1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
|
import os
import csv
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.metrics import (
accuracy_score,
f1_score,
classification_report,
confusion_matrix,
cohen_kappa_score,
)
from utils import CLASS_NAMES
def evaluate_model(model: nn.Module, test_loader: DataLoader, device: torch.device) -> dict:
"""Run inference on test_loader and return a dict of all metrics."""
model.eval()
all_preds, all_labels = [], []
with torch.no_grad():
for images, labels in test_loader:
images = images.to(device, non_blocking=True)
outputs = model(images)
preds = outputs.argmax(dim=1)
all_preds.extend(preds.cpu().numpy())
all_labels.extend(labels.numpy())
all_preds = np.array(all_preds)
all_labels = np.array(all_labels)
return {
'accuracy': accuracy_score(all_labels, all_preds),
'weighted_f1': f1_score(all_labels, all_preds, average='weighted', zero_division=0),
'macro_f1': f1_score(all_labels, all_preds, average='macro', zero_division=0),
'classification_report': classification_report(
all_labels, all_preds, target_names=CLASS_NAMES, zero_division=0
),
'confusion_matrix': confusion_matrix(all_labels, all_preds),
'cohen_kappa': cohen_kappa_score(all_labels, all_preds, weights='quadratic'),
}
def plot_confusion_matrix(cm: np.ndarray, save_path: str) -> None:
"""Save a seaborn confusion matrix heatmap to save_path."""
fig, ax = plt.subplots(figsize=(8, 6))
sns.heatmap(
cm, annot=True, fmt='d', cmap='Blues',
xticklabels=CLASS_NAMES, yticklabels=CLASS_NAMES,
ax=ax
)
ax.set_xlabel('Predicted')
ax.set_ylabel('True')
ax.set_title('Confusion Matrix')
plt.tight_layout()
fig.savefig(save_path, dpi=150)
plt.close(fig)
def plot_training_curves(
train_losses: list, val_losses: list, val_f1s: list, save_path: str
) -> None:
"""Save loss and F1 training curves to save_path."""
epochs = range(1, len(train_losses) + 1)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))
ax1.plot(epochs, train_losses, label='Train loss')
ax1.plot(epochs, val_losses, label='Val loss')
ax1.set_xlabel('Epoch')
ax1.set_ylabel('Loss')
ax1.set_title('Training and Validation Loss')
ax1.legend()
ax2.plot(epochs, val_f1s, label='Val macro F1', color='green')
ax2.set_xlabel('Epoch')
ax2.set_ylabel('Macro F1')
ax2.set_title('Validation Macro F1')
ax2.legend()
plt.tight_layout()
fig.savefig(save_path, dpi=150)
plt.close(fig)
def generate_summary(all_results: dict, save_dir: str) -> None:
"""Print comparison table, save as CSV, and generate bar chart."""
os.makedirs(save_dir, exist_ok=True)
rows = []
for key, r in all_results.items():
model_name, clahe_str = key.rsplit('_clahe=', 1)
rows.append({
'model': model_name,
'clahe': clahe_str,
'weighted_f1': r['weighted_f1'],
'macro_f1': r['macro_f1'],
'accuracy': r['accuracy'],
'cohen_kappa': r['cohen_kappa'],
'train_time_s': round(r['train_time'], 1),
'epochs_trained': r['epochs_trained'],
})
# Print table
header = f"{'Model':<18} {'CLAHE':<6} {'W-F1':>6} {'M-F1':>6} {'Acc':>6} {'Kappa':>6} {'Time(s)':>8} {'Epochs':>7}"
print('\n' + '=' * len(header))
print(header)
print('-' * len(header))
for row in rows:
print(
f"{row['model']:<18} {row['clahe']:<6} "
f"{row['weighted_f1']:>6.4f} {row['macro_f1']:>6.4f} "
f"{row['accuracy']:>6.4f} {row['cohen_kappa']:>6.4f} "
f"{row['train_time_s']:>8} {row['epochs_trained']:>7}"
)
print('=' * len(header))
# Save CSV
csv_path = os.path.join(save_dir, 'summary.csv')
with open(csv_path, 'w', newline='') as f:
writer = csv.DictWriter(f, fieldnames=list(rows[0].keys()))
writer.writeheader()
writer.writerows(rows)
print(f"\nSummary saved to {csv_path}")
# Comparison bar chart — show both macro and weighted F1
x_labels = [f"{r['model']}\nCLAHE={r['clahe']}" for r in rows]
w_f1_vals = [r['weighted_f1'] for r in rows]
m_f1_vals = [r['macro_f1'] for r in rows]
x = np.arange(len(x_labels))
bar_width = 0.35
fig, ax = plt.subplots(figsize=(12, 5))
bars_w = ax.bar(x - bar_width / 2, w_f1_vals, bar_width, label='Weighted F1', color='#4C72B0')
bars_m = ax.bar(x + bar_width / 2, m_f1_vals, bar_width, label='Macro F1', color='#DD8452')
ax.set_ylabel('F1-Score')
ax.set_title('F1 Comparison Across Experiments')
ax.set_xticks(x)
ax.set_xticklabels(x_labels)
ax.set_ylim(0, 1.0)
ax.legend()
for bar, val in zip(bars_w, w_f1_vals):
ax.text(bar.get_x() + bar.get_width() / 2, bar.get_height() + 0.01,
f'{val:.3f}', ha='center', va='bottom', fontsize=8)
for bar, val in zip(bars_m, m_f1_vals):
ax.text(bar.get_x() + bar.get_width() / 2, bar.get_height() + 0.01,
f'{val:.3f}', ha='center', va='bottom', fontsize=8)
plt.tight_layout()
chart_path = os.path.join(save_dir, 'comparison_chart.png')
fig.savefig(chart_path, dpi=150)
plt.close(fig)
print(f"Comparison chart saved to {chart_path}")
|
