Update README.md

README.md

@@ -37,15 +37,15 @@ The dataset was created under the research project of Grant Agency of Czech Repu
 
 ### Training Procedure
 
-The training was done using Pytorch library, where CrossEntropyLoss() together with AdamW optimizer function. The training was done 
+The training was done using Pytorch library, where CrossEntropyLoss() together with AdamW optimizer function.
 
 ### Results & Metrics
 
-The overall accuracy of training for all classes reaches 99%, the mean intersection of union reaches 70%.
+The dataset has 1207 images in resolution of 416x416 pixels together with 1207 masks. The overall accuracy of training for all classes reaches 99%, the mean intersection of union reaches 70%.
 
 #### Hardware
 
-The training was done using NVIDIA Quadro P4000.
+The training was done using NVIDIA Quadro P4000 with CUDA support.
 
 #### Software