793 | 0.8435 | 0.7079 | 0.6398 | 0.8380 | 0.9083 | 0.6770 |
-| [CIE-H](/models/CIE)   | 2020 | 0.5250 | 0.6858 | 0.7015 | 0.5706 | 0.8207 | 0.7700 | 0.7073 | 0.7313 | 0.4383 | 0.6994 | 0.6237 | 0.7018 | 0.7031 | 0.6641 | 0.4763 | 0.8525 | 0.7172 | 0.6400 | 0.8385 | 0.9168 | 0.6892 |
-| [BBGM](/models/BBGM)   | 2020 | 0.6187 | 0.7106 | 0.7969 | 0.7896 | 0.8740 | 0.9401 | 0.8947 | 0.8022 | 0.5676 | 0.7914 | 0.6458 | 0.7892 | 0.7615 | 0.7512 | 0.6519 | 0.9818 | 0.7729 | 0.7701 | 0.9494 | 0.9393 | 0.7899 |
-| [NGM-v2](/models/NGM)  | 2021 | 0.6184 | 0.7118 | 0.7762 | 0.7875 | 0.8733 | 0.9363 | 0.8770 | 0.7977 | 0.5535 | 0.7781 | 0.8952 | 0.7880 | 0.8011 | 0.7923 | 0.6258 | 0.9771 | 0.7769 | 0.7574 | 0.9665 | 0.9323 | 0.8011 |
-| [NHGM-v2](/models/NGM) | 2021 | 0.5995 | 0.7154 | 0.7724 | 0.7902 | 0.8773 | 0.9457 | 0.8903 | 0.8181 | 0.5995 | 0.8129 | 0.8695 | 0.7811 | 0.7645 | 0.7750 | 0.6440 | 0.9872 | 0.7778 | 0.7538 | 0.9787 | 0.9280 | 0.8040 |
+| model                                                        | year | aero   | bike   | bird   | boat   | bottle | bus    | car    | cat    | chair  | cow    | table  | dog    | horse  | mbkie  | person | plant  | sheep  | sofa   | train  | tv     | mean   |
+| ------------------------------------------------------------ | ---- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
+| [GMN](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gmn) | 2018 | 0.4163 | 0.5964 | 0.6027 | 0.4795 | 0.7918 | 0.7020 | 0.6735 | 0.6488 | 0.3924 | 0.6128 | 0.6693 | 0.5976 | 0.6106 | 0.5975 | 0.3721 | 0.7818 | 0.6800 | 0.4993 | 0.8421 | 0.9141 | 0.6240 |
+| [PCA-GM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#pca-gm) | 2019 | 0.4979 | 0.6193 | 0.6531 | 0.5715 | 0.7882 | 0.7556 | 0.6466 | 0.6969 | 0.4164 | 0.6339 | 0.5073 | 0.6705 | 0.6671 | 0.6164 | 0.4447 | 0.8116 | 0.6782 | 0.5922 | 0.7845 | 0.9042 | 0.6478 |
+| [NGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2019 | 0.5010 | 0.6350 | 0.5790 | 0.5340 | 0.7980 | 0.7710 | 0.7360 | 0.6820 | 0.4110 | 0.6640 | 0.4080 | 0.6030 | 0.6190 | 0.6350 | 0.4560 | 0.7710 | 0.6930 | 0.6550 | 0.7920 | 0.8820 | 0.6413 |
+| [NHGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2019 | 0.5240 | 0.6220 | 0.5830 | 0.5570 | 0.7870 | 0.7770 | 0.7440 | 0.7070 | 0.4200 | 0.6460 | 0.5380 | 0.6100 | 0.6190 | 0.6080 | 0.4680 | 0.7910 | 0.6680 | 0.5510 | 0.8090 | 0.8870 | 0.6458 |
+| [IPCA-GM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#pca-gm) | 2020 | 0.5378 | 0.6622 | 0.6714 | 0.6120 | 0.8039 | 0.7527 | 0.7255 | 0.7252 | 0.4455 | 0.6524 | 0.5430 | 0.6724 | 0.6790 | 0.6421 | 0.4793 | 0.8435 | 0.7079 | 0.6398 | 0.8380 | 0.9083 | 0.6770 |
+| [CIE-H](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#cie-h) | 2020 | 0.5250 | 0.6858 | 0.7015 | 0.5706 | 0.8207 | 0.7700 | 0.7073 | 0.7313 | 0.4383 | 0.6994 | 0.6237 | 0.7018 | 0.7031 | 0.6641 | 0.4763 | 0.8525 | 0.7172 | 0.6400 | 0.8385 | 0.9168 | 0.6892 |
+| [BBGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#bbgm) | 2020 | 0.6187 | 0.7106 | 0.7969 | 0.7896 | 0.8740 | 0.9401 | 0.8947 | 0.8022 | 0.5676 | 0.7914 | 0.6458 | 0.7892 | 0.7615 | 0.7512 | 0.6519 | 0.9818 | 0.7729 | 0.7701 | 0.9494 | 0.9393 | 0.7899 |
+| [NGM-v2](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2021 | 0.6184 | 0.7118 | 0.7762 | 0.7875 | 0.8733 | 0.9363 | 0.8770 | 0.7977 | 0.5535 | 0.7781 | 0.8952 | 0.7880 | 0.8011 | 0.7923 | 0.6258 | 0.9771 | 0.7769 | 0.7574 | 0.9665 | 0.9323 | 0.8011 |
+| [NHGM-v2](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2021 | 0.5995 | 0.7154 | 0.7724 | 0.7902 | 0.8773 | 0.9457 | 0.8903 | 0.8181 | 0.5995 | 0.8129 | 0.8695 | 0.7811 | 0.7645 | 0.7750 | 0.6440 | 0.9872 | 0.7778 | 0.7538 | 0.9787 | 0.9280 | 0.8040 |
 
