R
ReflectIris
← Back to Training Runs

exp_192_cnn_deform

Stoppedml-02

Started

28.8 dB
Train PSNR
Momentum
Accelerating
Strong avg PSNR gain: +5.6 dB / 5K steps
PSNR Δ5K: +5.61 dB
Gaussian growth: +179,982
Loss trend: Decreasing
Visual Analysis
STALL
Visual quality plateaued (SSIM range 0.0074 over last 3 checkpoints) (46 checkpoints analyzed)
SSIM
0.888
Blur Ratio
0.403
Edge Preservation
0.529
Expression Fidelity
1.000
Progress
0%
8,300 / 0 steps
Gaussians
200.0K
Growing
Speed
Duration
Densify Window
0K–0K
0 events
Batch Size
1
Step 8,3000 total
densify

Training Metrics

Train + Val PSNR (dB) — Higher is Better

Training Loss — Lower is Better

Gaussian Count — Grows During Densification

Training Speed (iterations/sec) & GPU Memory (GB)

Visual Progress

Step 90Kml-02
·
Step 88Kml-02
·
Step 86Kml-02
·
Step 84Kml-02
·
Step 82Kml-02
·
Step 80Kml-02
·
Step 78Kml-02
·
Step 76Kml-02
·
Step 74Kml-02
·
Step 72Kml-02
·
Step 70Kml-02
·
Step 68Kml-02
·
Step 66Kml-02
·
Step 64Kml-02
·
Step 62Kml-02
·
Step 60Kml-02
·
Step 58Kml-02
·
Step 56Kml-02
·
Step 54Kml-02
·
Step 52Kml-02
·
Step 50Kml-02
·
Step 48Kml-02
·
Step 46Kml-02
·
Step 44Kml-02
·
Step 42Kml-02
·
Step 40Kml-02
·
Step 38Kml-02
·
Step 36Kml-02
·
Step 34Kml-02
·
Step 32Kml-02
·
Step 30Kml-02
·
Step 28Kml-02
·
Step 26Kml-02
·
Step 24Kml-02
·
Step 22Kml-02
·
Step 20Kml-02
·
Step 18Kml-02
·
Step 16Kml-02
·
Step 14Kml-02
·
Step 12Kml-02
·
Step 10Kml-02
·
Step 8Kml-02
·
Step 6Kml-02
·
Step 4Kml-02
·
Step 2Kml-02
·
Step 1ml-02
·
Full Configuration
{}