Update README.md

README.md

@@ -106,10 +106,55 @@ conda install --file requirements.txt
 ### Download Package
 To download package you can simply clone this GitLab repository by using the following command:
 ```bash
-$ git clone https://lab.compute.dtu.dk/lutobi/mask_rcnn_git/
+$ git clone https://lab.compute.dtu.dk/lutobi/mlsp2019_software_package/
 ```
 All the contents of the repository can also be downloaded from the GitHub site by using the "Download ZIP" button.
 
+### Run everythinh
+In order to run end to end experiment in order to generate all tables and figures from the paper, including the following activities:
+  * Mask R-CNN part:
+      * traning 5 separate models
+      * generating 5 predictions for each sample, based on 5 different models
+      * carrying out post processing of the samples and calculating final scores
+      * generating table consisting of scores
+  * SA-FCN part:
+      * traning 5 separate models
+      * generating 5 predictions for each sample, based on 5 different models
+      * carrying out post processing of the samples, saving post processed samples and calculating final scores
+      * generating table consisting of scores
+  * generating Figure 4, Figure 5 and Figure 6 from the paper
+  * generating Tbale 1 and Table 2 from the paper
+
+please follow steps:
+1. Log in to DTU Compute cluster via ThinLinc.
+2. Open gterm terminal.
+3. Log in to one of the GPUs available for instance: 
+```
+ssh titan11
+```
+4. Activate your environment, for instance: 
+```
+conda activate lutobi
+```
+5. Check which node is available:
+```
+gpustat
+```
+6. Check in to the available nodes, for instance:
+```
+export CUDA\_VISIBLE\_DEVICES="0,1"
+```
+7. Go to directory of the downloaded repo, for instance:
+```
+cd /dtu-compute/s162377/mlsp2019_software_package/
+```
+8. Open file 'mask_rcnn/run_maskrcnn.sh' and check if the dataset path is properly defined.
+9. Check if you are on correct branch on the repo.
+10. Run the bash script by calling:
+```
+./run_all.sh
+```
+
 ### Run Mask R-CNN
 In order to run end to end experiment for Mask R-CNN, which consists of:
   * traning 5 separate models
@@ -139,13 +184,13 @@ export CUDA\_VISIBLE\_DEVICES="0,1"
 ```
 7. Go to directory of the downloaded repo, for instance:
 ```
-cd /dtu-compute/s162377/mask_rcnn_git/
+cd /dtu-compute/s162377/mlsp2019_software_package/mask_rcnn_git/
 ```
-8. Open file run_it.sh and check if the dataset path is properly defined.
+8. Open file run_maskrcnn.sh and check if the dataset path is properly defined.
 9. Check if you are on correct branch on the repo.
 10. Run the bash script by calling:
 ```
-./run_it.sh
+./run_maskrcnn.sh
 ```
 
 ### Run SA-FCN
@@ -164,7 +209,7 @@ ssh titan11
 ```
 4. Activate your environment, for instance: 
 ```
-conda activate lutobi
+source activate s162377
 ```
 5. Check which node is available:
 ```
@@ -172,16 +217,16 @@ gpustat
 ```
 6. Check in to the available nodes, for instance:
 ```
-export CUDA\_VISIBLE\_DEVICES="0,1"
+export CUDA\_VISIBLE\_DEVICES="1"
 ```
 7. Go to directory of the downloaded repo, for instance:
 ```
-cd /dtu-compute/s162377/sa_fcn_thesis/python
+cd /dtu-compute/s162377/mlsp2019_software_package/sa_fcn_thesis/
 ```
 8. Check if you are on correct branch on the repo.
 9. Run the bash script by calling:
 ```
-./run_it.sh
+./run_safcn.sh
 ```
 
 For more information on package content can be found in the documentation [file](Documentation.md).