 ### Willow Object Class - 2GM & MGM
 
-| model                    | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
-| ------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
-| [GMN](/models/GMN)       | 2018 | -               | 0.6790 | 0.7670 | 0.9980 | 0.6920    | 0.8310     | 0.7934 |
-| [PCA-GM](/models/PCA)    | 2019 | -               | 0.8760 | 0.8360 | 1.0000 | 0.7760    | 0.8840     | 0.8744 |
-| [NGM](/models/NGM)       | 2019 | -               | 0.8420 | 0.7760 | 0.9940 | 0.7680    | 0.8830     | 0.8530 |
-| [NHGM](/models/NGM)      | 2019 | -               | 0.8650 | 0.7220 | 0.9990 | 0.7930    | 0.8940     | 0.8550 |
-| [NMGM](/models/NGM)      | 2019 | -               | 0.7850 | 0.9210 | 1.0000 | 0.7870    | 0.9480     | 0.8880 |
-| [IPCA-GM](/models/PCA)   | 2020 | -               | 0.9040 | 0.8860 | 1.0000 | 0.8300    | 0.8830     | 0.9006 |
-| [BBGM](/models/BBGM)     | 2020 | -               | 0.9680 | 0.8990 | 1.0000 | 0.9980    | 0.9940     | 0.9718 |
-| [GANN-MGM](/models/GANN) | 2020 | self-supervised | 0.9600 | 0.9642 | 1.0000 | 1.0000    | 0.9879     | 0.9906 |
-| [NGM-v2](/models/NGM)     | 2021 | -               | 0.9740 | 0.9340 | 1.0000 | 0.9860    | 0.9830     | 0.9754 |
-| [NHGM-v2](/models/NGM)    | 2021 | -               | 0.9740 | 0.9390 | 1.0000 | 0.9860    | 0.9890     | 0.9780 |
-| [NMGM-v2](/models/NGM)    | 2021 | -               | 0.9760 | 0.9447 | 1.0000 | 1.0000    | 0.9902     | 0.9822 |
+| model                                                        | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
+| ------------------------------------------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
+| [GMN](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gmn) | 2018 | -               | 0.6790 | 0.7670 | 0.9980 | 0.6920    | 0.8310     | 0.7934 |
+| [PCA-GM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#pca-gm) | 2019 | -               | 0.8760 | 0.8360 | 1.0000 | 0.7760    | 0.8840     | 0.8744 |
+| [NGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2019 | -               | 0.8420 | 0.7760 | 0.9940 | 0.7680    | 0.8830     | 0.8530 |
+| [NHGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2019 | -               | 0.8650 | 0.7220 | 0.9990 | 0.7930    | 0.8940     | 0.8550 |
+| [NMGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2019 | -               | 0.7850 | 0.9210 | 1.0000 | 0.7870    | 0.9480     | 0.8880 |
+| [IPCA-GM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#pca) | 2020 | -               | 0.9040 | 0.8860 | 1.0000 | 0.8300    | 0.8830     | 0.9006 |
+| [CIE-H](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#cie-h) | 2020 | -               | 0.8581 | 0.8206 | 0.9994 | 0.8836    | 0.8871     | 0.8898 |
+| [BBGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#bbgm) | 2020 | -               | 0.9680 | 0.8990 | 1.0000 | 0.9980    | 0.9940     | 0.9718 |
+| [GANN-MGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gann) | 2020 | self-supervised | 0.9600 | 0.9642 | 1.0000 | 1.0000    | 0.9879     | 0.9906 |
+| [NGM-v2](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2021 | -               | 0.9740 | 0.9340 | 1.0000 | 0.9860    | 0.9830     | 0.9754 |
+| [NHGM-v2](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2021 | -               | 0.9740 | 0.9390 | 1.0000 | 0.9860    | 0.9890     | 0.9780 |
+| [NMGM-v2](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#ngm) | 2021 | -               | 0.9760 | 0.9447 | 1.0000 | 1.0000    | 0.9902     | 0.9822 |
 
