Skill Claude CodeCodex
Stratifies CV folds at the patient level rather than image level, preventing data leakage when multiple images exist per patient.
not rated 60
+1 4mo ago A 34 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
Apply class-specific confidence thresholds by inferring the dominant class per image and indexing into a per-class threshold array.
not rated 60
+1 4mo ago A 28 tokens
Skill Claude CodeCodex
Optimize per-class decision thresholds for macro-F1 by replacing the non-differentiable hard threshold with a sigmoid-sharpened soft-F1 surrogate and fitting the per-class threshold vector via least-squares — averaged over multiple random validation splits to suppress overfitting on rare classes.
not rated 60
+1 4mo ago A 66 tokens
Skill Claude CodeCodex
Fit a per-label probability calibrator on out-of-fold scores using Platt scaling (logistic regression on raw scores) and fall back to isotonic regression for labels where the logistic doesn't converge — pickle the dict of fitted calibrators and apply at inference for a small but free leaderboard lift on multi-label…
not rated 60
+1 4mo ago A 72 tokens
Skill Claude CodeCodex
Train separate models per imaging modality (FLAIR/T1w/T1wCE/T2w) and average their predictions for final ensemble.
not rated 60
+1 4mo ago A 37 tokens
Skill Claude CodeCodex
Trains one specialized model per imaging modality or series type, routing inputs by metadata at inference for modality-specific feature learning.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Single CNN backbone with one shallow Dense neck per organ and mixed sigmoid (binary) + softmax (multi-class severity) heads, trained with a dict of losses so each organ is calibrated independently while sharing visual features.
not rated 60
+1 4mo ago A 54 tokens
Skill Claude CodeCodex
Aggregate per-slice CNN predictions into a single patient-level injury score by mean-pooling across TTA copies first, then max-pooling across slices — the worst-slice wins, which matches the medical reality that one bad slice is enough to grade the patient.
not rated 60
+1 4mo ago A 62 tokens
Skill Claude CodeCodex
Normalize high-dynamic-range satellite or medical imagery to [0,1] using per-channel percentile clipping to suppress outliers while preserving relative contrast.
not rated 60
+1 4mo ago A 36 tokens
Skill Claude CodeCodex
Grid-searches the optimal classification threshold to maximize probabilistic F-beta score on validation predictions.
not rated 60
+1 4mo ago A 27 tokens
Skill Claude CodeCodex
Group near-duplicate images by perceptual hash (pHash) as a zero-cost baseline signal for product or image matching.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Convert (x, y, class) point annotations into a CNN classification training set by cropping fixed-size square patches centered on each point, using a numpy shape check to silently reject border-clipped crops.
not rated 60
+1 4mo ago A 49 tokens
Skill Claude CodeCodex
Stitch overlapping tile predictions into a full-resolution output by accumulating probabilities and dividing by per-pixel overlap counts.
not rated 60
+1 4mo ago A 33 tokens
Skill Claude CodeCodex
Apply lower dropout in shallow/final U-Net layers and higher dropout in deep layers to preserve spatial detail while regularizing abstract features.
not rated 60
+1 4mo ago A 33 tokens
Skill Claude CodeCodex
Custom training callback that computes Quadratic Weighted Kappa on validation data each epoch and checkpoints the best model.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Samples a fixed number of slices from variable-length CT/MRI stacks using quantile indexing to produce consistent input depth.
not rated 60
+1 4mo ago A 32 tokens
Skill Claude CodeCodex
Sets the binary classification threshold as a prediction quantile matching the expected positive prevalence rate, avoiding manual threshold tuning.
not rated 60
+1 4mo ago A 34 tokens
Skill Claude CodeCodex
Extract dense per-pixel motion fields between consecutive video frames using a pretrained RAFT model, producing an HxWx2 flow tensor that can be channel-stacked with RGB or used as a standalone motion feature for action / impact / event detection.
not rated 60
+1 4mo ago A 57 tokens
Skill Claude CodeCodex
Converts a raster image to a size-bounded SVG via K-means color quantization, contour extraction, importance-ranked polygon assembly, and progressive simplification.
not rated 60
+1 4mo ago A 42 tokens
Skill Claude CodeCodex
Load fluorescence microscopy images stored as 4 separate single-channel PNGs (red microtubules, green target protein, blue nucleus, yellow ER) into a single HxWx4 tensor, preserving the biological semantics of each channel rather than collapsing to RGB.
not rated 60
+1 4mo ago A 64 tokens
Skill Claude CodeCodex
Encodes binary segmentation masks into compressed RLE format for efficient storage and submission.
not rated 60
+1 4mo ago A 23 tokens
Skill Claude CodeCodex
Brute-force a 2D rotation angle over a coarse grid to align field-coordinate points with image-plane detections when the camera angle is unknown.
not rated 60
+1 4mo ago A 36 tokens
Skill Claude CodeCodex
Test-time augmentation via 4 rotation angles (0/90/180/270), applying inverse rotation to each prediction before averaging.
not rated 60
+1 4mo ago A 34 tokens
Skill Claude CodeCodex
Uses Facebook's semi-weakly supervised ImageNet-pretrained models (trained on 940M unlabeled images) as CNN backbones for stronger transfer learning than standard supervised pretraining.
not rated 60
+1 4mo ago A 47 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: