Upload 20 files

.gitattributes

@@ -45,3 +45,18 @@ test_1426.png filter=lfs diff=lfs merge=lfs -text
 test_3104.png filter=lfs diff=lfs merge=lfs -text
 test_3105.png filter=lfs diff=lfs merge=lfs -text
 test_3111.png filter=lfs diff=lfs merge=lfs -text
+discriminator.png filter=lfs diff=lfs merge=lfs -text
+epoch_001[[:space:]](2).png filter=lfs diff=lfs merge=lfs -text
+epoch_007.png filter=lfs diff=lfs merge=lfs -text
+epoch_100.png filter=lfs diff=lfs merge=lfs -text
+ezgif-58298bca2da920.gif filter=lfs diff=lfs merge=lfs -text
+gan_architecture_combined.png filter=lfs diff=lfs merge=lfs -text
+generator.png filter=lfs diff=lfs merge=lfs -text
+test_001.png filter=lfs diff=lfs merge=lfs -text
+test_1179.png filter=lfs diff=lfs merge=lfs -text
+test_12015.png filter=lfs diff=lfs merge=lfs -text
+test_4884.png filter=lfs diff=lfs merge=lfs -text
+test_5269.png filter=lfs diff=lfs merge=lfs -text
+test_5361.png filter=lfs diff=lfs merge=lfs -text
+test_7255.png filter=lfs diff=lfs merge=lfs -text
+test_7362.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,176 @@
----
-license: mit
-datasets:
-- UserNae3/LLVIP
-metrics: null
-L1 Loss: 0.0611
-PSNR: 24.3096
-SSIM: 0.8386
-library_name: tensorflow 
-used losses : preceptual loss from vgg connv5_block4 , l1 loss,adversial loss , edge loss 
-architecture : conditional gan with more wright to l1 loss (visible image to ir)
-pipeline_tag: image-to-image
----
+# 🌙 Conditional GAN for Visible → Infrared (LLVIP)
+
+> **High-fidelity Visible-to-Infrared Translation using a Conditional GAN with Multi-Loss Optimization**
+
+---
+
+## 🧩 Overview
+
+This project implements a **Conditional Generative Adversarial Network (cGAN)** trained to translate **visible-light (RGB)** images into **infrared (IR)** representations.
+
+It leverages **multi-loss optimization** — combining perceptual, pixel, adversarial, and edge-based objectives — to generate sharp, realistic IR outputs that preserve both **scene structure** and **thermal contrast**.
+
+A higher emphasis is given to **L1 loss**, ensuring that overall brightness and object boundaries remain consistent between visible and infrared domains.
+
+---
+
+## 📁 Dataset
+
+- **Dataset:** [LLVIP Dataset](https://huggingface.co/datasets/UserNae3/LLVIP)  
+  Paired **visible (RGB)** and **infrared (IR)** images under diverse lighting and background conditions.
+
+---
+
+## 🧠 Model Architecture
+
+- **Type:** Conditional GAN (cGAN)  
+- **Direction:** *Visible → Infrared*  
+- **Framework:** TensorFlow  
+- **Pipeline Tag:** `image-to-image`  
+- **License:** MIT  
+
+### 🧱 Generator  
+- U-Net encoder–decoder with skip connections  
+- Conditioned on RGB input  
+- Output: single-channel IR image  
+
+### ⚔️ Discriminator  
+- PatchGAN (70×70 receptive field)  
+- Evaluates realism of local patches for fine detail learning  
+
+---
+
+## ⚙️ Training Configuration
+
+| Setting | Value |
+|----------|--------|
+| **Epochs** | 100 |
+| **Steps per Epoch** | 376 |
+| **Batch Size** | 4 |
+| **Optimizer** | Adam (β₁ = 0.5, β₂ = 0.999) |
+| **Learning Rate** | 2e-4 |
+| **Precision** | Mixed (FP16/32) |
+| **Hardware** | NVIDIA T4 (Kaggle GPU Runtime) |
+
+---
+
+## 💡 Multi-Loss Function Design
+
+| Loss Type | Description | Weight (λ) | Purpose |
+|------------|--------------|-------------|----------|
+| **L1 Loss** | Pixel-wise mean absolute error between generated and real IR | **100** | Ensures global brightness & shape consistency |
+| **Perceptual Loss (VGG)** | Feature loss from `conv5_block4` of pretrained VGG-19 | **10** | Captures high-level texture and semantic alignment |
+| **Adversarial Loss** | Binary cross-entropy loss from PatchGAN discriminator | **1** | Encourages realistic IR texture generation |
+| **Edge Loss** | Sobel/gradient difference between real & generated images | **5** | Enhances sharpness and edge clarity |
+
+The **total generator loss** is computed as:
+\[
+L_{G} = \lambda_{L1} L_{L1} + \lambda_{perc} L_{perc} + \lambda_{adv} L_{adv} + \lambda_{edge} L_{edge}
+\]
+
+---
+
+## 📊 Evaluation Metrics
+
+| Metric | Definition | Result |
+|---------|-------------|--------|
+| **L1 Loss** | Mean absolute difference between generated and ground truth IR | **0.0611** |
+| **PSNR (Peak Signal-to-Noise Ratio)** | Measures reconstruction quality (higher is better) | **24.3096 dB** |
+| **SSIM (Structural Similarity Index Measure)** | Perceptual similarity between generated & target images | **0.8386** |
+
+---
+## 🏗️ Model Architectures
+
+| Model | Visualization |
+|-------|---------------|
+| **Generator** | ![Generator Architecture](generator.png) |
+| **Discriminator** | ![Discriminator Architecture](discriminator.png) |
+| **Combined GAN** | ![GAN Architecture Combined](gan_architecture_combined.png) |
+
+---
+
+
+
+## 🖼️ Visual Results
+
+### 🎞️ Training Progress (Sample Evolution)
+<img src="ezgif-58298bca2da920.gif" alt="Training Progress" width="700"/>
+
+### ✨ Final Convergence Samples
+| Early Epochs (Blurry, Low Brightness) | Later Epochs (Sharper, High Contrast) |
+|--------------------------------------|---------------------------------------|
+| <img src="./epoch_007.png" width="550"/> | <img src="epoch_100.png" width="550"/> |
+
+###  Comparison: Input vs Ground Truth vs Generated
+| RGB Input-  Ground Truth IR - Predicted IR |
+
+| <img src="test_1179.png" width="750"/>
+| <img src="test_001.png" width="750"/>
+| <img src="test_4884.png" width="750"/>
+| <img src="test_5269.png" width="750"/>
+| <img src="test_5361.png" width="750"/>
+| <img src="test_7255.png" width="750"/>
+| <img src="test_7362.png" width="750"/>
+| <img src="test_12015.png" width="750"/>
+---
+
+## 📈 Loss Curves
+
+### Generator & Discriminator Loss
+<img src="./train_loss_curve.png" alt="Training Loss Curve" width="600"/>
+
+### Validation Loss per Epoch
+<img src="./val_loss_curve.png" alt="Validation Loss Curve" width="600"/>
+
+All training metrics are logged in:
+
+---
+```bash
+/
+├── logs.log
+└── loss_summary.csv
+```
+## 🧩 Observations
+
+- The model **captures IR brightness and object distinction**, but early epochs show slight blur due to L1-dominant stages.  
+- **Contrast and edge sharpness improve** after ~70 epochs as adversarial and perceptual losses gain weight.  
+- Background variations in LLVIP introduce challenges; future fine-tuning on domain-aligned subsets can further improve realism.
+
+---
+
+## 🚀 Future Work
+
+- Apply **feature matching loss** for smoother discriminator gradients  
+- Introduce **spectral normalization** for training stability  
+- Add **temporal or sequence consistency** for video IR translation  
+- Adaptive loss balancing with epoch-based dynamic weighting  
+
+---
+❤️ Acknowledgements
+
+LLVIP Dataset for paired RGB–IR samples
+
+TensorFlow and VGG-19 for perceptual feature extraction
+
+Kaggle GPU for high-performance model training
+
+## 📜 License
+
+**MIT License © 2025**  
+Author: **Sai Sumanth Appala**
+
+---
+
+## 🧾 Citation
+
+If you use this work, please cite:
+
+```bibtex
+@misc{appala2025visible2ir,
+  author = {Appala, Sai Sumanth},
+  title = {Conditional GAN for Visible-to-Infrared Translation with Multi-Loss Training},
+  year = {2025},
+  license = {MIT},
+  dataset = {UserNae3/LLVIP},
+  framework = {TensorFlow},
+}

logs.log

@@ -0,0 +1,1016 @@
+6.4s 1 0.00s - Debugger warning: It seems that frozen modules are being used, which may
+6.4s 2 0.00s - make the debugger miss breakpoints. Please pass -Xfrozen_modules=off
+6.4s 3 0.00s - to python to disable frozen modules.
+6.4s 4 0.00s - Note: Debugging will proceed. Set PYDEVD_DISABLE_FILE_VALIDATION=1 to disable this validation.
+6.9s 5 0.00s - Debugger warning: It seems that frozen modules are being used, which may
+6.9s 6 0.00s - make the debugger miss breakpoints. Please pass -Xfrozen_modules=off
+6.9s 7 0.00s - to python to disable frozen modules.
+6.9s 8 0.00s - Note: Debugging will proceed. Set PYDEVD_DISABLE_FILE_VALIDATION=1 to disable this validation.
+11.5s 9 2025-10-20 18:18:33.354351: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
+11.5s 10 WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
+11.5s 11 E0000 00:00:1760984313.560693      19 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
+11.5s 12 E0000 00:00:1760984313.610912      19 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
+11.7s 13 2025-10-20 18:18:33.354351: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
+11.7s 14 WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
+11.7s 15 E0000 00:00:1760984313.560693      19 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
+11.7s 16 E0000 00:00:1760984313.610912      19 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
+25.0s 17 I0000 00:00:1760984327.609864      19 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 15513 MB memory:  -> device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0
+25.2s 18 I0000 00:00:1760984327.609864      19 gpu_device.cc:2022] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 15513 MB memory:  -> device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0
+28.3s 19 ✅ Frozen 25/36 layers (~70%)
+28.3s 20 input_layer False
+28.3s 21 conv2d False
+28.3s 22 leaky_re_lu False
+28.3s 23 conv2d_1 False
+28.3s 24 batch_normalization False
+28.3s 25 leaky_re_lu_1 False
+28.3s 26 conv2d_2 False
+28.3s 27 batch_normalization_1 False
+28.3s 28 leaky_re_lu_2 False
+28.3s 29 conv2d_3 False
+29.0s 30 ✅ Restored checkpoint from /kaggle/input/gen-var/tensorflow2/default/2/best_val.ckpt-42
+29.2s 31 376
+126.9s 32 Saved visualization to output/rgb_ir_pairs.png
+
+150.8s 38 Step 0/376 | G=10.1522 | D=0.7469
+195.9s 39 Step 100/376 | G=6.6517 | D=0.5214
+241.1s 40 Step 200/376 | G=6.5913 | D=0.6182
+286.3s 41 Step 300/376 | G=6.8534 | D=0.5289
+310.6s 44 Time 183.42s | G=6.1416 | D=0.5880
+319.1s 45 Val_loss=8.1308
+324.5s 46 🖼 Saved sample images to output/epoch_001.png
+324.9s 47 🏆 Best checkpoint updated | val_loss=8.1308
+337.5s 48 Step 0/376 | G=9.8777 | D=0.7159
+382.8s 49 Step 100/376 | G=6.7390 | D=0.4855
+428.0s 50 Step 200/376 | G=6.3669 | D=0.6654
+473.2s 51 Step 300/376 | G=6.0465 | D=0.5933
+494.8s 54 Time 169.87s | G=5.9655 | D=0.5861
+502.9s 55 Val_loss=8.0259
+506.1s 56 🖼 Saved sample images to output/epoch_002.png
+506.4s 57 🏆 Best checkpoint updated | val_loss=8.0259
+519.0s 58 Step 0/376 | G=8.9304 | D=0.8360
+564.2s 59 Step 100/376 | G=6.4695 | D=0.4651
+609.5s 60 Step 200/376 | G=6.2067 | D=0.6051
+654.7s 61 Step 300/376 | G=5.6935 | D=0.6093
+676.4s 64 Time 169.98s | G=5.8677 | D=0.5865
+684.4s 65 Val_loss=7.9718
+687.8s 66 🖼 Saved sample images to output/epoch_003.png
+688.1s 67 🏆 Best checkpoint updated | val_loss=7.9718
+700.6s 68 Step 0/376 | G=9.2573 | D=0.9514
+745.9s 69 Step 100/376 | G=6.8420 | D=0.5058
+791.1s 70 Step 200/376 | G=6.3702 | D=0.6503
+836.4s 71 Step 300/376 | G=5.8164 | D=0.5970
+857.6s 74 Time 169.54s | G=5.7606 | D=0.5877
+866.4s 75 Val_loss=7.9856
+869.5s 76 🖼 Saved sample images to output/epoch_004.png
+881.7s 77 Step 0/376 | G=10.5251 | D=0.7426
+927.0s 78 Step 100/376 | G=6.7499 | D=0.5435
+972.2s 79 Step 200/376 | G=5.7333 | D=0.6468
+1017.5s 80 Step 300/376 | G=5.3933 | D=0.6261
+
+
+1039.4s 83 Time 169.86s | G=5.7380 | D=0.5873
+1047.2s 84 Val_loss=7.8545
+1050.4s 85 🖼 Saved sample images to output/epoch_005.png
+1050.7s 86 🏆 Best checkpoint updated | val_loss=7.8545
+1051.0s 87 💾 Checkpoint saved at epoch 5
+1063.9s 88 Step 0/376 | G=8.6886 | D=0.7638
+1109.1s 89 Step 100/376 | G=5.7305 | D=0.5340
+1154.4s 90 Step 200/376 | G=7.4428 | D=0.6705
+1199.6s 91 Step 300/376 | G=5.7122 | D=0.5952
+
+
+1220.8s 94 Time 169.78s | G=5.6885 | D=0.5939
+1228.8s 95 Val_loss=7.7142
+1232.1s 96 🖼 Saved sample images to output/epoch_006.png
+1232.4s 97 🏆 Best checkpoint updated | val_loss=7.7142
+1245.2s 98 Step 0/376 | G=9.0071 | D=0.7516
+1290.4s 99 Step 100/376 | G=6.7447 | D=0.5066
+1335.7s 100 Step 200/376 | G=6.1205 | D=0.5977
+1380.9s 101 Step 300/376 | G=5.5829 | D=0.6040
+1
+1
+1402.1s 104 Time 169.68s | G=5.6324 | D=0.5936
+1410.3s 105 Val_loss=7.7325
+1413.3s 106 🖼 Saved sample images to output/epoch_007.png
+1426.5s 107 Step 0/376 | G=10.3457 | D=0.9597
+1471.8s 108 Step 100/376 | G=6.8666 | D=0.4757
+1517.0s 109 Step 200/376 | G=6.1979 | D=0.6157
+1562.3s 110 Step 300/376 | G=5.9637 | D=0.5726
+1
+1
+1583.5s 113 Time 170.18s | G=5.5638 | D=0.5961
+1593.8s 114 Val_loss=7.6370
+1597.0s 115 🖼 Saved sample images to output/epoch_008.png
+1597.3s 116 🏆 Best checkpoint updated | val_loss=7.6370
+1610.4s 117 Step 0/376 | G=8.4915 | D=0.8733
+1655.6s 118 Step 100/376 | G=6.3861 | D=0.5267
+1700.8s 119 Step 200/376 | G=5.5733 | D=0.6337
+1746.1s 120 Step 300/376 | G=5.4631 | D=0.6066
+1
+1
+1767.3s 123 Time 170.03s | G=5.5368 | D=0.5963
+1775.3s 124 Val_loss=7.6658
+1778.5s 125 🖼 Saved sample images to output/epoch_009.png
+1792.2s 126 Step 0/376 | G=8.7045 | D=0.7134
+1837.4s 127 Step 100/376 | G=5.7153 | D=0.5514
+1882.6s 128 Step 200/376 | G=6.2656 | D=0.5665
+1927.9s 129 Step 300/376 | G=5.5148 | D=0.5675
+1
+1
+1949.1s 132 Time 170.66s | G=5.4865 | D=0.5975
+1957.0s 133 Val_loss=7.6524
+1960.2s 134 🖼 Saved sample images to output/epoch_010.png
+1960.5s 135 💾 Checkpoint saved at epoch 10
+1972.8s 136 Step 0/376 | G=8.4238 | D=1.1631
+2018.0s 137 Step 100/376 | G=6.2513 | D=0.5029
+2063.3s 138 Step 200/376 | G=5.5215 | D=0.6579
+2108.5s 139 Step 300/376 | G=5.6408 | D=0.5814
+2
+2
+2131.1s 142 Time 170.57s | G=5.4401 | D=0.6039
+2141.4s 143 Val_loss=7.6458
+2144.6s 144 🖼 Saved sample images to output/epoch_011.png
+2156.6s 145 Step 0/376 | G=8.1797 | D=0.8865
+2201.8s 146 Step 100/376 | G=5.8403 | D=0.5265
+2247.0s 147 Step 200/376 | G=5.7694 | D=0.5645
+2292.3s 148 Step 300/376 | G=5.2140 | D=0.6485
+2
+2
+2313.4s 151 Time 168.75s | G=5.3909 | D=0.6007
+2323.7s 152 Val_loss=7.3745
+2326.7s 153 🖼 Saved sample images to output/epoch_012.png
+2327.0s 154 🏆 Best checkpoint updated | val_loss=7.3745
+2340.7s 155 Step 0/376 | G=9.7328 | D=0.9066
+2385.9s 156 Step 100/376 | G=6.2705 | D=0.6467
+2431.1s 157 Step 200/376 | G=5.6847 | D=0.6454
+2476.4s 158 Step 300/376 | G=5.2225 | D=0.5801
+2
+2
+2497.5s 161 Time 170.47s | G=5.3476 | D=0.6009
+2505.4s 162 Val_loss=7.5291
+2510.9s 163 🖼 Saved sample images to output/epoch_013.png
+2522.8s 164 Step 0/376 | G=9.2941 | D=0.9617
+2568.0s 165 Step 100/376 | G=6.2757 | D=0.6003
+2613.3s 166 Step 200/376 | G=5.7474 | D=0.6420
+2658.5s 167 Step 300/376 | G=5.2191 | D=0.5598
+2
+2
+2681.4s 170 Time 170.48s | G=5.2989 | D=0.6030
+2689.3s 171 Val_loss=7.3649
+2692.4s 172 🖼 Saved sample images to output/epoch_014.png
+2692.7s 173 🏆 Best checkpoint updated | val_loss=7.3649
+2704.3s 174 Step 0/376 | G=8.6483 | D=0.8423
+2749.5s 175 Step 100/376 | G=6.0136 | D=0.5458
+2794.8s 176 Step 200/376 | G=6.2493 | D=0.6051
+2840.0s 177 Step 300/376 | G=5.3029 | D=0.6275
+2
+2
+2861.2s 180 Time 168.48s | G=5.2628 | D=0.6038
+2869.1s 181 Val_loss=7.1946
+2872.3s 182 🖼 Saved sample images to output/epoch_015.png
+2872.6s 183 🏆 Best checkpoint updated | val_loss=7.1946
+2872.9s 184 💾 Checkpoint saved at epoch 15
+2886.9s 185 Step 0/376 | G=8.4540 | D=0.9136
+2932.2s 186 Step 100/376 | G=6.3066 | D=0.5660
+2977.5s 187 Step 200/376 | G=6.3131 | D=0.5907
+3022.7s 188 Step 300/376 | G=5.0895 | D=0.6121
+3
+3
+3044.0s 191 Time 171.06s | G=5.2323 | D=0.6049
+3051.8s 192 Val_loss=7.1181
+3054.8s 193 🖼 Saved sample images to output/epoch_016.png
+3055.1s 194 🏆 Best checkpoint updated | val_loss=7.1181
+3067.3s 195 Step 0/376 | G=8.3916 | D=1.0179
+3112.5s 196 Step 100/376 | G=6.2327 | D=0.5590
+3157.8s 197 Step 200/376 | G=5.5025 | D=0.6376
+3203.1s 198 Step 300/376 | G=5.2561 | D=0.5560
+3
+3
+3224.2s 201 Time 169.03s | G=5.1991 | D=0.6055
+3232.1s 202 Val_loss=7.2863
+3235.3s 203 🖼 Saved sample images to output/epoch_017.png
+3249.4s 204 Step 0/376 | G=8.9895 | D=0.8920
+3294.6s 205 Step 100/376 | G=6.2291 | D=0.5340
+3339.9s 206 Step 200/376 | G=5.6260 | D=0.5993
+3385.1s 207 Step 300/376 | G=5.1172 | D=0.6228
+3
+3
+3406.3s 210 Time 170.99s | G=5.1345 | D=0.6058
+3414.3s 211 Val_loss=7.0963
+3417.3s 212 🖼 Saved sample images to output/epoch_018.png
+3417.6s 213 🏆 Best checkpoint updated | val_loss=7.0963
+3429.7s 214 Step 0/376 | G=8.4496 | D=0.7219
+3475.0s 215 Step 100/376 | G=5.9285 | D=0.5680
+3520.2s 216 Step 200/376 | G=5.6910 | D=0.6167
+3565.5s 217 Step 300/376 | G=4.7538 | D=0.5893
+3
+3
+3586.7s 220 Time 169.04s | G=5.0872 | D=0.6078
+3594.6s 221 Val_loss=7.1790
+3597.6s 222 🖼 Saved sample images to output/epoch_019.png
+3611.9s 223 Step 0/376 | G=9.2708 | D=1.0899
+3657.1s 224 Step 100/376 | G=5.5898 | D=0.5551
+3702.4s 225 Step 200/376 | G=5.4319 | D=0.6237
+3747.7s 226 Step 300/376 | G=5.0019 | D=0.5962
+3
+3
+3768.9s 229 Time 171.20s | G=5.0589 | D=0.6095
+3777.0s 230 Val_loss=7.0951
+3780.0s 231 🖼 Saved sample images to output/epoch_020.png
+3780.3s 232 🏆 Best checkpoint updated | val_loss=7.0951
+3780.6s 233 💾 Checkpoint saved at epoch 20
+3792.7s 234 Step 0/376 | G=8.4845 | D=0.8562
+3837.9s 235 Step 100/376 | G=5.6454 | D=0.4984
+3883.2s 236 Step 200/376 | G=5.3433 | D=0.6519
+3928.5s 237 Step 300/376 | G=4.4948 | D=0.6561
+3
+3
+3949.8s 240 Time 169.10s | G=5.0314 | D=0.6069
+3957.6s 241 Val_loss=7.0698
+3960.9s 242 🖼 Saved sample images to output/epoch_021.png
+3961.2s 243 🏆 Best checkpoint updated | val_loss=7.0698
+3975.7s 244 Step 0/376 | G=8.8488 | D=0.7604
+4020.9s 245 Step 100/376 | G=5.4203 | D=0.5349
+4066.2s 246 Step 200/376 | G=5.7204 | D=0.6369
+4111.4s 247 Step 300/376 | G=4.9041 | D=0.5937
+4
+4
+4132.8s 250 Time 171.61s | G=5.0194 | D=0.6094
+4143.1s 251 Val_loss=7.0145
+4146.0s 252 🖼 Saved sample images to output/epoch_022.png
+4146.3s 253 🏆 Best checkpoint updated | val_loss=7.0145
+4158.4s 254 Step 0/376 | G=8.4787 | D=0.8817
+4203.6s 255 Step 100/376 | G=5.4149 | D=0.5902
+4248.9s 256 Step 200/376 | G=5.3208 | D=0.6242
+4294.2s 257 Step 300/376 | G=4.6400 | D=0.6054
+4
+4
+4315.3s 260 Time 168.93s | G=4.9605 | D=0.6119
+4323.1s 261 Val_loss=6.8700
+4326.3s 262 🖼 Saved sample images to output/epoch_023.png
+4326.6s 263 🏆 Best checkpoint updated | val_loss=6.8700
+4338.4s 264 Step 0/376 | G=7.5732 | D=0.6659
+4383.7s 265 Step 100/376 | G=5.9233 | D=0.4832
+4428.9s 266 Step 200/376 | G=5.2821 | D=0.6215
+4474.2s 267 Step 300/376 | G=5.0356 | D=0.6299
+4
+4
+4498.3s 270 Time 171.72s | G=4.9180 | D=0.6126
+4506.1s 271 Val_loss=6.9174
+4509.1s 272 🖼 Saved sample images to output/epoch_024.png
+4521.0s 273 Step 0/376 | G=7.4529 | D=0.8022
+4566.2s 274 Step 100/376 | G=5.4565 | D=0.5570
+4611.4s 275 Step 200/376 | G=4.8301 | D=0.7032
+4656.7s 276 Step 300/376 | G=4.8302 | D=0.6007
+4
+4
+4677.9s 279 Time 168.80s | G=4.8706 | D=0.6118
+4685.9s 280 Val_loss=6.7568
+4688.9s 281 🖼 Saved sample images to output/epoch_025.png
+4689.2s 282 🏆 Best checkpoint updated | val_loss=6.7568
+4689.5s 283 💾 Checkpoint saved at epoch 25
+4701.6s 284 Step 0/376 | G=8.1572 | D=0.9106
+4746.9s 285 Step 100/376 | G=5.4285 | D=0.5716
+4792.2s 286 Step 200/376 | G=5.1490 | D=0.6190
+4837.4s 287 Step 300/376 | G=4.6954 | D=0.6809
+4
+4
+4858.6s 290 Time 169.05s | G=4.8471 | D=0.6125
+4866.4s 291 Val_loss=7.1181
+4869.4s 292 🖼 Saved sample images to output/epoch_026.png
+4881.1s 293 Step 0/376 | G=7.8186 | D=0.7620
+4926.4s 294 Step 100/376 | G=5.3644 | D=0.5120
+4971.6s 295 Step 200/376 | G=5.7542 | D=0.6179
+5016.9s 296 Step 300/376 | G=4.6515 | D=0.6274
+5
+5
+5041.3s 299 Time 171.87s | G=4.8267 | D=0.6131
+5049.2s 300 Val_loss=6.8917
+5052.2s 301 🖼 Saved sample images to output/epoch_027.png
+5064.2s 302 Step 0/376 | G=8.3894 | D=0.8106
+5109.5s 303 Step 100/376 | G=6.2067 | D=0.6047
+5154.8s 304 Step 200/376 | G=4.9070 | D=0.6469
+5200.1s 305 Step 300/376 | G=4.5984 | D=0.6116
+5
+5
+5221.3s 308 Time 168.97s | G=4.7842 | D=0.6137
+5229.0s 309 Val_loss=6.8348
+5234.4s 310 🖼 Saved sample images to output/epoch_028.png
+5246.2s 311 Step 0/376 | G=7.6272 | D=0.8283
+5291.5s 312 Step 100/376 | G=5.3753 | D=0.5221
+5336.8s 313 Step 200/376 | G=4.9872 | D=0.6496
+5382.1s 314 Step 300/376 | G=4.4991 | D=0.6430
+5
+5
+5403.4s 317 Time 168.91s | G=4.7228 | D=0.6133
+5411.2s 318 Val_loss=6.9368
+5414.3s 319 🖼 Saved sample images to output/epoch_029.png
+5426.3s 320 Step 0/376 | G=7.4167 | D=0.6308
+5471.6s 321 Step 100/376 | G=5.3999 | D=0.5426
+5516.9s 322 Step 200/376 | G=4.8630 | D=0.5926
+5562.1s 323 Step 300/376 | G=4.7185 | D=0.6238
+5
+5
+5587.0s 326 Time 172.68s | G=4.7189 | D=0.6138
+5598.4s 327 Val_loss=6.5834
+5602.3s 328 🖼 Saved sample images to output/epoch_030.png
+5602.6s 329 🏆 Best checkpoint updated | val_loss=6.5834
+5603.0s 330 💾 Checkpoint saved at epoch 30
+5616.8s 331 Step 0/376 | G=8.3277 | D=0.5476
+5662.1s 332 Step 100/376 | G=5.4074 | D=0.6476
+5707.4s 333 Step 200/376 | G=4.6740 | D=0.6172
+5752.6s 334 Step 300/376 | G=4.4735 | D=0.6534
+5
+5
+5773.8s 337 Time 170.83s | G=4.6650 | D=0.6149
+5781.5s 338 Val_loss=6.5301
+5787.0s 339 🖼 Saved sample images to output/epoch_031.png
+5787.3s 340 🏆 Best checkpoint updated | val_loss=6.5301
+5799.3s 341 Step 0/376 | G=7.5849 | D=0.8446
+5844.5s 342 Step 100/376 | G=5.6047 | D=0.5846
+5889.8s 343 Step 200/376 | G=4.8021 | D=0.6334
+5935.1s 344 Step 300/376 | G=4.3887 | D=0.5969
+5
+5
+5956.4s 347 Time 169.06s | G=4.6389 | D=0.6163
+5964.4s 348 Val_loss=6.4039
+5967.4s 349 🖼 Saved sample images to output/epoch_032.png
+5967.7s 350 🏆 Best checkpoint updated | val_loss=6.4039
+5979.7s 351 Step 0/376 | G=7.6932 | D=0.7573
+6025.0s 352 Step 100/376 | G=5.4156 | D=0.5347
+6070.3s 353 Step 200/376 | G=4.9140 | D=0.6005
+6115.6s 354 Step 300/376 | G=4.5657 | D=0.6101
+6
+6
+6141.0s 357 Time 173.25s | G=4.6034 | D=0.6154
+6148.8s 358 Val_loss=6.4423
+6154.2s 359 🖼 Saved sample images to output/epoch_033.png
+6166.2s 360 Step 0/376 | G=7.7424 | D=0.6651
+6211.6s 361 Step 100/376 | G=5.2940 | D=0.6088
+6256.8s 362 Step 200/376 | G=4.7449 | D=0.6406
+6302.1s 363 Step 300/376 | G=4.1235 | D=0.6599
+6
+6
+6323.5s 366 Time 169.19s | G=4.5536 | D=0.6159
+6331.3s 367 Val_loss=6.5015
+6334.4s 368 🖼 Saved sample images to output/epoch_034.png
+6346.5s 369 Step 0/376 | G=7.2271 | D=0.8131
+6391.8s 370 Step 100/376 | G=5.8559 | D=0.5748
+6437.1s 371 Step 200/376 | G=5.1040 | D=0.6515
+6482.4s 372 Step 300/376 | G=4.3491 | D=0.5957
+6
+6
+6503.7s 375 Time 169.24s | G=4.5184 | D=0.6151
+6511.4s 376 Val_loss=6.4034
+6514.5s 377 🖼 Saved sample images to output/epoch_035.png
+6514.8s 378 🏆 Best checkpoint updated | val_loss=6.4034
+6515.1s 379 💾 Checkpoint saved at epoch 35
+6527.1s 380 Step 0/376 | G=7.3549 | D=0.7792
+6572.4s 381 Step 100/376 | G=5.3535 | D=0.6090
+6617.7s 382 Step 200/376 | G=4.7425 | D=0.6340
+6663.0s 383 Step 300/376 | G=4.8284 | D=0.6444
+6
+6
+6684.1s 386 Time 169.00s | G=4.5015 | D=0.6168
+6692.4s 387 Val_loss=6.3655
+6695.5s 388 🖼 Saved sample images to output/epoch_036.png
+6695.8s 389 🏆 Best checkpoint updated | val_loss=6.3655
+6712.8s 390 Step 0/376 | G=7.3334 | D=0.7174
+6758.1s 391 Step 100/376 | G=4.5692 | D=0.5397
+6803.4s 392 Step 200/376 | G=4.0998 | D=0.6367
+6848.7s 393 Step 300/376 | G=4.3749 | D=0.6307
+6
+6
+6869.9s 396 Time 174.06s | G=4.4665 | D=0.6189
+6877.7s 397 Val_loss=6.3378
+6880.9s 398 🖼 Saved sample images to output/epoch_037.png
+6881.2s 399 🏆 Best checkpoint updated | val_loss=6.3378
+6893.3s 400 Step 0/376 | G=7.1830 | D=0.6298
+6938.6s 401 Step 100/376 | G=4.8157 | D=0.5073
+6983.9s 402 Step 200/376 | G=5.0199 | D=0.6477
+7029.2s 403 Step 300/376 | G=4.1610 | D=0.5946
+7
+7
+7050.6s 406 Time 169.40s | G=4.4084 | D=0.6181
+7058.5s 407 Val_loss=6.3234
+7061.6s 408 🖼 Saved sample images to output/epoch_038.png
+7061.9s 409 🏆 Best checkpoint updated | val_loss=6.3234
+7074.0s 410 Step 0/376 | G=7.6214 | D=0.7791
+7119.3s 411 Step 100/376 | G=5.3714 | D=0.5909
+7164.6s 412 Step 200/376 | G=4.5973 | D=0.6268
+7209.9s 413 Step 300/376 | G=4.3019 | D=0.6437
+7
+7
+7231.1s 416 Time 169.22s | G=4.3977 | D=0.6163
+7239.1s 417 Val_loss=6.2702
+7242.2s 418 🖼 Saved sample images to output/epoch_039.png
+7242.5s 419 🏆 Best checkpoint updated | val_loss=6.2702
+7254.4s 420 Step 0/376 | G=7.7957 | D=0.8412
+7299.8s 421 Step 100/376 | G=4.8231 | D=0.5613
+7345.0s 422 Step 200/376 | G=5.2463 | D=0.6042
+7390.3s 423 Step 300/376 | G=4.1722 | D=0.6671
+7
+7
+7411.5s 426 Time 168.99s | G=4.3469 | D=0.6208
+7419.6s 427 Val_loss=6.2376
+7422.8s 428 🖼 Saved sample images to output/epoch_040.png
+7423.1s 429 🏆 Best checkpoint updated | val_loss=6.2376
+7423.4s 430 💾 Checkpoint saved at epoch 40
+7440.6s 431 Step 0/376 | G=7.9816 | D=0.7683
+7485.9s 432 Step 100/376 | G=5.5838 | D=0.5975
+7531.2s 433 Step 200/376 | G=5.0480 | D=0.6322
+7576.5s 434 Step 300/376 | G=4.3194 | D=0.5960
+7
+7
+7597.8s 437 Time 174.43s | G=4.3204 | D=0.6197
+7605.9s 438 Val_loss=6.2099
+7608.9s 439 🖼 Saved sample images to output/epoch_041.png
+7609.2s 440 🏆 Best checkpoint updated | val_loss=6.2099
+7621.3s 441 Step 0/376 | G=8.0320 | D=0.8083
+7666.6s 442 Step 100/376 | G=4.8852 | D=0.5922
+7711.9s 443 Step 200/376 | G=5.0478 | D=0.6280
+7757.2s 444 Step 300/376 | G=4.0726 | D=0.6006
+7
+7
+7778.6s 447 Time 169.32s | G=4.2921 | D=0.6179
+7786.6s 448 Val_loss=6.1295
+7789.7s 449 🖼 Saved sample images to output/epoch_042.png
+7790.0s 450 🏆 Best checkpoint updated | val_loss=6.1295
+7802.0s 451 Step 0/376 | G=7.7331 | D=0.7679
+7847.4s 452 Step 100/376 | G=4.7346 | D=0.5389
+7892.6s 453 Step 200/376 | G=4.4696 | D=0.6263
+7937.9s 454 Step 300/376 | G=3.9252 | D=0.5932
+7
+7
+7959.2s 457 Time 169.14s | G=4.2269 | D=0.6210
+7967.1s 458 Val_loss=5.9122
+7970.2s 459 🖼 Saved sample images to output/epoch_043.png
+7970.5s 460 🏆 Best checkpoint updated | val_loss=5.9122
+7982.6s 461 Step 0/376 | G=7.9052 | D=0.8564
+8028.0s 462 Step 100/376 | G=5.1935 | D=0.5575
+8073.2s 463 Step 200/376 | G=4.4812 | D=0.6561
+8118.6s 464 Step 300/376 | G=4.0348 | D=0.6358
+8
+8
+8139.9s 467 Time 169.36s | G=4.1986 | D=0.6204
+8147.8s 468 Val_loss=5.9393
+8150.9s 469 🖼 Saved sample images to output/epoch_044.png
+8163.0s 470 Step 0/376 | G=6.7050 | D=0.7443
+8208.3s 471 Step 100/376 | G=4.6833 | D=0.6071
+8253.6s 472 Step 200/376 | G=4.2582 | D=0.6225
+8298.9s 473 Step 300/376 | G=4.2085 | D=0.5813
+8
+8
+8325.9s 476 Time 174.92s | G=4.1790 | D=0.6226
+8333.7s 477 Val_loss=6.0035
+8336.8s 478 🖼 Saved sample images to output/epoch_045.png
+8337.1s 479 💾 Checkpoint saved at epoch 45
+8349.0s 480 Step 0/376 | G=7.1352 | D=0.5797
+8394.4s 481 Step 100/376 | G=4.8119 | D=0.6121
+8439.6s 482 Step 200/376 | G=4.1505 | D=0.6122
+8484.9s 483 Step 300/376 | G=4.3496 | D=0.6447
+8
+8
+8506.3s 486 Time 169.09s | G=4.1459 | D=0.6218
+8514.1s 487 Val_loss=5.9690
+8517.3s 488 🖼 Saved sample images to output/epoch_046.png
+8529.5s 489 Step 0/376 | G=7.1425 | D=0.8774
+8574.8s 490 Step 100/376 | G=5.0781 | D=0.6307
+8620.1s 491 Step 200/376 | G=4.3326 | D=0.6371
+8665.4s 492 Step 300/376 | G=4.1976 | D=0.6224
+8
+8
+8686.6s 495 Time 169.31s | G=4.0964 | D=0.6209
+8696.9s 496 Val_loss=5.9383
+8699.9s 497 🖼 Saved sample images to output/epoch_047.png
+8711.8s 498 Step 0/376 | G=7.2791 | D=0.6243
+8757.2s 499 Step 100/376 | G=5.2249 | D=0.5633
+8802.4s 500 Step 200/376 | G=4.2565 | D=0.6243
+8847.7s 501 Step 300/376 | G=3.9169 | D=0.6548
+8
+8
+8869.0s 504 Time 169.04s | G=4.0535 | D=0.6216
+8877.0s 505 Val_loss=5.9086
+8880.0s 506 🖼 Saved sample images to output/epoch_048.png
+8880.3s 507 🏆 Best checkpoint updated | val_loss=5.9086
+8892.4s 508 Step 0/376 | G=6.3896 | D=0.6278
+8937.8s 509 Step 100/376 | G=4.6246 | D=0.5498
+8983.1s 510 Step 200/376 | G=4.0058 | D=0.6666
+9028.4s 511 Step 300/376 | G=4.0673 | D=0.6080
+9
+9
+9049.6s 514 Time 169.30s | G=4.0225 | D=0.6231
+9057.5s 515 Val_loss=5.7599
+9063.0s 516 🖼 Saved sample images to output/epoch_049.png
+9063.3s 517 🏆 Best checkpoint updated | val_loss=5.7599
+9081.6s 518 Step 0/376 | G=7.1973 | D=0.8021
+9127.0s 519 Step 100/376 | G=4.7325 | D=0.6218
+9172.2s 520 Step 200/376 | G=4.7112 | D=0.6080
+9217.5s 521 Step 300/376 | G=3.7986 | D=0.6098
+9
+9
+9238.8s 524 Time 175.41s | G=3.9794 | D=0.6229
+9246.8s 525 Val_loss=5.6452
+9249.9s 526 🖼 Saved sample images to output/epoch_050.png
+9250.2s 527 🏆 Best checkpoint updated | val_loss=5.6452
+9250.5s 528 💾 Checkpoint saved at epoch 50
+9262.5s 529 Step 0/376 | G=7.3798 | D=0.6634
+9307.8s 530 Step 100/376 | G=4.4809 | D=0.5703
+9353.0s 531 Step 200/376 | G=4.3223 | D=0.6227
+9398.3s 532 Step 300/376 | G=3.7706 | D=0.6429
+9
+9
+9419.6s 535 Time 168.97s | G=3.9478 | D=0.6256
+9427.7s 536 Val_loss=5.6258
+9430.9s 537 🖼 Saved sample images to output/epoch_051.png
+9431.2s 538 🏆 Best checkpoint updated | val_loss=5.6258
+9443.4s 539 Step 0/376 | G=6.4754 | D=0.7115
+9488.7s 540 Step 100/376 | G=4.9335 | D=0.6201
+9534.0s 541 Step 200/376 | G=4.2455 | D=0.6402
+9579.2s 542 Step 300/376 | G=3.9834 | D=0.5999
+9
+9
+9600.5s 545 Time 169.29s | G=3.9202 | D=0.6241
+9608.7s 546 Val_loss=5.8241
+9612.0s 547 🖼 Saved sample images to output/epoch_052.png
+9624.1s 548 Step 0/376 | G=5.7289 | D=0.6756
+9669.4s 549 Step 100/376 | G=4.4836 | D=0.5917
+9714.6s 550 Step 200/376 | G=4.0337 | D=0.6521
+9759.9s 551 Step 300/376 | G=3.6739 | D=0.6380
+9
+9
+9781.3s 554 Time 169.29s | G=3.8781 | D=0.6227
+9789.1s 555 Val_loss=5.6002
+9794.6s 556 🖼 Saved sample images to output/epoch_053.png
+9794.9s 557 🏆 Best checkpoint updated | val_loss=5.6002
+9807.0s 558 Step 0/376 | G=7.2531 | D=0.6886
+9852.4s 559 Step 100/376 | G=4.5507 | D=0.5559
+9897.6s 560 Step 200/376 | G=4.0481 | D=0.6331
+9942.9s 561 Step 300/376 | G=3.7436 | D=0.6088
+9
+9
+9964.2s 564 Time 169.28s | G=3.8469 | D=0.6240
+9972.1s 565 Val_loss=5.4908
+9975.3s 566 🖼 Saved sample images to output/epoch_054.png
+9975.6s 567 🏆 Best checkpoint updated | val_loss=5.4908
+9987.4s 568 Step 0/376 | G=7.0989 | D=0.6965
+10032.8s 569 Step 100/376 | G=4.2875 | D=0.5799
+10078.0s 570 Step 200/376 | G=4.0449 | D=0.6357
+10123.3s 571 Step 300/376 | G=3.6967 | D=0.6392
+10
+10
+10151.4s 574 Time 175.80s | G=3.7968 | D=0.6261
+10159.4s 575 Val_loss=5.4853
+10162.5s 576 🖼 Saved sample images to output/epoch_055.png
+10162.8s 577 🏆 Best checkpoint updated | val_loss=5.4853
+10163.1s 578 💾 Checkpoint saved at epoch 55
+10175.1s 579 Step 0/376 | G=6.5453 | D=0.6883
+10220.4s 580 Step 100/376 | G=4.8273 | D=0.6235
+10265.6s 581 Step 200/376 | G=4.6326 | D=0.6328
+10310.9s 582 Step 300/376 | G=3.5085 | D=0.6500
+10
+10
+10332.0s 585 Time 168.89s | G=3.7650 | D=0.6280
+10339.9s 586 Val_loss=5.6348
+10345.4s 587 🖼 Saved sample images to output/epoch_056.png
+10357.5s 588 Step 0/376 | G=6.1980 | D=0.9013
+10402.8s 589 Step 100/376 | G=4.5555 | D=0.6144
+10448.1s 590 Step 200/376 | G=4.1018 | D=0.6405
+10493.3s 591 Step 300/376 | G=3.5860 | D=0.6230
+10
+10
+10514.5s 594 Time 169.16s | G=3.7293 | D=0.6259
+10524.8s 595 Val_loss=5.4346
+10527.9s 596 🖼 Saved sample images to output/epoch_057.png
+10528.2s 597 🏆 Best checkpoint updated | val_loss=5.4346
+10540.2s 598 Step 0/376 | G=6.5101 | D=0.5780
+10585.6s 599 Step 100/376 | G=4.2086 | D=0.5738
+10630.8s 600 Step 200/376 | G=4.3800 | D=0.6470
+10676.1s 601 Step 300/376 | G=3.6316 | D=0.6667
+10
+10
+10697.4s 604 Time 169.11s | G=3.7031 | D=0.6267
+10705.3s 605 Val_loss=5.2923
+10710.8s 606 🖼 Saved sample images to output/epoch_058.png
+10711.1s 607 🏆 Best checkpoint updated | val_loss=5.2923
+10723.1s 608 Step 0/376 | G=6.2087 | D=0.6703
+10768.5s 609 Step 100/376 | G=4.5461 | D=0.6209
+10813.8s 610 Step 200/376 | G=3.6366 | D=0.6273
+10859.2s 611 Step 300/376 | G=3.6145 | D=0.6185
+10
+10
+10880.5s 614 Time 169.39s | G=3.6572 | D=0.6265
+10888.5s 615 Val_loss=5.2706
+10891.8s 616 🖼 Saved sample images to output/epoch_059.png
+10892.1s 617 🏆 Best checkpoint updated | val_loss=5.2706
+10904.3s 618 Step 0/376 | G=5.6787 | D=0.6679
+10949.8s 619 Step 100/376 | G=4.4435 | D=0.6094
+10995.1s 620 Step 200/376 | G=3.8235 | D=0.6758
+11040.4s 621 Step 300/376 | G=3.6584 | D=0.6582
+11
+11
+11061.8s 624 Time 169.62s | G=3.6291 | D=0.6276
+11069.8s 625 Val_loss=5.4209
+11073.1s 626 🖼 Saved sample images to output/epoch_060.png
+11073.4s 627 💾 Checkpoint saved at epoch 60
+11093.5s 628 Step 0/376 | G=5.5204 | D=0.5549
+11138.9s 629 Step 100/376 | G=4.4152 | D=0.6049
+11184.1s 630 Step 200/376 | G=4.2356 | D=0.6240
+11229.4s 631 Step 300/376 | G=3.1710 | D=0.6618
+11
+11
+11250.8s 634 Time 177.28s | G=3.6050 | D=0.6300
+11261.0s 635 Val_loss=5.2053
+11264.1s 636 🖼 Saved sample images to output/epoch_061.png
+11264.5s 637 🏆 Best checkpoint updated | val_loss=5.2053
+11276.7s 638 Step 0/376 | G=7.0660 | D=0.8382
+11322.1s 639 Step 100/376 | G=4.7023 | D=0.5939
+11367.4s 640 Step 200/376 | G=3.4557 | D=0.6008
+11412.7s 641 Step 300/376 | G=3.1275 | D=0.6347
+11
+11
+11434.1s 644 Time 169.61s | G=3.5584 | D=0.6283
+11442.2s 645 Val_loss=5.2976
+11447.7s 646 🖼 Saved sample images to output/epoch_062.png
+11459.9s 647 Step 0/376 | G=6.1519 | D=0.6746
+11505.3s 648 Step 100/376 | G=4.0729 | D=0.6114
+11550.6s 649 Step 200/376 | G=3.5431 | D=0.6546
+11595.9s 650 Step 300/376 | G=3.3409 | D=0.6478
+11
+11
+11649.6s 653 Time 201.92s | G=3.5359 | D=0.6299
+11657.5s 654 Val_loss=5.2755
+11660.5s 655 🖼 Saved sample images to output/epoch_063.png
+11672.4s 656 Step 0/376 | G=5.7210 | D=0.7923
+11717.8s 657 Step 100/376 | G=4.3220 | D=0.6124
+11763.1s 658 Step 200/376 | G=3.8023 | D=0.6492
+11808.4s 659 Step 300/376 | G=3.4106 | D=0.6445
+11
+11
+11829.6s 662 Time 169.07s | G=3.4787 | D=0.6300
+11837.6s 663 Val_loss=5.1321
+11840.6s 664 🖼 Saved sample images to output/epoch_064.png
+11840.9s 665 🏆 Best checkpoint updated | val_loss=5.1321
+11852.7s 666 Step 0/376 | G=5.2394 | D=0.7294
+11898.1s 667 Step 100/376 | G=4.1536 | D=0.5974
+11943.5s 668 Step 200/376 | G=3.9781 | D=0.6169
+11988.7s 669 Step 300/376 | G=3.9450 | D=0.5819
+12
+12
+12010.0s 672 Time 169.00s | G=3.4519 | D=0.6294
+12017.9s 673 Val_loss=4.9427
+12023.4s 674 🖼 Saved sample images to output/epoch_065.png
+12023.7s 675 🏆 Best checkpoint updated | val_loss=4.9427
+12024.0s 676 💾 Checkpoint saved at epoch 65
+12035.8s 677 Step 0/376 | G=5.8535 | D=0.7737
+12081.2s 678 Step 100/376 | G=3.9873 | D=0.5937
+12126.5s 679 Step 200/376 | G=3.3124 | D=0.6624
+12171.8s 680 Step 300/376 | G=3.2737 | D=0.6563
+12
+12
+12193.4s 683 Time 169.36s | G=3.4109 | D=0.6314
+12201.4s 684 Val_loss=5.0014
+12204.6s 685 🖼 Saved sample images to output/epoch_066.png
+12216.8s 686 Step 0/376 | G=6.4397 | D=0.7202
+12262.2s 687 Step 100/376 | G=3.9876 | D=0.5936
+12307.5s 688 Step 200/376 | G=4.3265 | D=0.6032
+12352.9s 689 Step 300/376 | G=3.2042 | D=0.6529
+12
+12
+12384.2s 692 Time 179.63s | G=3.3774 | D=0.6329
+12392.2s 693 Val_loss=4.9945
+12395.2s 694 🖼 Saved sample images to output/epoch_067.png
+12407.7s 695 Step 0/376 | G=5.8329 | D=0.7105
+12453.1s 696 Step 100/376 | G=3.6485 | D=0.6176
+12498.5s 697 Step 200/376 | G=3.7839 | D=0.6328
+12543.8s 698 Step 300/376 | G=3.4857 | D=0.6119
+12
+12
+12565.1s 701 Time 169.76s | G=3.3480 | D=0.6318
+12573.0s 702 Val_loss=4.9362
+12576.0s 703 🖼 Saved sample images to output/epoch_068.png
+12576.3s 704 🏆 Best checkpoint updated | val_loss=4.9362
+12588.5s 705 Step 0/376 | G=5.4719 | D=0.7768
+12633.9s 706 Step 100/376 | G=3.8334 | D=0.6669
+12679.2s 707 Step 200/376 | G=3.6392 | D=0.6257
+12724.5s 708 Step 300/376 | G=3.1372 | D=0.6679
+12
+12
+12745.8s 711 Time 169.43s | G=3.3092 | D=0.6321
+12753.7s 712 Val_loss=4.8826
+12756.7s 713 🖼 Saved sample images to output/epoch_069.png
+12757.0s 714 🏆 Best checkpoint updated | val_loss=4.8826
+12769.0s 715 Step 0/376 | G=4.9498 | D=0.6127
+12814.4s 716 Step 100/376 | G=3.6878 | D=0.6158
+12859.7s 717 Step 200/376 | G=3.3736 | D=0.6621
+12905.0s 718 Step 300/376 | G=3.0053 | D=0.6262
+12
+12
+12926.4s 721 Time 169.29s | G=3.2584 | D=0.6321
+12934.4s 722 Val_loss=4.9833
+12937.4s 723 🖼 Saved sample images to output/epoch_070.png
+12937.7s 724 💾 Checkpoint saved at epoch 70
+12949.7s 725 Step 0/376 | G=5.6698 | D=0.6535
+12995.1s 726 Step 100/376 | G=3.8697 | D=0.6405
+13040.5s 727 Step 200/376 | G=3.9499 | D=0.6113
+13085.7s 728 Step 300/376 | G=3.0893 | D=0.6718
+13
+13
+13107.0s 731 Time 169.23s | G=3.2324 | D=0.6317
+13114.9s 732 Val_loss=4.7447
+13120.4s 733 🖼 Saved sample images to output/epoch_071.png
+13120.7s 734 🏆 Best checkpoint updated | val_loss=4.7447
+13132.8s 735 Step 0/376 | G=5.3708 | D=0.7000
+13178.2s 736 Step 100/376 | G=3.5859 | D=0.6146
+13223.5s 737 Step 200/376 | G=3.2398 | D=0.6210
+13268.8s 738 Step 300/376 | G=3.0854 | D=0.6507
+13
+13
+13290.0s 741 Time 169.27s | G=3.1795 | D=0.6347
+13298.0s 742 Val_loss=4.8294
+13301.0s 743 🖼 Saved sample images to output/epoch_072.png
+13313.0s 744 Step 0/376 | G=4.6913 | D=0.5467
+13358.4s 745 Step 100/376 | G=4.4168 | D=0.6707
+13403.7s 746 Step 200/376 | G=3.3704 | D=0.6365
+13449.1s 747 Step 300/376 | G=3.3304 | D=0.6046
+13
+13
+13470.4s 750 Time 169.37s | G=3.1613 | D=0.6319
+13478.4s 751 Val_loss=4.6030
+13481.5s 752 🖼 Saved sample images to output/epoch_073.png
+13481.8s 753 🏆 Best checkpoint updated | val_loss=4.6030
+13493.9s 754 Step 0/376 | G=6.5052 | D=0.6467
+13539.4s 755 Step 100/376 | G=4.0048 | D=0.5739
+13584.7s 756 Step 200/376 | G=3.2776 | D=0.6492
+13630.0s 757 Step 300/376 | G=2.9286 | D=0.5974
+13
+13
+13660.8s 760 Time 178.91s | G=3.1334 | D=0.6315
+13669.0s 761 Val_loss=4.5431
+13672.2s 762 🖼 Saved sample images to output/epoch_074.png
+13672.5s 763 🏆 Best checkpoint updated | val_loss=4.5431
+13684.6s 764 Step 0/376 | G=6.2637 | D=0.7287
+13730.0s 765 Step 100/376 | G=3.7316 | D=0.6523
+13775.3s 766 Step 200/376 | G=3.4680 | D=0.6680
+13820.6s 767 Step 300/376 | G=2.9001 | D=0.6955
+13
+13
+13842.0s 770 Time 169.46s | G=3.0860 | D=0.6342
+13850.2s 771 Val_loss=4.5978
+13855.7s 772 🖼 Saved sample images to output/epoch_075.png
+13856.0s 773 💾 Checkpoint saved at epoch 75
+13867.9s 774 Step 0/376 | G=5.3579 | D=0.7652
+13913.3s 775 Step 100/376 | G=3.6684 | D=0.5819
+13958.7s 776 Step 200/376 | G=3.1248 | D=0.6668
+14004.0s 777 Step 300/376 | G=2.9518 | D=0.6354
+14
+14
+14025.4s 780 Time 169.31s | G=3.0519 | D=0.6322
+14033.3s 781 Val_loss=4.6097
+14036.4s 782 🖼 Saved sample images to output/epoch_076.png
+14048.3s 783 Step 0/376 | G=5.4006 | D=0.7185
+14093.8s 784 Step 100/376 | G=3.6177 | D=0.5462
+14139.0s 785 Step 200/376 | G=2.7455 | D=0.6766
+14184.4s 786 Step 300/376 | G=2.7631 | D=0.6362
+14
+14
+14205.8s 789 Time 169.36s | G=3.0110 | D=0.6350
+14213.7s 790 Val_loss=4.5112
+14216.7s 791 🖼 Saved sample images to output/epoch_077.png
+14217.0s 792 🏆 Best checkpoint updated | val_loss=4.5112
+14229.1s 793 Step 0/376 | G=4.7770 | D=0.6762
+14274.5s 794 Step 100/376 | G=3.5976 | D=0.5739
+14319.8s 795 Step 200/376 | G=3.3589 | D=0.6383
+14365.1s 796 Step 300/376 | G=2.7231 | D=0.6584
+14
+14
+14386.6s 799 Time 169.60s | G=2.9787 | D=0.6366
+14394.7s 800 Val_loss=4.3760
+14397.7s 801 🖼 Saved sample images to output/epoch_078.png
+14398.0s 802 🏆 Best checkpoint updated | val_loss=4.3760
+14409.9s 803 Step 0/376 | G=5.0417 | D=0.6882
+14455.4s 804 Step 100/376 | G=3.4231 | D=0.5878
+14500.7s 805 Step 200/376 | G=3.2906 | D=0.6477
+14546.0s 806 Step 300/376 | G=2.6614 | D=0.6399
+14
+14
+14567.5s 809 Time 169.42s | G=2.9434 | D=0.6357
+14575.6s 810 Val_loss=4.5083
+14578.7s 811 🖼 Saved sample images to output/epoch_079.png
+14590.8s 812 Step 0/376 | G=6.9896 | D=0.6929
+14636.3s 813 Step 100/376 | G=3.5000 | D=0.5599
+14681.6s 814 Step 200/376 | G=2.8046 | D=0.6534
+14726.9s 815 Step 300/376 | G=3.1000 | D=0.6145
+14
+14
+14748.3s 818 Time 169.60s | G=2.9138 | D=0.6356
+14756.3s 819 Val_loss=4.2344
+14759.4s 820 🖼 Saved sample images to output/epoch_080.png
+14759.7s 821 🏆 Best checkpoint updated | val_loss=4.2344
+14760.0s 822 💾 Checkpoint saved at epoch 80
+14772.0s 823 Step 0/376 | G=4.8706 | D=0.7112
+14817.4s 824 Step 100/376 | G=3.4408 | D=0.5991
+14862.7s 825 Step 200/376 | G=3.0256 | D=0.6408
+14908.0s 826 Step 300/376 | G=2.7274 | D=0.6581
+14
+14
+14929.3s 829 Time 169.28s | G=2.8598 | D=0.6357
+14937.5s 830 Val_loss=4.3669
+14940.6s 831 🖼 Saved sample images to output/epoch_081.png
+14952.5s 832 Step 0/376 | G=5.5032 | D=0.7291
+14997.9s 833 Step 100/376 | G=3.8340 | D=0.6254
+15043.2s 834 Step 200/376 | G=2.8452 | D=0.6226
+15088.6s 835 Step 300/376 | G=2.7787 | D=0.6664
+15
+15
+15120.7s 838 Time 180.04s | G=2.8461 | D=0.6353
+15128.7s 839 Val_loss=4.2840
+15131.7s 840 🖼 Saved sample images to output/epoch_082.png
+15143.8s 841 Step 0/376 | G=5.1436 | D=0.6448
+15189.2s 842 Step 100/376 | G=2.9755 | D=0.5940
+15234.5s 843 Step 200/376 | G=2.9174 | D=0.6628
+15279.8s 844 Step 300/376 | G=2.6727 | D=0.6550
+15
+15
+15301.2s 847 Time 169.40s | G=2.8079 | D=0.6347
+15309.3s 848 Val_loss=4.1996
+15314.8s 849 🖼 Saved sample images to output/epoch_083.png
+15315.1s 850 🏆 Best checkpoint updated | val_loss=4.1996
+15327.1s 851 Step 0/376 | G=5.2726 | D=0.6822
+15372.5s 852 Step 100/376 | G=3.5970 | D=0.6313
+15417.8s 853 Step 200/376 | G=2.7029 | D=0.7004
+15463.1s 854 Step 300/376 | G=2.5813 | D=0.6395
+15
+15
+15484.5s 857 Time 169.34s | G=2.7617 | D=0.6356
+15492.4s 858 Val_loss=4.1724
+15495.5s 859 🖼 Saved sample images to output/epoch_084.png
+15495.8s 860 🏆 Best checkpoint updated | val_loss=4.1724
+15508.0s 861 Step 0/376 | G=4.6803 | D=0.6805
+15553.4s 862 Step 100/376 | G=3.2016 | D=0.6237
+15598.7s 863 Step 200/376 | G=3.1953 | D=0.6630
+15644.0s 864 Step 300/376 | G=2.6157 | D=0.7006
+15
+15
+15665.4s 867 Time 169.59s | G=2.7215 | D=0.6368
+15673.5s 868 Val_loss=4.1145
+15678.9s 869 🖼 Saved sample images to output/epoch_085.png
+15679.2s 870 🏆 Best checkpoint updated | val_loss=4.1145
+15679.6s 871 💾 Checkpoint saved at epoch 85
+15692.1s 872 Step 0/376 | G=4.8261 | D=0.7200
+15737.5s 873 Step 100/376 | G=3.7966 | D=0.6242
+15782.8s 874 Step 200/376 | G=3.2803 | D=0.6386
+15828.2s 875 Step 300/376 | G=2.5505 | D=0.6630
+15
+15
+15849.5s 878 Time 169.87s | G=2.6996 | D=0.6378
+15857.6s 879 Val_loss=4.2780
+15860.7s 880 🖼 Saved sample images to output/epoch_086.png
+15872.8s 881 Step 0/376 | G=4.3633 | D=0.6062
+15918.3s 882 Step 100/376 | G=3.3645 | D=0.5385
+15963.6s 883 Step 200/376 | G=2.5901 | D=0.6135
+16008.9s 884 Step 300/376 | G=2.7246 | D=0.5871
+16
+16
+16030.3s 887 Time 169.60s | G=2.6562 | D=0.6368
+16038.5s 888 Val_loss=4.0184
+16041.6s 889 🖼 Saved sample images to output/epoch_087.png
+16041.9s 890 🏆 Best checkpoint updated | val_loss=4.0184
+16054.0s 891 Step 0/376 | G=3.8949 | D=0.5574
+16099.5s 892 Step 100/376 | G=3.3085 | D=0.6019
+16144.8s 893 Step 200/376 | G=2.7265 | D=0.6345
+16190.1s 894 Step 300/376 | G=2.6312 | D=0.6203
+16
+16
+16211.3s 897 Time 169.44s | G=2.6140 | D=0.6363
+16219.4s 898 Val_loss=3.9724
+16224.8s 899 🖼 Saved sample images to output/epoch_088.png
+16225.1s 900 🏆 Best checkpoint updated | val_loss=3.9724
+16237.1s 901 Step 0/376 | G=4.5991 | D=0.5632
+16282.6s 902 Step 100/376 | G=3.1918 | D=0.6311
+16327.9s 903 Step 200/376 | G=2.8315 | D=0.6645
+16373.2s 904 Step 300/376 | G=2.4876 | D=0.6444
+16
+16
+16394.6s 907 Time 169.40s | G=2.5822 | D=0.6378
+16402.6s 908 Val_loss=4.0451
+16405.7s 909 🖼 Saved sample images to output/epoch_089.png
+16418.0s 910 Step 0/376 | G=4.6367 | D=0.6808
+16463.4s 911 Step 100/376 | G=3.2083 | D=0.5872
+16508.8s 912 Step 200/376 | G=2.9264 | D=0.6365
+16554.1s 913 Step 300/376 | G=2.1684 | D=0.6539
+16
+16
+16575.5s 916 Time 169.79s | G=2.5478 | D=0.6362
+16583.7s 917 Val_loss=3.9122
+16586.7s 918 🖼 Saved sample images to output/epoch_090.png
+16598.7s 919 🏆 Best checkpoint updated | val_loss=3.9122
+16599.2s 920 💾 Checkpoint saved at epoch 90
+16611.3s 921 Step 0/376 | G=4.0842 | D=0.7403
+16656.8s 922 Step 100/376 | G=3.0089 | D=0.5677
+16702.1s 923 Step 200/376 | G=2.7950 | D=0.6168
+16747.5s 924 Step 300/376 | G=2.4747 | D=0.6055
+16
+16
+16768.9s 927 Time 169.63s | G=2.4920 | D=0.6390
+16777.0s 928 Val_loss=3.8380
+16780.2s 929 🖼 Saved sample images to output/epoch_091.png
+16780.4s 930 🏆 Best checkpoint updated | val_loss=3.8380
+16792.9s 931 Step 0/376 | G=5.4327 | D=0.6846
+16838.4s 932 Step 100/376 | G=3.3698 | D=0.6232
+16883.7s 933 Step 200/376 | G=2.7433 | D=0.6527
+16929.0s 934 Step 300/376 | G=2.5256 | D=0.6204
+16
+16
+16950.3s 937 Time 169.84s | G=2.4625 | D=0.6406
+16958.5s 938 Val_loss=3.7432
+16961.6s 939 🖼 Saved sample images to output/epoch_092.png
+16961.9s 940 🏆 Best checkpoint updated | val_loss=3.7432
+16974.3s 941 Step 0/376 | G=3.5366 | D=0.5955
+17019.7s 942 Step 100/376 | G=3.5291 | D=0.5829
+17065.1s 943 Step 200/376 | G=2.5609 | D=0.6201
+17110.4s 944 Step 300/376 | G=2.5530 | D=0.6388
+17
+17
+17131.7s 947 Time 169.80s | G=2.4321 | D=0.6390
+17139.9s 948 Val_loss=3.8107
+17143.1s 949 🖼 Saved sample images to output/epoch_093.png
+17155.3s 950 Step 0/376 | G=4.7956 | D=0.7008
+17200.8s 951 Step 100/376 | G=3.2964 | D=0.6357
+17246.1s 952 Step 200/376 | G=2.7449 | D=0.6916
+17291.4s 953 Step 300/376 | G=2.3979 | D=0.6455
+17
+17
+17313.0s 956 Time 169.92s | G=2.4041 | D=0.6396
