Upload weights, notebooks, sample images

configs/pretrained_config.yaml

@@ -9,7 +9,7 @@ parameters:
       MODEL_MODULE: "models"  # Module name to import model classes from (default: "models")
       RGB_ENCODER:
         ENCODER: "facebook/dinov3-vitl16-pretrain-lvd1689m"  # DINOv3 encoder model name (HuggingFace format)
-        IMAGE_SIZE: 448  # Input image size (height and width in pixels)
+        IMAGE_SIZE: 896  # Input image size (height and width in pixels)
         RETURN_SELECTED_LAYERS: [3, 6, 9, 12]  # Transformer layer indices to extract features from (0-indexed)
         RGB_ENCODER_LR: 0.0  # Learning rate for RGB encoder (0.0 = frozen, must be explicitly set)
       DECODERS:
@@ -19,10 +19,10 @@ parameters:
           REASSEMBLE_OUT_CHANNELS: [768,1024,1536,2048]  # Output channels for each decoder stage (DPT-style reassembly)
           REASSEMBLE_FACTORS: [4.0, 2.0, 1.0, 0.5]  # Spatial upsampling factors for each stage
           READOUT_TYPE: "ignore"  # Readout type for DPT decoder ("ignore", "project", etc.)
-          FROM_PRETRAINED: "weights/rgb_decoder.pth"  # Path to pretrained decoder weights (optional)
+          # FROM_PRETRAINED: "weights/rgb_decoder.pth"  # Path to pretrained decoder weights (optional)
           USE_BN: False  # Use batch normalization in decoder
           DROPOUT: 0.1  # Dropout rate in decoder layers
-          OUTPUT_IMAGE_SIZE: [448,448]  # Output image resolution [height, width]
+          OUTPUT_IMAGE_SIZE: [896,896]  # Output image resolution [height, width]
           OUTPUT_CHANNELS: 3  # Number of output channels (3 for RGB diffuse image)
           DECODER_LR: 1.0e-5 # Custom learning rate for decoder (0.0 = frozen, 1.0 = same as base LR)
           NUM_FUSION_BLOCKS_TRAINABLE: 1  # Number of fusion blocks to train (0-4, null = train all if DECODER_LR != 0)
@@ -35,14 +35,14 @@ parameters:
           READOUT_TYPE: "ignore"  # Readout type for DPT decoder
           USE_BN: False  # Use batch normalization in decoder
           DROPOUT: 0.1  # Dropout rate in decoder layers
-          OUTPUT_IMAGE_SIZE: [448,448]  # Output image resolution [height, width]
+          OUTPUT_IMAGE_SIZE: [896,896]  # Output image resolution [height, width]
           OUTPUT_CHANNELS: 1  # Number of output channels (1 for highlight mask)
           DECODER_LR: 5.0e-4  # Custom learning rate for decoder (0.0 = frozen, 1.0 = same as base LR)
           NUM_FUSION_BLOCKS_TRAINABLE: null  # Number of fusion blocks to train (0-4, null = train all if DECODER_LR != 0)
       TOKEN_INPAINTER:
         TOKEN_INPAINTER_CLASS: "TokenInpainter_Prior"  # Token inpainter class name
         TOKEN_INPAINTER_MODULE: "token_inpainters"  # Module name to import token inpainter from
-        FROM_PRETRAINED: "weights/token_inpainter.pth"  # Path to pretrained token inpainter weights 
+        # FROM_PRETRAINED: "weights/token_inpainter.pth"  # Path to pretrained token inpainter weights 
         TOKEN_INPAINTER_LR: 1.0e-5  # Learning rate for token inpainter (can differ from base LR)
         DEPTH: 6  # Number of transformer blocks
         HEADS: 16  # Number of attention heads