Upload processor

README.md

@@ -1,11 +1,6 @@
 ---
 license: mit
 library_name: transformers
-widget:
-- src: >-
-    https://fema-cap-imagery.s3.amazonaws.com/Images/CAP_-_Flooding_Spring_2023/Source/IAWG_23-B-5061/A0005/D75_0793_DxO_PL6_P.jpg
-- example_title: Example classification of flooded scene
-pipeline_tag: image-classification
 tags:
 - LADI
 - Aerial Imagery
@@ -13,6 +8,10 @@ tags:
 - Emergency Management
 datasets:
 - MITLL/LADI-v2-dataset
+widget:
+- src: https://fema-cap-imagery.s3.amazonaws.com/Images/CAP_-_Flooding_Spring_2023/Source/IAWG_23-B-5061/A0005/D75_0793_DxO_PL6_P.jpg
+- example_title: Example classification of flooded scene
+pipeline_tag: image-classification
 ---
 # Model Card for MITLL/LADI-v2-classifier-large-reference
 LADI-v2-classifier-large-reference is based on [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) and fine-tuned on the [MITLL/LADI-v2-dataset](https://huggingface.co/datasets/MITLL/LADI-v2-dataset). LADI-v2-classifier is trained to identify labels of interest to disaster response managers from aerial images.

preprocessor_config.json

@@ -1,4 +1,18 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,