From af42043e6f6649f0c88a3db97e8a65dc7b2f9a66 Mon Sep 17 00:00:00 2001
From: Jared Smith <jrssmith@ucdavis.edu>
Date: Sat, 30 May 2026 16:29:18 -0700
Subject: [PATCH] updating datasets

---
 src/components/DatasetMetadataModal.tsx | 20 +++++++++
 static/data/hf_datasets.json            | 60 ++++++++++++-------------
 2 files changed, 49 insertions(+), 31 deletions(-)

diff --git a/src/components/DatasetMetadataModal.tsx b/src/components/DatasetMetadataModal.tsx
index aed60b9..95033c4 100644
--- a/src/components/DatasetMetadataModal.tsx
+++ b/src/components/DatasetMetadataModal.tsx
@@ -24,6 +24,24 @@ function formatArray(value: number[] | null) {
 	return `[${value.map((entry) => entry.toFixed(3)).join(', ')}]`;
 }
 
+function formatBytesDecimal(bytes: number | null | undefined) {
+	if (bytes == null) return 'Unknown';
+	if (!Number.isFinite(bytes) || bytes < 0) return 'Unknown';
+
+	const units = ['B', 'kB', 'MB', 'GB', 'TB'];
+	let value = bytes;
+	let unitIndex = 0;
+
+	while (value >= 1000 && unitIndex < units.length - 1) {
+		value /= 1000;
+		unitIndex += 1;
+	}
+
+	const formatted = value >= 100 ? Math.round(value).toString() : value.toFixed(1);
+	const trimmed = formatted.endsWith('.0') ? formatted.slice(0, -2) : formatted;
+	return `${trimmed} ${units[unitIndex]}`;
+}
+
 function hasExampleImage(url: string | null): url is string {
 	return Boolean(url && url.startsWith('http'));
 }
@@ -82,6 +100,7 @@ export function DatasetMetadataModal({
 		['Input format', formatValue(dataset.input_data_format)],
 		['Annotation format', formatValue(dataset.annotation_format)],
 		['Number of images', formatImageCount(dataset.num_images)],
+		['Size', formatBytesDecimal(dataset.zip_size_bytes)],
 	] as const;
 	const loader = formatLoaderInstructions(dataset);
 
@@ -121,6 +140,7 @@ export function DatasetMetadataModal({
 							<section className={styles.secondarySection}>
 								<h3 className={styles.sectionTitle}>Classes</h3>
 								<p className={styles.bodyText}>{dataset.classes}</p>
+
 							</section>
 						)}
 						{(dataset.stats_mean || dataset.stats_std) && (
diff --git a/static/data/hf_datasets.json b/static/data/hf_datasets.json
index 0a151fb..f060d5f 100644
--- a/static/data/hf_datasets.json
+++ b/static/data/hf_datasets.json
@@ -1,63 +1,61 @@
 [
   {
-    "name": "HF Demo Dataset",
-    "machine_learning_task": "classification",
-    "agricultural_task": "crop_health_monitoring",
+    "name": "wGrapeUNIPD-DL_white_grape_bunch_detection",
+    "machine_learning_task": "object_detection",
+    "agricultural_task": "",
     "location": [
-      "France",
-      "Spain",
       "Italy"
     ],
-    "environment": "lab",
-    "augmented_num_images": 480,
+    "environment": "real",
     "crop_types": [
-      "tomato",
-      "pepper",
-      "lettuce"
+      "grapes"
     ],
     "sensor_modality": "rgb",
     "real_or_synthetic": "real",
-    "platform": "huggingface",
+    "platform": "ground",
     "input_data_format": "image_folder",
-    "annotation_format": "folder_names",
-    "num_images": 0,
-    "documentation": "https://huggingface.co/datasets/your-org/hf-demo-dataset",
-    "classes": [
-      "healthy",
-      "diseased"
-    ],
+    "annotation_format": "coco_json",
+    "num_images": 217,
+    "documentation": "wGrapeUNIPD-DL_white_grape_bunch_detection",
     "stats_mean": null,
     "stats_std": null,
     "examples_image_url": null,
-    "license": null,
+    "license": "cc-by-4.0",
     "citation": null,
     "parent_dataset": null,
-    "zip_size_bytes": null,
+    "zip_size_bytes": 1410000000,
     "source": "huggingface"
   },
   {
-    "name": "HF Demo Dataset 2",
-    "machine_learning_task": "detection",
-    "agricultural_task": "crop_health_monitoring",
-    "location": "global",
+    "name": "Project-AgML/Strawberry-DS_strawberry_detection",
+    "machine_learning_task": "object_detection",
+    "agricultural_task": "crop_maturity_monitoring",
+    "location": "Egypt",
     "environment": "field",
     "crop_types": [
-      "grapes"
+      "strawberry"
     ],
     "sensor_modality": "rgb",
-    "platform": "huggingface",
+    "platform": "ground",
     "input_data_format": "image_folder",
-    "annotation_format": "hf",
-    "num_images": 20,
-    "documentation": "https://huggingface.co/datasets/your-org/hf-demo-dataset",
-    "classes": "",
+    "annotation_format": "coco_json",
+    "num_images": 247,
+    "documentation": "https://www.sciencedirect.com/science/article/pii/S2352340923002846",
+    "classes": [
+      "Green",
+      "White",
+      "Early-Turning",
+      "Turning",
+      "Late-Turning",
+      "Red"
+    ],
     "stats_mean": null,
     "stats_std": null,
     "examples_image_url": null,
     "license": null,
     "citation": null,
     "parent_dataset": null,
-    "zip_size_bytes": null,
+    "zip_size_bytes": 293000000,
     "source": "huggingface"
   }
 ]
\ No newline at end of file