Update README.md

README.md

@@ -147,61 +147,43 @@ This AI model can be embedded as an Application Programming Interface (API) call
 
 ## Training Dataset
 
-** Data Modality
-
-NV-CC-Img-Text-Dataset  <br>
-** Data Modality <br>
-* Image <br>
-** Image Training Data Size <br>
-* 1 Million to 1 Billion Images <br>
-** Data Collection Method by dataset <br>
-* Automated <br>
-** Labeling Method by dataset <br>
-* Not Applicable (no labels are needed) <br>
+**NV-CC-Img-Text-Dataset**
+
+**Data Modality:** Image <br>
+**Image Training Data Size:** 1 Million to 1 Billion Images <br>
+**Data Collection Method by dataset:** Automated <br>
+**Labeling Method by dataset:** Not Applicable (no labels are needed) <br>
 **Properties:** 700 Million Images <br>
 
 ## Evaluation Datasets
 
-ImageNet <br>
-** Link <br>
-* [ImageNet](https://www.image-net.org/) <br>
-** Data Collection <br>
-* Automated  <br>
-** Labeling Method <br>
-* Human  <br>
-** Training Images <br>
-* 1,281,167 <br>
-** Validation Images <br>
-* 50,000 <br>
-** Test Images <br>
-* 100,000
+**ImageNet**
+
+**Link:** [ImageNet](https://www.image-net.org/) <br>
+**Data Collection:** Automated <br>
+**Labeling Method:** Human <br>
+**Training Images:** 1,281,167 <br>
+**Validation Images:** 50,000 <br>
+**Test Images:** 100,000 <br>
 
 To perform the semantic segmentation evaluation, we use training sets from ADE20K and PascalVOC to train a linear layer, and subsequently performed evaluations on the validation set.
 See below for further details:
 
-ADE20k <br>
-** Link <br>
-* [ADE20K](https://ade20k.csail.mit.edu/) <br>
-** Data Collection <br>
-* Human  <br>
-** Labeling Method <br>
-* Human  <br>
-** Training Images <br>
-* 25,574 <br>
-** Validation Images <br>
-* 2,000 <br>
-
-Pascal VOC <br>
-** Link <br>
-* [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) <br>
-** Data Collection <br>
-* Human  <br>
-** Labeling Method <br>
-* Human  <br>
-** Training Images <br>
-* 1,464 <br>
-** Validation Images <br>
-* 1,449 <br>
+**ADE20k**
+
+**Link:** [ADE20K](https://ade20k.csail.mit.edu/) <br>
+**Data Collection:** Human <br>
+**Labeling Method:** Human <br>
+**Training Images:** 25,574 <br>
+**Validation Images:** 2,000 <br>
+
+**Pascal VOC**
+
+**Link:** [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) <br>
+**Data Collection:** Human <br>
+**Labeling Method:** Human <br>
+**Training Images:** 1,464 <br>
+**Validation Images:** 1,449 <br>
 
 | Benchmark | C-RADIOv3-B | C-RADIOv3-L | C-RADIOv4-SO400M | C-RADIOv3-H | C-RADIOv4-H |
 |-----------|-------------|-------------|------------------|-------------|-------------|
@@ -273,4 +255,4 @@ Field                                               |  Response
 Model Application Field(s):                               |  Generation of visual embeddings
 Describe the life critical impact (if present).   |  Not Applicable
 Use Case Restrictions:                              |  Abide by NVIDIA Open Model License Agreement
-Model and dataset restrictions:            |  The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.
+Model and dataset restrictions:            |  The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.