 _ThinkMatch_ includes the flowing datasets with the provided benchmarks:
 

diff --git a/experiments/vgg16_cie_willow.yaml b/experiments/vgg16_cie_willow.yaml
@@ -0,0 +1,69 @@
+MODEL_NAME: vgg16_cie
+DATASET_NAME: willow
+
+DATASET_FULL_NAME: WillowObject
+
+MODULE: models.CIE.model
+
+BACKBONE: VGG16_bn
+
+BATCH_SIZE: 8
+DATALOADER_NUM: 2
+
+RANDOM_SEED: 123
+
+# available GPU ids
+GPUS:
+  - 0
+  #- 1
+
+# Problem configuration
+PROBLEM:
+  TYPE: 2GM
+  RESCALE:  # rescaled image size
+    - 256
+    - 256
+
+# Graph construction settings
+GRAPH:
+  SRC_GRAPH_CONSTRUCT: tri
+  TGT_GRAPH_CONSTRUCT: tri
+  SYM_ADJACENCY: True
+
+# Willow object class dataset configuration
+WillowObject:
+  TRAIN_NUM: 20  # number of images for training set
+  SPLIT_OFFSET: 0  # the starting index of training set
+
+# Training settings
+TRAIN:
+  # start, end epochs
+  START_EPOCH: 0
+  NUM_EPOCHS: 30
+
+  LOSS_FUNC: hung
+
+  # learning rate
+  LR: 1.0e-4
+  MOMENTUM: 0.9
+  LR_DECAY: 0.2
+  LR_STEP:  # (in epochs)
+    - 20
+
+  EPOCH_ITERS: 200  # iterations per epoch
+
+  CLASS: none
+
+# Evaluation settings
+EVAL:
+  EPOCH: 23  # epoch to be tested
+  SAMPLES: 1000  # number of tested pairs for each class
+
+# CIE model parameters
+CIE:
+  FEATURE_CHANNEL: 512
+  SK_ITER_NUM: 20
+  SK_EPSILON: 1.0e-10
+  SK_TAU: .005
+  GNN_FEAT: 2048
+  GNN_LAYER: 2
diff --git a/models/BBGM/README.md b/models/BBGM/README.md
@@ -18,7 +18,7 @@ pretrained model: [google drive](https://drive.google.com/file/d/1RxC7daviZf3kz2
 
 | model                  | year | aero   | bike   | bird   | boat   | bottle | bus    | car    | cat    | chair  | cow    | table  | dog    | horse  | mbkie  | person | plant  | sheep  | sofa   | train  | tv     | mean   |
 | ---------------------- | ---- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
-| [BBGM](/models/BBGM)   | 2020 | 0.6187 | 0.7106 | 0.7969 | 0.7896 | 0.8740 | 0.9401 | 0.8947 | 0.8022 | 0.5676 | 0.7914 | 0.6458 | 0.7892 | 0.7615 | 0.7512 | 0.6519 | 0.9818 | 0.7729 | 0.7701 | 0.9494 | 0.9393 | 0.7899 |
+| [BBGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#bbgm) | 2020 | 0.6187 | 0.7106 | 0.7969 | 0.7896 | 0.8740 | 0.9401 | 0.8947 | 0.8022 | 0.5676 | 0.7914 | 0.6458 | 0.7892 | 0.7615 | 0.7512 | 0.6519 | 0.9818 | 0.7729 | 0.7701 | 0.9494 | 0.9393 | 0.7899 |
 
 ### Willow Object Class - 2GM & MGM
 
@@ -28,7 +28,7 @@ pretrained model: [google drive](https://drive.google.com/file/d/1bt8wBeimM0ofm3
 
 | model                    | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
 | ------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
-| [BBGM](/models/BBGM)     | 2020 | -               | 0.9680 | 0.8990 | 1.0000 | 0.9980    | 0.9940     | 0.9718 |
+| [BBGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#bbgm) | 2020 | -               | 0.9680 | 0.8990 | 1.0000 | 0.9980    | 0.9940     | 0.9718 |
 
 ## File Organization
 ```

diff --git a/models/CIE/README.md b/models/CIE/README.md
@@ -18,7 +18,18 @@ pretrained model: [google drive](https://drive.google.com/file/d/1oRwcnw06t1rCbr
 
 | model                 | year | aero   | bike   | bird   | boat   | bottle | bus    | car    | cat    | chair  | cow    | table  | dog    | horse  | mbkie  | person | plant  | sheep  | sofa   | train  | tv     | mean   |
 | --------------------- | ---- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
-| [CIE-H](/models/CIE)   | 2020 | 0.5250 | 0.6858 | 0.7015 | 0.5706 | 0.8207 | 0.7700 | 0.7073 | 0.7313 | 0.4383 | 0.6994 | 0.6237 | 0.7018 | 0.7031 | 0.6641 | 0.4763 | 0.8525 | 0.7172 | 0.6400 | 0.8385 | 0.9168 | 0.6892 |
+| [CIE-H](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#cie-h) | 2020 | 0.5250 | 0.6858 | 0.7015 | 0.5706 | 0.8207 | 0.7700 | 0.7073 | 0.7313 | 0.4383 | 0.6994 | 0.6237 | 0.7018 | 0.7031 | 0.6641 | 0.4763 | 0.8525 | 0.7172 | 0.6400 | 0.8385 | 0.9168 | 0.6892 |
+
+### Willow Object Class - 2GM
+
+experiment config: ``experiments/vgg16_cie_willow.yaml``
+
+pretrained model: [google drive](https://drive.google.com/file/d/1aUdNTWlFxk-sf-bj08ADUoo9CSIQjzDb/view?usp=sharing)
+
+| model                    | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
+| ------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
+| [CIE-H](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#cie-h) | 2020 | -               | 0.8581 | 0.8206 | 0.9994 | 0.8836    | 0.8871     | 0.8898 |
+
 
 ## File Organization
 ```

diff --git a/models/GANN/README.md b/models/GANN/README.md
@@ -24,7 +24,7 @@ pretrained model: [google drive](https://drive.google.com/file/d/15Sg6mi9nrpsD4M
 
 | model                    | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
 | ------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
-| [GANN-MGM](/models/GANN) | 2020 | self-supervised | 0.9600 | 0.9642 | 1.0000 | 1.0000    | 0.9879     | 0.9906 |
+| [GANN-MGM](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gann) | 2020 | self-supervised | 0.9600 | 0.9642 | 1.0000 | 1.0000    | 0.9879     | 0.9906 |
 
 ## File Organization
 ```

diff --git a/models/GMN/README.md b/models/GMN/README.md
@@ -19,16 +19,16 @@ pretrained model: [google drive](https://drive.google.com/file/d/1X8p4XjzqGDniYi
 
 | model                  | year | aero   | bike   | bird   | boat   | bottle | bus    | car    | cat    | chair  | cow    | table  | dog    | horse  | mbkie  | person | plant  | sheep  | sofa   | train  | tv     | mean   |
 | ---------------------- | ---- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ |
-| [GMN](/models/GMN)     | 2018 | 0.4163 | 0.5964 | 0.6027 | 0.4795 | 0.7918 | 0.7020 | 0.6735 | 0.6488 | 0.3924 | 0.6128 | 0.6693 | 0.5976 | 0.6106 | 0.5975 | 0.3721 | 0.7818 | 0.6800 | 0.4993 | 0.8421 | 0.9141 | 0.6240 |
+| [GMN](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gmn) | 2018 | 0.4163 | 0.5964 | 0.6027 | 0.4795 | 0.7918 | 0.7020 | 0.6735 | 0.6488 | 0.3924 | 0.6128 | 0.6693 | 0.5976 | 0.6106 | 0.5975 | 0.3721 | 0.7818 | 0.6800 | 0.4993 | 0.8421 | 0.9141 | 0.6240 |
 
-### Willow Object Class - 2GM & MGM
+### Willow Object Class - 2GM
 experiment config: ``experiments/vgg16_gmn_willow.yaml``
 
 pretrained model: [google drive](https://drive.google.com/file/d/1PWM1i0oywH3hrwPdYerPazRmhApC0B4U/view?usp=sharing)
 
 | model                    | year | remark          | Car    | Duck   | Face   | Motorbike | Winebottle | mean   |
 | ------------------------ | ---- | --------------- | ------ | ------ | ------ | --------- | ---------- | ------ |
-| [GMN](/models/GMN)       | 2018 | -               | 0.6790 | 0.7670 | 0.9980 | 0.6920    | 0.8310     | 0.7934 |
+| [GMN](https://thinkmatch.readthedocs.io/en/latest/guide/models.html#gmn) | 2018 | -               | 0.6790 | 0.7670 | 0.9980 | 0.6920    | 0.8310     | 0.7934 |
 
 ## File Organization
 ```