Skill Claude CodeCodex
Selects the top-N most informative tiles from a gigapixel whole slide image by ranking on pixel intensity sum, keeping tiles with the most tissue content.
not rated 60
+1 4mo ago A 39 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
Pre-shard TFRecords into N files each balanced along 3 axes (patient, target, image-count), then KFold over file indices for leak-free triple-stratified folds.
not rated 60
+1 4mo ago A 47 tokens
Skill Claude CodeCodex
Extract volumetric features from 3D segmentation masks including scan/tumor pixel ratios, tumor percentage, and tumor centroid coordinates.
not rated 60
+1 4mo ago A 35 tokens
cv-tversky-loss
172Skill Claude CodeCodex
Tversky loss with independent alpha/beta constants to separately penalize false positives and false negatives in imbalanced segmentation.
not rated 60
+1 4mo ago A 30 tokens
Skill Claude CodeCodex
Train segmentation with BCE loss first for stable convergence, then fine-tune with Lovasz-hinge on raw logits for IoU-optimal predictions.
not rated 60
+1 4mo ago A 39 tokens
Skill Claude CodeCodex
Chain a study-level classifier with an image-level detector, merging class probabilities and bounding boxes into a unified prediction.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Use a lightweight slice-classifier to find the Z-range containing an organ in a CT volume, then crop and trilinear-resample that sub-volume into a fixed shape for a heavier 3D classifier — replaces "use the whole volume" with "use only the relevant slab" at a fraction of the FLOPs.
not rated 60
+1 4mo ago A 77 tokens
Skill Claude CodeCodex
Efficiently sample N evenly-spaced frames from a video using OpenCV grab/retrieve pattern with optional resize for batch face detection or classification.
not rated 60
+1 4mo ago A 36 tokens
Skill Claude CodeCodex
Extracts calibrated yes/no probabilities from a VQA model by masking all logits except yes/no token variants and renormalizing via softmax.
not rated 60
+1 4mo ago A 39 tokens
Skill Claude CodeCodex
Combines gradual learning rate warmup with cosine annealing decay for stable fine-tuning of pretrained models.
not rated 60
+1 4mo ago A 33 tokens
Skill Claude CodeCodex
Propagates image-level multi-labels to individual instances as weak supervision for instance-level training.
not rated 60
+1 4mo ago A 29 tokens
Skill Claude CodeCodex
BCE loss with per-class asymmetric positive/negative weights to match competition metrics or handle class imbalance in multilabel classification.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Ensemble predictions from heterogeneous vision-language models by blending their output embeddings with fixed scalar weights in embedding space.
not rated 60
+1 4mo ago A 28 tokens
Skill Claude CodeCodex
Convert bounding boxes between YOLO (normalized center), VOC (absolute corners), and COCO (absolute xywh) formats with image dimension scaling.
not rated 60
+1 4mo ago A 37 tokens
Skill Claude CodeCodex
Load large LLMs with 4-bit NF4 quantization and optional double quantization via BitsAndBytes to reduce GPU memory by 4x while preserving inference quality.
not rated 60
+1 4mo ago A 47 tokens
Skill Claude CodeCodex
Shared-backbone neural network with actor (policy) and critic (value) heads for grid-based game agent RL training.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Dynamically reduce maxtokens and batch size as wall-clock time approaches a cutoff to ensure all inputs get processed.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Ensemble multi-model LLM predictions using weighted combination of average probability, cross-model agreement ratio, and max confidence.
not rated 60
+1 4mo ago A 30 tokens
Skill Claude CodeCodex
Parse sequential yes/no answers to build inclusion/exclusion sets, then apply compound boolean filters to narrow a candidate list.
not rated 60
+1 4mo ago A 31 tokens
Skill Claude CodeCodex
Steers LLM output format by injecting a partial assistant response into the chat template before generation, forcing structured output without fine-tuning.
not rated 60
+1 4mo ago A 37 tokens
Skill Claude CodeCodex
Batch-compute perplexity for multiple texts using a causal LM with proper padding, shifted labels, and pad-token masking for efficient GPU utilization.
not rated 60
+1 4mo ago A 37 tokens
Skill Claude CodeCodex
Force-clamp free-form LLM output to binary yes/no with keyword matching and a fallback default for constrained environments.
not rated 60
+1 4mo ago A 30 tokens
Skill Claude CodeCodex
Hierarchical binary search over entity space by asking category, region, then first-letter questions to narrow candidates before guessing.
not rated 60
+1 4mo ago A 33 tokens
Skill Claude CodeCodex
Extract final numeric answers from LaTeX \boxed{} notation in LLM math reasoning output, scanning matches in reverse for robustness.
not rated 60
+1 4mo ago A 33 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: