Add per-app icons and declare the app task

Add IMPACT-Synth training config (losses + optimizer) so the app is fine-tunable

fix: name the output group after the module the model exposes

fix: log the image of the module the model exposes

fix: log the image of the module the model exposes

fix: log the image of the module the model exposes

fix: log the image of the module the model exposes

fix: name the output group after the module the model exposes

fix: name the output group after the module the model exposes

fix: name the output group after the module the model exposes

Drop the 2077-line UNetpp.yml (replaced by block-level UNetPlusPlus.yml)

Drop the 2077-line UNetpp.yml (replaced by block-level UNetPlusPlus.yml)

Drop the 2077-line UNetpp.yml (replaced by block-level UNetPlusPlus.yml)

Drop the 2077-line UNetpp.yml (replaced by block-level UNetPlusPlus.yml)

Block-level UNetPlusPlus.yml + Tanh + clean-key checkpoints (forward-exact 0.0)

Block-level UNetPlusPlus.yml + Tanh + clean-key checkpoints (forward-exact 0.0)

Block-level UNetPlusPlus.yml + Tanh + clean-key checkpoints (forward-exact 0.0)

Block-level UNetPlusPlus.yml + Tanh + clean-key checkpoints (forward-exact 0.0)

Use declarative UNetpp.yml + clean-key checkpoints (forward-exact 0.0, inference-only)

Use declarative UNetpp.yml + clean-key checkpoints (forward-exact 0.0, inference-only)

Use declarative UNetpp.yml + clean-key checkpoints (forward-exact 0.0, inference-only)

Use declarative UNetpp.yml + clean-key checkpoints (forward-exact 0.0, inference-only)

perf: recalibrate vram_plan (leave GPU headroom) + refresh perf README

perf: recalibrate vram_plan (leave GPU headroom) + refresh perf README

Fix model-intrinsic params in the model (input channels / class count / network architecture) instead of exposing them in the config

app.json: drop redundant top-level patch_size (now read from Prediction.yml)

Update model card, app.json (patch size + VRAM plan) and inference configs

Make SAM_Perceptual metric explicit (train=False) in evaluation configs

Use SAM_Perceptual(train=True, weights=[0,1,1,0]) as training loss instead of IMPACTReg

Update

Update CV_3.pt MR/CT models

Update app.conf

Add Finetune models

Add MR/CT models

Add finetune models

Add finetune models

Add finetune models

Update MR/Prediction.yml

Update MR_CBCT/Prediction.yml

Update CBCT/Prediction.yml

Update MR/Prediction.yml

Update MR_CBCT/Prediction.yml

Update MR_CBCT/Prediction.yml

Update MR/Prediction.yml

Update CBCT/Prediction.yml

Update CBCT/Prediction.yml

Update CBCT/Prediction.yml

Update CBCT/Prediction.yml

Update CBCT/Prediction.yml

Update CBCT/Prediction.yml