Update README.md

cong-wu · Apr 20, 2024 · 0af1b19 · 0af1b19
1 parent 09dc8e2
commit 0af1b19
Showing 1 changed file with 7 additions and 7 deletions.
diff --git a/README.md b/README.md
@@ -46,9 +46,9 @@ The Official implementation for  'SCD-Net: Spatiotemporal Clues Disentanglement
 - To train on NTU-RGB+D 60 under Cross-Subject evaluation, you can run
 
 
-    `python ./pretraining.py --lr 0.01 --batch-size 64 --encoder-t 0.2   --encoder-k 8192 \
-                --checkpoint-path ./checkpoints/pretrain/ \
-                --schedule 351  --epochs 451  --pre-dataset ntu60 \
+    `python ./pretraining.py --lr 0.01 --batch-size 64 --encoder-t 0.2   --encoder-k 8192 
+                --checkpoint-path ./checkpoints/pretrain/ 
+                --schedule 351  --epochs 451  --pre-dataset ntu60 
                 --protocol cross_subject --skeleton-representation joint`
 
 ## Testing 
@@ -57,15 +57,15 @@ The Official implementation for  'SCD-Net: Spatiotemporal Clues Disentanglement
 - For action recognition on NTU-RGB+D 60 under Cross-Subject evaluation, you can run
 
 
-    `python ./action_classification.py --lr 2 --batch-size 1024 \
-                --pretrained ./checkpoints/pretrain/checkpoint.pth.tar \
+    `python ./action_classification.py --lr 2 --batch-size 1024 
+                --pretrained ./checkpoints/pretrain/checkpoint.pth.tar 
                 --finetune-dataset ntu60 --protocol cross_subject --finetune_skeleton_representation joint`
 
 - For action retrieval on NTU-RGB+D 60 under Cross-Subject evaluation, you can run
 
 
-    `python ./action_retrieval.py --knn-neighbours 1 \
-                --pretrained ./checkpoints/pretrain/checkpoint.pth.tar \
+    `python ./action_retrieval.py --knn-neighbours 1 
+                --pretrained ./checkpoints/pretrain/checkpoint.pth.tar 
                 --finetune-dataset ntu60 --protocol cross_subject --finetune-skeleton-representation joint`
 
 <a name="Log"></a>