update

README.md

@@ -73,7 +73,7 @@ Run `python test_transformer.py` to evaluate the model using the following argum
 python test_transformer.py --batch_size 10 --features_path /path/to/features --model_path /path/to/saved_transformer_models/ckpt --num_clusters 5
 ```
 
-**Note:** We have removed the ```SPICE``` evaluation metric during training because it is time-cost. You can add it when evaluate the model: download this [file](https://drive.google.com/file/d/1vEVsbEFjDstmSvoWhu4UdKaJjX1jJXpR/view?usp=sharing) and put it in ```/path/to/evaluation/```, then uncomment codes in [init代码]().
+**Note:** We have removed the ```SPICE``` evaluation metric during training because it is time-cost. You can add it when evaluate the model: download this [file](https://drive.google.com/file/d/1vEVsbEFjDstmSvoWhu4UdKaJjX1jJXpR/view?usp=sharing) and put it in ```/path/to/evaluation/```, then uncomment codes in [__init__.py](https://github.com/zchoi/S2-Transformer/blob/master/evaluation/__init__.py).
 
 We provide pretrained model [here](https://drive.google.com/file/d/1Y133r4Wd9ediS1Jqlwc1qtL15vCK_Mik/view?usp=sharing), you will get following results (second row) by evaluating the pretrained model:
 
@@ -107,7 +107,4 @@ Huang, and Rongrong Ji. Rstnet: Captioning with adaptive attention on visual and
 ```
 ## Acknowledgements
 Thanks Zhang _et.al_ for releasing the visual features (ResNeXt-101 and ResNeXt-152). Our code implementation is also based on their [repo](https://github.com/zhangxuying1004/RSTNet).   
-Thanks for the original annotations prepared by [M<sup>2</sup> Transformer](https://github.com/aimagelab/meshed-memory-transformer), and effective visual representation from [grid-feats-vqa](https://github.com/facebookresearch/grid-feats-vqa).
-
->>>>>>> master
-
+Thanks for the original annotations prepared by [M<sup>2</sup> Transformer](https://github.com/aimagelab/meshed-memory-transformer), and effective visual representation from [grid-feats-vqa](https://github.com/facebookresearch/grid-feats-vqa).