Skill Claude CodeCodex
Encode text prompts into fixed-length dense vectors using SentenceTransformer for cosine-similarity evaluation in image-to-text retrieval tasks.
not rated 60
+1 4mo ago A 32 tokens
60Stars on the repository
200Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
Skill Claude CodeCodex
2D CNN with asymmetric kernels — temporal convolutions (Nx1) then spectral convolutions (1xM) — to decouple time and feature extraction.
not rated 60
+1 4mo ago A 41 tokens
Skill Claude CodeCodex
Track dice score separately for positive (mask-present) and negative (empty-mask) images to avoid division distortion.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Siamese network head that compares two embeddings via element-wise multiply, add, abs-diff, and squared-diff features for verification tasks.
not rated 60
+1 4mo ago A 39 tokens
Skill Claude CodeCodex
Sigmoid-transformed normalized RMSE that maps error from [0,inf) to a bounded (0,1] similarity score using R2-score ratio.
not rated 60
+1 4mo ago A 41 tokens
Skill Claude CodeCodex
Resample a 3D medical volume to a fixed depth N (e.g. 32) and feed the N slices as input channels to a 2D CNN with inchans=N instead of using a 3D conv backbone — gets the volumetric context for a fraction of the memory and lets you use any timm 2D pretrained model.
not rated 60
+1 4mo ago A 87 tokens
Skill Claude CodeCodex
Encode the empirical per-position event rate as a soft prior over slice index by binning normalized slice location and looking up a precomputed weight vector — adds class-aware spatial context to a per-slice classifier without changing the model.
not rated 60
+1 4mo ago A 53 tokens
Skill Claude CodeCodex
Pad 3D volumes with fewer slices than required by duplicating existing slices with slight brightness variation via convertScaleAbs.
not rated 60
+1 4mo ago A 33 tokens
Skill Claude CodeCodex
Encode game state as a Super Mini Map (SMM) with separate binary channels for players, ball, and ownership, bit-packed for efficient transfer in RL training.
not rated 60
+1 4mo ago A 42 tokens
Skill Claude CodeCodex
Cyclic cosine annealing LR that produces M diverse snapshots from a single training run for free ensembling.
not rated 60
+1 4mo ago A 29 tokens
Skill Claude CodeCodex
Aggregate patch-level count-regression predictions into image-level totals by multiplying each prediction by a boolean mask (x (x > tau)) instead of rounding, retaining fractional evidence above threshold while killing background noise.
not rated 60
+1 4mo ago A 48 tokens
Skill Claude CodeCodex
Turn sparse single-frame event labels (impacts, collisions, goals) into a usable detector training set by stamping the positive label onto a ±k-frame window around each event, then dropping any frame that contains no positives — gives the detector enough positive samples without changing the original annotation.
not rated 60
+1 4mo ago A 65 tokens
Skill Claude CodeCodex
Split large-image segmentation data into train/val by spatial rectangle regions with border buffer exclusion to prevent patch leakage.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Compute normalized spectral band ratios (NDWI, CCCI, NDVI) from multispectral imagery and threshold for binary segmentation of water, vegetation, or other targets.
not rated 60
+1 4mo ago A 40 tokens
Skill Claude CodeCodex
Keras callback implementing Stochastic Weight Averaging (SWA) — running mean of model weights over final training epochs.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Stratifies cross-validation folds by output sequence length to ensure balanced length distributions across train/val splits.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Normalize raw stroke coordinates to 0-255 range, resample at uniform arc-length spacing, then apply Ramer-Douglas-Peucker simplification.
not rated 60
+1 4mo ago A 42 tokens
Skill Claude CodeCodex
Render stroke sequences to grayscale images with temporal intensity encoding where earlier strokes are brighter and later strokes fade to encode drawing order.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Serialize structured ground truth (chart data, table rows, form fields) as special-token-delimited sequences for generative vision-language model training.
not rated 60
+1 4mo ago A 37 tokens
Skill Claude CodeCodex
Add random temporal offset to the center frame during training to augment temporal diversity in video-based models.
not rated 60
+1 4mo ago A 27 tokens
Skill Claude CodeCodex
Pad batch sequence lengths to multiples of 8 for efficient tensor core utilization on GPUs, with -100 masking for label padding.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Compiles a PyTorch model to a TensorRT FP16 engine via torchtensorrt for 2-5x inference speedup, saved as reusable TorchScript.
not rated 60
+1 4mo ago A 46 tokens
Skill Claude CodeCodex
Applies geometric and color augmentations at inference time and averages predictions to reduce variance.
not rated 60
+1 4mo ago A 23 tokens
Skill Claude CodeCodex
Assembles N extracted tiles into a sqrt(N) x sqrt(N) mosaic image for single-forward-pass CNN inference on whole slide images.
not rated 60
+1 4mo ago A 37 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: