update

.idea/Video-Bench.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 3.8 (videomae)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/deployment.xml

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="PublishConfigData" remoteFilesAllowedToDisappearOnAutoupload="false">
+    <serverData>
+      <paths name="[email protected]:36000 password">
+        <serverdata>
+          <mappings>
+            <mapping local="$PROJECT_DIR$" web="/" />
+          </mappings>
+        </serverdata>
+      </paths>
+      <paths name="[email protected]:36000 password (1)">
+        <serverdata>
+          <mappings>
+            <mapping local="$PROJECT_DIR$" web="/" />
+          </mappings>
+        </serverdata>
+      </paths>
+      <paths name="[email protected]:22 password">
+        <serverdata>
+          <mappings>
+            <mapping local="$PROJECT_DIR$" web="/" />
+          </mappings>
+        </serverdata>
+      </paths>
+      <paths name="[email protected]:22 password (1)">
+        <serverdata>
+          <mappings>
+            <mapping local="$PROJECT_DIR$" web="/" />
+          </mappings>
+        </serverdata>
+      </paths>
+    </serverData>
+  </component>
+</project>

.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 3.8 (videomae)" 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/Video-Bench.iml" filepath="$PROJECT_DIR$/.idea/Video-Bench.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="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="5983f0f5-7cc8-4a1b-b6b8-29b6de24d9b1" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="MarkdownSettingsMigration">
+    <option name="stateVersion" value="1" />
+  </component>
+  <component name="ProjectId" id="2YvCPBFCmJYfrrZhilKxOxZjgWB" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.OpenProjectViewOnStart": "true",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "WebServerToolWindowFactoryState": "true",
+    "last_opened_file_path": "D:/up_hf_space/Video-Bench/file",
+    "settings.editor.selected.configurable": "com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable"
+  }
+}]]></component>
+  <component name="RecentsManager">
+    <key name="CopyFile.RECENT_KEYS">
+      <recent name="D:\up_hf_space\Video-Bench\file" />
+    </key>
+  </component>
+  <component name="RunManager">
+    <configuration name="app" type="PythonConfigurationType" factoryName="Python" temporary="true" nameIsGenerated="true">
+      <module name="Video-Bench" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/app.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+    <recent_temporary>
+      <list>
+        <item itemvalue="Python.app" />
+      </list>
+    </recent_temporary>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="5983f0f5-7cc8-4a1b-b6b8-29b6de24d9b1" name="Changes" comment="" />
+      <created>1701396639759</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1701396639759</updated>
+      <workItem from="1701396641392" duration="695000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+  <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/Video_Bench$app.coverage" NAME="app Coverage Results" MODIFIED="1701397312132" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+  </component>
+</project>

app.py

@@ -9,6 +9,7 @@ import tempfile
 
 from constants import *
 from src.auto_leaderboard.model_metadata_type import ModelType
+from src.compute import compute_scores
 
 global data_component, filter_component
 
@@ -26,7 +27,8 @@ def add_new_eval(
     if input_file is None:
         return "Error! Empty file!"
     else:
-        input_data = input_file.decode("utf-8").split('\n')[1].split(',')
+        input_file = compute_scores(input_file)
+        input_data = input_file[1]
         input_data = [float(i) for i in input_data]
 
         csv_data = pd.read_csv(CSV_DIR)

file/result.csv

@@ -7,4 +7,5 @@ Random,28.45459441,25.84861538,24.47045673,35.04471112,0.3458,0.26224,0.265,0.22
 [Valley-7B](https://github.com/RupertLuo/Valley),33.95521521,28.38772829,29.20933333,44.268584,0.381,0.32032,0.2802802,0.3141,0.2905,0.203448,0.111108278,0.237,0.32587,0.31341,0.41666,0.5653846,0.333
 [mPLUG-owl-7B](https://github.com/X-PLUG/mPLUG-Owl),33.14659856,33.16526701,26.39762867,39.8769,0.41470735,0.4245,0.363,0.31656,0.2705,0.2275862,0.277777611,0.2395,0.3017,0.25072886,0.333333,0.510256,0.32
 [Video-LLaMA-7B](https://github.com/DAMO-NLP-SG/Video-LLaMA),32.83174044,32.48401966,27.79906667,38.212135,0.3985,0.4115,0.3405,0.312766,0.289,0.275862,0.166666556,0.2475,0.324082,0.26239,0.30555555,0.4910256,0.3115
-[Chat-UniVi-7B](https://github.com/PKU-YuanGroup/Chat-UniVi),35.31147004,37.87,27.43,40.64,0.49,0.486,0.4165,0.413,0.29,0.2827,0.166666649,0.2305,0.3357,0.2566,0.3889,0.5308,0.2907
+[Chat-UniVi-7B](https://github.com/PKU-YuanGroup/Chat-UniVi),35.31147004,37.87,27.43,40.64,0.49,0.486,0.4165,0.413,0.29,0.2827,0.166666649,0.2305,0.3357,0.2566,0.3889,0.5308,0.2907
+[1](1),35.701846153846155,32.89153846153847,32.04,42.174,37.97,35.14,37.97,35.53,31.58,27.27,16.67,34.21,31.65,30.26,33.33,53.33,35.44

