first commit

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,16 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="3">
+            <item index="0" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="1" class="java.lang.String" itemvalue="CLIP" />
+            <item index="2" class="java.lang.String" itemvalue="transformers" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (venv) (3)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/whoops-explorer-full.iml" filepath="$PROJECT_DIR$/.idea/whoops-explorer-full.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.idea/whoops-explorer-full.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.9 (venv) (3)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

README.md

@@ -1,10 +1,10 @@
 ---
-title: Whoops Explorer Full
-emoji: 📊
-colorFrom: green
-colorTo: yellow
+title: WHOOPS! Explorer
+emoji: 🔥
+colorFrom: purple
+colorTo: blue
 sdk: gradio
-sdk_version: 3.23.0
+sdk_version: 3.21.0
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,107 @@
+import math
+
+from datasets import load_dataset
+import gradio as gr
+
+whoops = load_dataset("nlphuji/whoops")['test']
+# print(f"Loaded WHOOPS!, first example:")
+# print(whoops[0])
+dataset_size = len(whoops)
+
+IMAGE = 'image'
+IMAGE_DESIGNER = 'image_designer'
+DESIGNER_EXPLANATION = 'designer_explanation'
+CROWD_CAPTIONS = 'crowd_captions'
+CROWD_EXPLANATIONS = 'crowd_explanations'
+CROWD_UNDERSPECIFIED_CAPTIONS = 'crowd_underspecified_captions'
+QA = 'question_answering_pairs'
+IMAGE_ID = 'image_id'
+SELECTED_CAPTION = 'selected_caption'
+COMMONSENSE_CATEGORY = 'commonsense_category'
+left_side_columns = [IMAGE]
+right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns]
+enumerate_cols = [CROWD_CAPTIONS, CROWD_EXPLANATIONS, CROWD_UNDERSPECIFIED_CAPTIONS]
+emoji_to_label = {IMAGE_DESIGNER: '🎨, 🧑‍🎨, 💻', DESIGNER_EXPLANATION: '💡, 🤔, 🧑‍🎨',
+                  CROWD_CAPTIONS: '👥, 💬, 📝', CROWD_EXPLANATIONS: '👥, 💡, 🤔', CROWD_UNDERSPECIFIED_CAPTIONS: '👥, 💬, 👎',
+                  QA: '❓, 🤔, 💡', IMAGE_ID: '🔍, 📄, 💾', COMMONSENSE_CATEGORY: '🤔, 📚, 💡', SELECTED_CAPTION: '📝, 👌, 💬'}
+# batch_size = 16
+batch_size = 8
+target_size = (1024, 1024)
+
+
+def func(index):
+    start_index = index * batch_size
+    end_index = start_index + batch_size
+    all_examples = [whoops[index] for index in list(range(start_index, end_index))]
+    values_lst = []
+    for example_idx, example in enumerate(all_examples):
+        values = get_instance_values(example)
+        values_lst += values
+    return values_lst
+
+
+def get_instance_values(example):
+    values = []
+    for k in left_side_columns + right_side_columns:
+        if k == IMAGE:
+            value = example["image"].resize(target_size)
+        elif k in enumerate_cols:
+            value = list_to_string(example[k])
+        elif k == QA:
+            qa_list = [f"Q: {x[0]} A: {x[1]}" for x in example[k]]
+            value = list_to_string(qa_list)
+        else:
+            value = example[k]
+        values.append(value)
+    return values
+def list_to_string(lst):
+    return '\n'.join(['{}. {}'.format(i+1, item) for i, item in enumerate(lst)])
+
+demo = gr.Blocks()
+
+
+def get_col():
+    instance_values = get_instance_values(example)
+    with gr.Column():
+        inputs_left = []
+        assert len(left_side_columns) == len(
+            instance_values[:len(left_side_columns)])  # excluding the image & designer
+        for key, value in zip(left_side_columns, instance_values[:len(left_side_columns)]):
+            if key == IMAGE:
+                img_resized = example["image"].resize(target_size)
+                input_k = gr.Image(value=img_resized, label=example['commonsense_category'])
+            else:
+                label = key.capitalize().replace("_", " ")
+                input_k = gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+            inputs_left.append(input_k)
+        with gr.Accordion("Click for details", open=False):
+            text_inputs_right = []
+            assert len(right_side_columns) == len(
+                instance_values[len(left_side_columns):])  # excluding the image & designer
+            for key, value in zip(right_side_columns, instance_values[len(left_side_columns):]):
+                label = key.capitalize().replace("_", " ")
+                text_input_k = gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+                text_inputs_right.append(text_input_k)
+    return inputs_left, text_inputs_right
+
+
+with demo:
+    gr.Markdown("# Slide to iterate WHOOPS!")
+
+    with gr.Column():
+        num_batches = math.ceil(dataset_size / batch_size)
+        slider = gr.Slider(minimum=0, maximum=num_batches, step=1, label=f'Page (out of {num_batches})')
+        with gr.Row():
+            index = slider.value
+            start_index = 0 * batch_size
+            end_index = start_index + batch_size
+            all_examples = [whoops[index] for index in list(range(start_index, end_index))]
+            all_inputs_left_right = []
+            for example_idx, example in enumerate(all_examples):
+                inputs_left, text_inputs_right = get_col()
+                inputs_left_right = inputs_left + text_inputs_right
+                all_inputs_left_right += inputs_left_right
+
+    slider.change(func, inputs=[slider], outputs=all_inputs_left_right)
+
+demo.launch()

app_grid.py

@@ -0,0 +1,88 @@
+import random
+
+import gradio as gr
+from datasets import load_dataset
+
+whoops = load_dataset("nlphuji/whoops")['test']
+whoops = whoops.shuffle()
+
+print(f"Loaded WMTIS, first example:")
+print(whoops[0])
+dataset_size = len(whoops)
+print(f"dataset_size: {dataset_size}")
+
+IMAGE = 'image'
+IMAGE_DESIGNER = 'image_designer'
+DESIGNER_EXPLANATION = 'designer_explanation'
+CROWD_CAPTIONS = 'crowd_captions'
+CROWD_EXPLANATIONS = 'crowd_explanations'
+CROWD_UNDERSPECIFIED_CAPTIONS = 'crowd_underspecified_captions'
+SELECTED_CAPTION = 'selected_caption'
+COMMONSENSE_CATEGORY = 'commonsense_category'
+QA = 'question_answering_pairs'
+IMAGE_ID = 'image_id'
+left_side_columns = [IMAGE]
+right_side_columns = [x for x in whoops.features.keys() if x not in left_side_columns and x not in [QA]]
+enumerate_cols = [CROWD_CAPTIONS, CROWD_EXPLANATIONS, CROWD_UNDERSPECIFIED_CAPTIONS]
+emoji_to_label = {IMAGE_DESIGNER: '🎨, 🧑‍🎨, 💻', DESIGNER_EXPLANATION: '💡, 🤔, 🧑‍🎨',
+                  CROWD_CAPTIONS: '👥, 💬, 📝', CROWD_EXPLANATIONS: '👥, 💡, 🤔', CROWD_UNDERSPECIFIED_CAPTIONS: '👥, 💬, 👎',
+                  QA: '❓, 🤔, 💡', IMAGE_ID: '🔍, 📄, 💾', COMMONSENSE_CATEGORY: '🤔, 📚, 💡', SELECTED_CAPTION: '📝, 👌, 💬'}
+target_size = (1024, 1024)
+
+columns_number = 3
+rows_number = 10
+
+def func(index):
+    example = whoops[index]
+    values = get_instance_values(example)
+    return values
+
+
+def get_instance_values(example):
+    values = []
+    for k in left_side_columns + right_side_columns:
+        if k in enumerate_cols:
+            value = list_to_string(example[k])
+        elif k == QA:
+            qa_list = [f"Q: {x[0]} A: {x[1]}" for x in example[k]]
+            value = list_to_string(qa_list)
+        else:
+            value = example[k]
+        values.append(value)
+    return values
+
+
+def list_to_string(lst):
+    return '\n'.join(['{}. {}'.format(i + 1, item) for i, item in enumerate(lst)])
+
+def create_image_accordion_block(index):
+    example = whoops[index]
+    instance_values = get_instance_values(example)
+    assert len(left_side_columns) == len(
+        instance_values[:len(left_side_columns)])  # excluding the image & designer
+    for key, value in zip(left_side_columns, instance_values[:len(left_side_columns)]):
+        if key == IMAGE:
+            img = whoops[index]["image"]
+            img_resized = img.resize(target_size)
+            gr.Image(value=img_resized, label=whoops[index]['commonsense_category'])
+        else:
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+    with gr.Accordion("Click for details", open=False):
+        assert len(right_side_columns) == len(
+            instance_values[len(left_side_columns):])  # excluding the image & designer
+        for key, value in zip(right_side_columns, instance_values[len(left_side_columns):]):
+            label = key.capitalize().replace("_", " ")
+            gr.Textbox(value=value, label=f"{label} {emoji_to_label[key]}")
+
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(f"# Slide to iterate WHOOPS!")
+    for row_num in range(0, rows_number):
+        with gr.Row():
+            for col_num in range(0, columns_number):
+                with gr.Column():
+                    index = random.choice(range(0, dataset_size))
+                    create_image_accordion_block(index)
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+datasets
+gradio==3.21.0