Spaces:
Runtime error
Runtime error
File size: 10,648 Bytes
c3efd49 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 |
"""Visualization tools for training monitoring."""
import matplotlib.pyplot as plt
import numpy as np
from typing import Dict, List, Optional, Any
from pathlib import Path
import logging
logger = logging.getLogger(__name__)
class Visualizer:
"""
Creates visualizations for training metrics.
Supports TensorBoard integration and static plots.
"""
def __init__(self, output_dir: str = "visualizations"):
"""
Initialize visualizer.
Args:
output_dir: Directory to save visualizations
"""
self.output_dir = Path(output_dir)
self.output_dir.mkdir(parents=True, exist_ok=True)
# Try to import tensorboard
self.tensorboard_available = False
try:
from torch.utils.tensorboard import SummaryWriter
self.SummaryWriter = SummaryWriter
self.tensorboard_available = True
logger.info("TensorBoard available")
except ImportError:
logger.warning("TensorBoard not available")
self.writer = None
logger.info(f"Visualizer initialized: output_dir={output_dir}")
def initialize_tensorboard(self, log_dir: Optional[str] = None) -> None:
"""
Initialize TensorBoard writer.
Args:
log_dir: Optional TensorBoard log directory
"""
if not self.tensorboard_available:
logger.warning("TensorBoard not available, skipping initialization")
return
if log_dir is None:
log_dir = str(self.output_dir / "tensorboard")
self.writer = self.SummaryWriter(log_dir)
logger.info(f"TensorBoard initialized: {log_dir}")
def log_scalar_to_tensorboard(
self,
tag: str,
value: float,
step: int
) -> None:
"""
Log scalar value to TensorBoard.
Args:
tag: Metric name
value: Metric value
step: Step number
"""
if self.writer is not None:
self.writer.add_scalar(tag, value, step)
def plot_training_curve(
self,
metrics: Dict[str, List[Dict[str, Any]]],
metric_name: str,
title: Optional[str] = None,
filename: Optional[str] = None
) -> str:
"""
Plot training curve for a metric.
Args:
metrics: Dictionary of metrics
metric_name: Name of metric to plot
title: Optional plot title
filename: Optional output filename
Returns:
Path to saved plot
"""
if metric_name not in metrics:
raise ValueError(f"Metric '{metric_name}' not found")
data = metrics[metric_name]
steps = [entry['step'] for entry in data]
values = [entry['value'] for entry in data]
plt.figure(figsize=(10, 6))
plt.plot(steps, values, linewidth=2)
plt.xlabel('Step')
plt.ylabel(metric_name.replace('_', ' ').title())
plt.title(title or f'{metric_name.replace("_", " ").title()} Over Time')
plt.grid(True, alpha=0.3)
if filename is None:
filename = f"{metric_name}_curve.png"
output_path = self.output_dir / filename
plt.savefig(output_path, dpi=150, bbox_inches='tight')
plt.close()
logger.info(f"Training curve saved: {output_path}")
return str(output_path)
def plot_multiple_metrics(
self,
metrics: Dict[str, List[Dict[str, Any]]],
metric_names: List[str],
title: Optional[str] = None,
filename: Optional[str] = None
) -> str:
"""
Plot multiple metrics on the same figure.
Args:
metrics: Dictionary of metrics
metric_names: List of metric names to plot
title: Optional plot title
filename: Optional output filename
Returns:
Path to saved plot
"""
plt.figure(figsize=(12, 6))
for metric_name in metric_names:
if metric_name in metrics:
data = metrics[metric_name]
steps = [entry['step'] for entry in data]
values = [entry['value'] for entry in data]
plt.plot(steps, values, label=metric_name, linewidth=2)
plt.xlabel('Step')
plt.ylabel('Value')
plt.title(title or 'Training Metrics')
plt.legend()
plt.grid(True, alpha=0.3)
if filename is None:
filename = "multiple_metrics.png"
output_path = self.output_dir / filename
plt.savefig(output_path, dpi=150, bbox_inches='tight')
plt.close()
logger.info(f"Multi-metric plot saved: {output_path}")
return str(output_path)
def plot_training_curves(
self,
metrics: Dict[str, List[Dict[str, Any]]],
title: str = "Training Progress",
filename: Optional[str] = None
) -> str:
"""
Plot comprehensive training curves with subplots.
Args:
metrics: Dictionary of all metrics
title: Main title for the figure
filename: Optional output filename
Returns:
Path to saved plot
"""
if not metrics:
logger.warning("No metrics to plot")
return ""
# Determine which metrics to plot
metric_names = list(metrics.keys())
num_metrics = len(metric_names)
if num_metrics == 0:
return ""
# Create subplots
fig, axes = plt.subplots(2, 2, figsize=(15, 10))
fig.suptitle(title, fontsize=16, fontweight='bold')
axes = axes.flatten()
# Plot up to 4 key metrics
key_metrics = ['reward', 'loss', 'total_reward', 'episode_time']
plot_idx = 0
for metric_name in key_metrics:
if metric_name in metrics and plot_idx < 4:
data = metrics[metric_name]
steps = [entry['step'] for entry in data]
values = [entry['value'] for entry in data]
ax = axes[plot_idx]
ax.plot(steps, values, linewidth=2, marker='o', markersize=4)
ax.set_xlabel('Episode')
ax.set_ylabel(metric_name.replace('_', ' ').title())
ax.set_title(f'{metric_name.replace("_", " ").title()}')
ax.grid(True, alpha=0.3)
# Add trend line
if len(steps) > 1:
z = np.polyfit(steps, values, 1)
p = np.poly1d(z)
ax.plot(steps, p(steps), "--", alpha=0.5, color='red', label='Trend')
ax.legend()
plot_idx += 1
# Hide unused subplots
for idx in range(plot_idx, 4):
axes[idx].axis('off')
plt.tight_layout()
if filename is None:
filename = f"training_curves_{len(steps)}_episodes.png"
output_path = self.output_dir / filename
plt.savefig(output_path, dpi=150, bbox_inches='tight')
plt.close()
logger.info(f"Training curves saved: {output_path}")
return str(output_path)
def plot_reward_distribution(
self,
rewards: List[float],
title: Optional[str] = None,
filename: Optional[str] = None
) -> str:
"""
Plot reward distribution histogram.
Args:
rewards: List of reward values
title: Optional plot title
filename: Optional output filename
Returns:
Path to saved plot
"""
plt.figure(figsize=(10, 6))
plt.hist(rewards, bins=30, alpha=0.7, edgecolor='black')
plt.xlabel('Reward')
plt.ylabel('Frequency')
plt.title(title or 'Reward Distribution')
plt.grid(True, alpha=0.3, axis='y')
# Add statistics
mean_reward = np.mean(rewards)
std_reward = np.std(rewards)
plt.axvline(mean_reward, color='red', linestyle='--',
label=f'Mean: {mean_reward:.3f}')
plt.axvline(mean_reward + std_reward, color='orange',
linestyle=':', alpha=0.7, label=f'±1 Std')
plt.axvline(mean_reward - std_reward, color='orange',
linestyle=':', alpha=0.7)
plt.legend()
if filename is None:
filename = "reward_distribution.png"
output_path = self.output_dir / filename
plt.savefig(output_path, dpi=150, bbox_inches='tight')
plt.close()
logger.info(f"Reward distribution saved: {output_path}")
return str(output_path)
def generate_summary_report(
self,
metrics: Dict[str, List[Dict[str, Any]]],
statistics: Dict[str, Dict[str, float]],
output_filename: str = "training_summary.txt"
) -> str:
"""
Generate text summary report.
Args:
metrics: Dictionary of metrics
statistics: Dictionary of metric statistics
output_filename: Output filename
Returns:
Path to saved report
"""
lines = []
lines.append("=" * 60)
lines.append("TRAINING SUMMARY REPORT")
lines.append("=" * 60)
lines.append("")
# Overall statistics
lines.append("METRIC STATISTICS:")
lines.append("-" * 60)
for metric_name, stats in statistics.items():
lines.append(f"\n{metric_name}:")
lines.append(f" Count: {stats['count']}")
lines.append(f" Mean: {stats['mean']:.6f}")
lines.append(f" Std: {stats['std']:.6f}")
lines.append(f" Min: {stats['min']:.6f}")
lines.append(f" Max: {stats['max']:.6f}")
lines.append("")
lines.append("=" * 60)
report_text = "\n".join(lines)
output_path = self.output_dir / output_filename
with open(output_path, 'w') as f:
f.write(report_text)
logger.info(f"Summary report saved: {output_path}")
return str(output_path)
def close(self) -> None:
"""Close TensorBoard writer if open."""
if self.writer is not None:
self.writer.close()
logger.info("TensorBoard writer closed")
|