ver 0.3.3 stable inner product

Author: smilesun

README.md

@@ -63,10 +63,13 @@ See example here: [Transformer as feature extractor, decorate JIGEN with DANN, t
 
 ### Benchmark different methods
 DomainLab provides a powerful benchmark functionality. 
-To benchmark several algorithms(combination of neural networks, models, trainers and associated hyperparameters), a single line command along with a benchmark configuration files is sufficient. See details in [Benchmarks](./docs/doc_benchmark.md)
+To benchmark several algorithms(combination of neural networks, models, trainers and associated hyperparameters), a single line command along with a benchmark configuration files is sufficient. See details in [benchmarks documentation and tutorial](./docs/doc_benchmark.md)
 
 One could simply run 
-`bash run_benchmark_slurm.sh your_benchmark_configuration.yaml` to launch different experiments with specified configuraiton. For example,  the following result (without any augmentation like flip) is for PACS dataset.
+`bash run_benchmark_slurm.sh your_benchmark_configuration.yaml` to launch different experiments with specified configuraiton. 
+
+
+For example,  the following result (without any augmentation like flip) is for PACS dataset.
 
 <div style="align: center; text-align:center;">
 <img src="https://github.com/marrlab/DomainLab/blob/master/docs/figs/stochastic_variation_two_rows.png" style="width:800px;"/> 

docs/conf.py

@@ -181,7 +181,7 @@
         {
             "href": "doc_benchmark",
             "internal": True,
-            "title": "Benchmarks"},
+            "title": "Benchmarks tutorial"},
 
         {
             "href": "doc_output",
@@ -198,7 +198,7 @@
         # },
     ],
     "heroes": {
-        "index": "DomainLab for modular domain generalization",
+        "index": "DomainLab for modular domain generalization in deep learning",
         "customization": "Configuration options to personalize your site.",
     },
     "version_dropdown": False,
@@ -266,7 +266,7 @@
         "DomainLab Documentation",
         author,
         "domainlab",
-        "A pytorch platform for domain generalization",
+        "A pytorch platform of modular domain generalization for deep learning",
         "Miscellaneous",
     ),
 ]

docs/doc_mldg.md

@@ -0,0 +1,4 @@
+# Trainer MLDG
+##  Meta Learning Domain Generalization
+
+Li, Da, et al. "Learning to generalize: Meta-learning for domain generalization." Proceedings of the AAAI conference on artificial intelligence. Vol. 32. No. 1. 2018.

docs/index.rst

@@ -18,6 +18,7 @@ Welcome to domainlab's documentation!
    docMatchDG
    docDIAL
    docFishr
+   doc_mldg
 
 
 Indices and tables

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "domainlab"
-version = "0.3.2"
+version = "0.3.3"
 readme = "README.md"
 repository = "https://github.com/marrlab/DomainLab"
 homepage = "https://marrlab.github.io/DomainLab/"

setup.py

@@ -35,7 +35,7 @@ def copy_dir(dir_path="zdata"):
     package_data =   {
                 'zdata': [f for f in copy_dir()],
              },
-    version='0.3.2',
+    version='0.3.3',
     description='Library of modular domain generalization for deep learning',
     url='https://github.com/marrlab/DomainLab',
     author='Xudong Sun, et.al.',