{% extends "base.html" %} {% block content %}

Model Comparison Report

Comparing runs:

Baseline: {{ data.summary.baseline_id }}

Current: {{ data.summary.run_id }}

Status: {{ data.summary.status }}

Executive Summary

Overall Changes

{{ data.changes.improvements }} Improvements 🟢
{{ data.changes.regressions }} Regressions 🔴
{{ data.changes.unchanged }} Unchanged ⚪

Status

{{ data.summary.status }}
{% for field_name, field in data.fields.items() %}

{{ field_name }}

Improvements: {{ field.metrics.improvements }}

Unchanged: {{ field.metrics.unchanged }}

Regressions: {{ field.metrics.regressions }}

{% if data.plots and field_name in data.plots %}
{{ data.plots[field_name] | safe }}
{% endif %}

Samples

{% for sample in field.samples %} {% endfor %}
Sample Input Baseline Current Expected Status
{{ sample.index }} {{ sample.input }} {{ sample.baseline }} {{ sample.current }} {{ sample.expected }} {% if sample.status == 'improved' %} 🟢 {% elif sample.status == 'regressed' %} 🔴 {% else %} ⚪ {% endif %}
{% for sample in field.samples if sample.status == 'improved' %} {% endfor %}
Sample Input Baseline Current Expected
{{ sample.index }} {{ sample.input }} {{ sample.baseline }} {{ sample.current }} {{ sample.expected }}
{% for sample in field.samples if sample.status == 'regressed' %} {% endfor %}
Sample Input Baseline Current Expected
{{ sample.index }} {{ sample.input }} {{ sample.baseline }} {{ sample.current }} {{ sample.expected }}
{% endfor %} {% endblock %}