file/sample_to_upload.csv

@@ -1,2 +0,0 @@
-Avg. All,Avg. Video-Exclusive,Avg. Prior-Knowledge QA,Avg. Decision-Making,ActivityNet,MSVD,MSRVTT,TGIF,Youcook2,Ucfcrime,MOT,TVQA,MV,NBA,Driving-exam,Driving-decision-making,SQA3D
-40,2,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1

src/compute.py

@@ -0,0 +1,119 @@
+import json
+import os
+import glob
+import argparse
+import csv
+
+
+def chatgpt_json(merge_file):
+    # chat results
+    merge_data = merge_file.decode("utf-8")
+    merge_data = eval(merge_data)
+    correct_answer_file = 'file/ANSWER.json'
+    with open(correct_answer_file, 'r', encoding='utf-8') as f:
+        correct_answer_data = json.load(f)
+
+    dataset_scores_dict = {}
+    for dataset_name, item in merge_data.items():
+
+        total_nums = len(item)
+        correct = 0
+        # assert len(item) >= len(correct_answer_data[dataset_name]), f'Video-Bench-Input.json---{dataset_name}---is incomplete!'
+        for id, sub_item in item.items():
+            if sub_item['output_chatgpt_choice'] == correct_answer_data[dataset_name][id]['answer']:
+                correct += 1
+
+        dataset_scores_dict[dataset_name] = round(correct / total_nums * 100, 2)
+    return dataset_scores_dict
+
+
+def compute_scores(merge_file):
+    dataset_score_dict = chatgpt_json(merge_file)
+    dataset_weight = {
+        1:
+            {
+                "ActivityNet": 1,
+                "MSVD": 1,
+                "MSRVTT": 1,
+                "TGIF": 1,
+                "Youcook2": 1,
+                "Ucfcrime": 1,
+                "MOT": 0.5,
+            },
+
+        2:
+            {
+                "TVQA": 1,
+                "MV": 1,
+                "NBA": 1,
+            },
+
+        3:
+            {
+                "Driving-exam": 0.5,
+                "Driving-decision-making": 1,
+                "SQA3D": 1,
+            }
+
+    }
+
+    # Video-exclusive Understanding score
+    exclusive_understanding_weight = dataset_weight[1]
+    weights_sum = sum(exclusive_understanding_weight.values())
+    exclusive_understanding_score = 0
+    # import ipdb; ipdb.set_trace()
+    for dataset_name, weight in exclusive_understanding_weight.items():
+        exclusive_understanding_score += weight * dataset_score_dict[dataset_name] / weights_sum
+
+    # Prior Knowledge-based Question-answer
+    prior_QA_weight = dataset_weight[2]
+    weights_sum = sum(prior_QA_weight.values())
+    prior_QA_score = 0
+    for dataset_name, weight in prior_QA_weight.items():
+        prior_QA_score += weight * dataset_score_dict[dataset_name] / weights_sum
+
+    # Comprehension and Decision-making
+    com_and_dec_QA_weight = dataset_weight[3]
+    weights_sum = sum(com_and_dec_QA_weight.values())
+    com_and_dec_QA_score = 0
+    for dataset_name, weight in com_and_dec_QA_weight.items():
+        com_and_dec_QA_score += weight * dataset_score_dict[dataset_name] / weights_sum
+
+    dataset_score_dict['Exclusive_understanding'] = exclusive_understanding_score
+    dataset_score_dict['Prior_Knowledge'] = prior_QA_score
+    dataset_score_dict['Comprehension_and_Decision-making'] = com_and_dec_QA_score
+
+    # final score
+    final_score = sum([exclusive_understanding_score, prior_QA_score, com_and_dec_QA_score]) / 3
+    dataset_score_dict['final_score'] = final_score
+
+    # print(dataset_score_dict)
+    # with open(args.score_output_file, 'w', encoding='utf-8') as f:
+    #   json.dump(dataset_score_dict, f, indent=2)
+    # print(f'{args.score_output_file} is saved!')
+    # ========================
+    data = [
+
+        ["Avg. All", "Avg. Video-Exclusive", "Avg. Prior-Knowledge QA", "Avg. Decision-Making",
+         "ActivityNet", "MSVD", "MSRVTT", "TGIF", "Youcook2", "Ucfcrime",
+         "MOT", "TVQA", "MV", "NBA", "Driving-exam", "Driving-decision-making", "SQA3D"],
+
+        [final_score, exclusive_understanding_score, prior_QA_score, com_and_dec_QA_score,
+         dataset_score_dict['ActivityNet'],
+         dataset_score_dict["MSVD"],
+         dataset_score_dict['MSRVTT'],
+         dataset_score_dict['TGIF'],
+         dataset_score_dict['Youcook2'],
+         dataset_score_dict['Ucfcrime'],
+         dataset_score_dict['MOT'],
+         dataset_score_dict['TVQA'],
+         dataset_score_dict['MV'],
+         dataset_score_dict['NBA'],
+         dataset_score_dict['Driving-exam'],
+         dataset_score_dict['Driving-decision-making'],
+         dataset_score_dict['SQA3D'],
+         ],
+    ]
+
+    return data
+