Add typical training script and some bug fixes

1. Resolve deprecated scheduler stepping issue
2. Make losses in the same scale(replace mean with sum in separate triplet loss, enlarge pose similarity loss 10x)
3. Add ReLU when compute distance in triplet loss
4. Remove classes except Model from `models` package init

1 files changed, 2 insertions, 1 deletions

diff --git a/.gitignore b/.gitignore
index 08f887c..f4b5746 100644
--- a/.gitignore
+++ b/.gitignore
@@ -146,4 +146,5 @@ dmypy.json
 
 # Dataset
 data/
-
+# Runtime
+runs/