diff --git a/README.md b/README.md
index 0c0a02f..aca10ac 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ Thank you.
 $ pip install -r requirements.txt
 ```
 ### 2. Install required environment for inference using Triton server
-Check [./README_Triton.md](./README_Triton.md) for details. Install tools/packages included:
+Check [./README_ENV.md](./README_ENV.md) for details. Install tools/packages included:
 - TensorRT
 - Docker
 - nvidia-docker
@@ -48,7 +48,7 @@ IC15 | SynthText, IC15 | Eng | For IC15 only | [Click](https://drive.google.com/
 LinkRefiner | CTW1500 | - | Used with the General Model | [Click](https://drive.google.com/open?id=1XSaFwBkOaFOdtk4Ane3DFyJGPRw6v5bO)
 
 ### 5. Model preparation before run Triton server:
-a. Triton Inference Server inference: see details at [./README_Triton.md](./README_Triton.md)<br>
+a. Triton Inference Server inference: see details at [./README_ENV.md](./README_ENV.md)<br>
 Initially, you need to run a (.sh) script to prepare Model Repo, then, you just need to run Docker image when inferencing.  Script get things ready for Triton server, steps covered:
 - Convert downloaded pretrain into mutiple formats
 - Locate converted model formats into Triton's Model Repository
@@ -66,7 +66,7 @@ $ curl -v localhost:8000/v2/health/ready
 Now everythings ready, start inference by:
 - Run docker image of Triton server (replace mount -v path to your full path to model_repository):
 ```
-$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/triton-server-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
+$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
 ...
 +------------+---------+--------+
 | Model      | Version | Status |
diff --git a/README_Triton.md b/README_ENV.md
similarity index 97%
rename from README_Triton.md
rename to README_ENV.md
index ae93658..2364856 100644
--- a/README_Triton.md
+++ b/README_ENV.md
@@ -216,9 +216,9 @@ $ curl https://get.docker.com | sh \
 Pull repo, image, and prepare models (Where <xx.yy> is the version of Triton that you want to use):
 ```
 $ sudo docker pull nvcr.io/nvidia/tritonserver:<xx.yy>-py3
-$ git clone https://github.com/huukim911/triton-server-CRAFT-pytorch.git
+$ git clone https://github.com/huukim911/Triton-TensorRT-Inference-CRAFT-pytorch.git
 Run the .sh script to convert model into target formats, prepare Model Repo and start Triton server container:
-$ cd triton-server-CRAFT-pytorch
+$ cd Triton-TensorRT-Inference-CRAFT-pytorch
 $ sh prepare.sh
 Convert source model into target formats and copy into Triton's Model Repository successfully.
 ```
@@ -227,9 +227,9 @@ Run server in container and client in cmd
 ```
 $ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v <full_path_to/model_repository>:/models nvcr.io/nvidia/tritonserver:<xx.yy>-py3 tritonserver --model-repository=/models
 
-For example, run on server with full path "/home/maverick911/repo/triton-server-CRAFT-pytorch
+For example, run on server with full path "/home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch
 /model_repository":
-$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/triton-server-CRAFT-pytorch
+$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch
 /model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
 
 +----------------------+---------+--------+
@@ -244,7 +244,7 @@ I0611 04:10:23.080860 1 http_server.c9:2906] Started Metrics Service at 0.0.0.0:
 ```
 2. Infer by client in cmd (this repo), with method (triton), model name (<model_type>_\<format>), version (not required). For ex:
 ```
-$ cd triton-server-CRAFT-pytorch/
+$ cd Triton-TensorRT-Inference-CRAFT-pytorch/
 $ python infer_triton.py -m='detec_trt' -x=1 --test_folder='./images'
 Request 1, batch size 1s/sample.jpg
 elapsed time : 0.9521937370300293s
@@ -258,7 +258,7 @@ elapsed time : 1.244419813156128s
 Run server in container and client sdk in container:
 1. Start the server side:
 ```
-$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/triton-server-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
+$ sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
 
 +----------------------+---------+--------+
 | Model                | Version | Status |
diff --git a/prepare.sh b/prepare.sh
index 80bf4a6..071e76a 100644
--- a/prepare.sh
+++ b/prepare.sh
@@ -24,4 +24,4 @@ if [ ${failed} -ne 0 ]; then
 
 # III. Start Triton server image in container, mount Model Repo prepared into container volume
 # Update the full path to data/model_repository follow deploy server path: "-v <full_path_to>/model_repository:/models"
-sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/triton-server-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
\ No newline at end of file
+sudo docker run --gpus all --rm -p8000:8000 -p8001:8001 -p8002:8002 -v /home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch/model_repository:/models nvcr.io/nvidia/tritonserver:21.05-py3 tritonserver --model-repository=/models
\ No newline at end of file
diff --git a/test.py b/test.py
index e6b24c1..48779d3 100644
--- a/test.py
+++ b/test.py
@@ -176,4 +176,4 @@ def test_net(net, image, text_threshold, link_threshold, low_text, cuda, poly, r
     print("Done, elapsed time : {}s. Check at folder result/".format(time.time() - t))
 
 # Example cmd:
-# python test.py --weight /home/maverick911/repo/triton-server-CRAFT-pytorch/weight/craft_mlt_25k.pth 
\ No newline at end of file
+# python test.py --weight /home/maverick911/repo/Triton-TensorRT-Inference-CRAFT-pytorch/weight/craft_mlt_25k.pth 
\ No newline at end of file