+17321.2s 957 Val_loss=3.6839
+17324.3s 958 🖼 Saved sample images to output/epoch_094.png
+17324.6s 959 🏆 Best checkpoint updated | val_loss=3.6839
+17336.8s 960 Step 0/376 | G=4.4018 | D=0.7070
+17382.2s 961 Step 100/376 | G=3.0409 | D=0.5230
+17427.6s 962 Step 200/376 | G=2.5092 | D=0.6279
+17472.9s 963 Step 300/376 | G=2.1991 | D=0.5932
+17
+17
+17494.1s 966 Time 169.47s | G=2.3599 | D=0.6390
+17502.3s 967 Val_loss=3.5712
+17505.4s 968 🖼 Saved sample images to output/epoch_095.png
+17505.7s 969 🏆 Best checkpoint updated | val_loss=3.5712
+17506.0s 970 💾 Checkpoint saved at epoch 95
+17518.2s 971 Step 0/376 | G=4.8006 | D=0.6310
+17563.7s 972 Step 100/376 | G=2.7726 | D=0.6086
+17609.0s 973 Step 200/376 | G=2.5687 | D=0.6676
+17654.3s 974 Step 300/376 | G=2.2540 | D=0.6034
+17
+17
+17675.7s 977 Time 169.57s | G=2.3281 | D=0.6411
+17683.8s 978 Val_loss=3.5431
+17686.8s 979 🖼 Saved sample images to output/epoch_096.png
+17687.1s 980 🏆 Best checkpoint updated | val_loss=3.5431
+17698.9s 981 Step 0/376 | G=3.7862 | D=0.7004
+17744.4s 982 Step 100/376 | G=2.4434 | D=0.5949
+17789.7s 983 Step 200/376 | G=2.2817 | D=0.6858
+17835.0s 984 Step 300/376 | G=2.2642 | D=0.6941
+17
+17
+17856.5s 987 Time 169.31s | G=2.2933 | D=0.6421
+17864.7s 988 Val_loss=3.5863
+17867.7s 989 🖼 Saved sample images to output/epoch_097.png
+17879.8s 990 Step 0/376 | G=3.7193 | D=0.5015
+17925.3s 991 Step 100/376 | G=2.9299 | D=0.6352
+17970.6s 992 Step 200/376 | G=2.1576 | D=0.6579
+18015.9s 993 Step 300/376 | G=2.2175 | D=0.6783
+18
+18
+18037.4s 996 Time 169.67s | G=2.2444 | D=0.6416
+18045.5s 997 Val_loss=3.4525
+18048.6s 998 🖼 Saved sample images to output/epoch_098.png
+18048.8s 999 🏆 Best checkpoint updated | val_loss=3.4525
+18060.8s 1000 Step 0/376 | G=4.0367 | D=0.5751
+18106.2s 1001 Step 100/376 | G=2.8571 | D=0.6623
+18151.5s 1002 Step 200/376 | G=2.0538 | D=0.7090
+18196.8s 1003 Step 300/376 | G=2.3591 | D=0.6435
+182
+182
+18218.2s 1006 Time 169.29s | G=2.2198 | D=0.6383
+18226.3s 1007 Val_loss=3.4924
+18229.4s 1008 🖼 Saved sample images to output/epoch_099.png
+18254.3s 1009 Step 0/376 | G=4.7228 | D=0.5148
+18299.9s 1010 Step 100/376 | G=2.9035 | D=0.5484
+18345.2s 1011 Step 200/376 | G=2.7119 | D=0.6533
+18390.5s 1012 Step 300/376 | G=2.1389 | D=0.6548
+184
+184
+18412.1s 1015 Time 182.69s | G=2.1891 | D=0.6406
+18420.2s 1016 Val_loss=3.4315
+18423.3s 1017 🖼 Saved sample images to output/epoch_100.png
+18423.6s 1018 🏆 Best checkpoint updated | val_loss=3.4315
+18423.9s 1019 💾 Checkpoint saved at epoch 100
+18423.9s 1020 ✅ Training complete and models saved!
+18487.2s 1021 ==== Test Dataset Metrics ====
+18487.2s 1022 L1 Loss   : 0.0570
+18487.2s 1023 PSNR      : 24.4505
+18487.2s 1024 SSIM      : 0.8575
+19258.6s 1027 L1 Loss   : 0.0570
+19258.6s 1028 PSNR      : 24.4500
+19258.6s 1029 SSIM      : 0.8576
+19258.6s 1030 All predictions saved to output/test_results

loss_summary.csv

@@ -0,0 +1,101 @@
+Epoch,Generator,Discriminator,Val_loss
+1,7.27804,0.60068,8.1308
+2,6.9991200000000005,0.60924,8.0259
+3,6.63356,0.6204,7.9718
+4,6.8093,0.65844,7.9856
+5,6.827920000000001,0.62926,7.8545
+6,6.65252,0.63148,7.7142
+7,6.617520000000001,0.6107,7.7325
+8,6.98754,0.6439600000000001,7.637
+9,6.29016,0.64732,7.6658
+10,6.33734,0.59926,7.6524
+11,6.2555,0.70184,7.6458
+12,6.078860000000001,0.64534,7.3745
+13,6.45162,0.67594,7.5291
+14,6.36704,0.67336,7.3649
+15,6.29538,0.6449,7.1946
+16,6.279100000000001,0.65746,7.1181
+17,6.1164000000000005,0.6752,7.2863
+18,6.21926,0.65078,7.0963
+19,5.98202,0.62074,7.179
+20,6.07066,0.69488,7.0951
+21,5.79988,0.6538999999999999,7.0698
+22,5.9826,0.62706,7.0145
+23,5.762980000000001,0.66268,6.87
+24,5.74644,0.60262,6.9174
+25,5.48806,0.65498,6.7568
+26,5.6554400000000005,0.67892,7.1181
+27,5.6830799999999995,0.62648,6.8917
+28,5.77714,0.6575,6.8348
+29,5.4423200000000005,0.65126,6.9368
+30,5.423399999999999,0.60072,6.5834
+31,5.50952,0.6161399999999999,6.5301
+32,5.40386,0.65516,6.4039
+33,5.43838,0.6235999999999999,6.4423
+34,5.29168,0.6380600000000001,6.5015
+35,5.4109,0.65004,6.4034
+36,5.35616,0.6566799999999999,6.3655
+37,4.9687600000000005,0.62868,6.3378
+38,5.1176,0.5995,6.3234
+39,5.25794,0.65136,6.2702
+40,5.27684,0.65892,6.2376
+41,5.45064,0.6427400000000001,6.2099
+42,5.26594,0.6494,6.1295
+43,5.01788,0.62946,5.9122
+44,5.16266,0.66524,5.9393
+45,4.8068,0.63556,6.0035
+46,4.91862,0.6141,5.969
+47,4.9694400000000005,0.6777,5.9383
+48,4.94618,0.6176600000000001,5.9086
+49,4.62196,0.6150599999999999,5.7599
+50,4.8838,0.6529200000000001,5.6452
+51,4.78028,0.6249800000000001,5.6258
+52,4.7116,0.6391600000000001,5.8241
+53,4.359640000000001,0.63602,5.6002
+54,4.68848,0.62208,5.4908
+55,4.584960000000001,0.63548,5.4853
+56,4.65574,0.64452,5.6348
+57,4.43412,0.68102,5.4346
+58,4.48668,0.61844,5.2923
+59,4.33262,0.6327,5.2706
+60,4.24664,0.64778,5.4209
+61,4.189439999999999,0.61512,5.2053
+62,4.38198,0.65918,5.2976
+63,4.12894,0.64366,5.2755
+64,4.14692,0.66568,5.1321
+65,4.1536,0.631,4.9427
+66,3.96756,0.6635,5.0014
+67,4.26708,0.64056,4.9945
+68,4.0198,0.64092,4.9362
+69,3.8781800000000004,0.67388,4.8826
+70,3.6549799999999997,0.62978,4.9833
+71,3.96222,0.64176,4.7447
+72,3.6922800000000002,0.6442,4.8294
+73,3.7940400000000003,0.61808,4.603
+74,3.9699200000000006,0.61974,4.5431
+75,3.8898800000000002,0.67574,4.5978
+76,3.6309600000000004,0.6563,4.6097
+77,3.50758,0.6425,4.5112
+78,3.4870600000000005,0.6366799999999999,4.376
+79,3.47204,0.63986,4.5083
+80,3.8616,0.6312599999999999,4.2344
+81,3.3848399999999996,0.6489800000000001,4.3669
+82,3.56144,0.65576,4.284
+83,3.30342,0.63826,4.1996
+84,3.3831,0.6578,4.1724
+85,3.28288,0.6609200000000001,4.1145
+86,3.4306200000000002,0.65672,4.278
+87,3.13974,0.59642,4.0184
+88,3.0350200000000003,0.61008,3.9724
+89,3.13844,0.6282,4.0451
+90,3.0975200000000003,0.6389199999999999,3.9122
+91,2.9709600000000003,0.63386,3.838
+92,3.30678,0.6443,3.7432
+93,2.92234,0.6152599999999999,3.8107
+94,3.12778,0.66264,3.6839
+95,2.90218,0.61802,3.5712
+96,2.9448,0.63034,3.5431
+97,2.61376,0.6634599999999999,3.5863
+98,2.65374,0.6229,3.4525
+99,2.7053000000000003,0.64564,3.4924
+100,2.93324,0.6023799999999999,3.4315