machine-learning
304
vitcls-token
用于在Vision Transformer模型中实现特征维度转换（序列到空间、空间到序列）时，根据配置动态处理CLS Token（分类标记）的技能。确保模型在启用或禁用CLS Token时均能正确运行。
ECNU-ICALK
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
machine-learning
304
tf-agentslstm
指导用户使用TensorFlow的TF-Agents库构建针对多只股票的强化学习训练代码。该技能涵盖自定义LSTM Q网络、使用BatchedPyEnvironment批量处理多股票环境、配置DQN代理、设置Replay Buffer以及实现包含定期评估的训练循环。
ECNU-ICALK
data-ai
machine-learning
304
transformer
指导如何在CEUTrackActor类的compute_losses方法中集成基于SVD的正交高秩正规化损失。该技能包括提取注意力矩阵、计算奇异值、构建正则化项并将其加入总损失函数的步骤。
ECNU-ICALK
data-ai
machine-learning
304
transformertoken
实现一个用于ViT目标跟踪的动态Token组合函数，根据模板与搜索区域的余弦相似度自动选择direct、template_central或partition融合模式。
ECNU-ICALK
data-ai
machine-learning
304
customize-performance-criteria-with-examples
Rewords and paraphrases vocational training performance criteria and adds concrete workplace examples to strengthen them.
ECNU-ICALK
data-ai
machine-learning
304
bert-bi-lstm-sentence-similarity-implementation
Generates code to build a sentence similarity detection model by extracting BERT embeddings and feeding them into a Bi-LSTM network using TensorFlow and Hugging Face Transformers.
ECNU-ICALK
data-ai
machine-learning
304
character-attribute-blending-and-enhancement
This skill is used to transfer attributes from a source character description to a target character description. It ensures the target character retains their unique integrity without degradation, removes direct references to the source character, and enhances the resulting text.
ECNU-ICALK
data-ai
machine-learning
304
circuit-netlist-to-graph-conversion-for-gnn
Converts SPICE-like circuit netlists into NetworkX MultiGraphs with randomized parameters, specific node/edge feature schemas, and multi-edge handling for Graph Neural Network Reinforcement Learning models.
ECNU-ICALK
data-ai
machine-learning
304
customize-performance-criteria-with-examples
Rewords or paraphrases performance criteria for training contexts and adds concrete, observable workplace examples to strengthen assessment context.
ECNU-ICALK
data-ai
machine-learning
304
deep-learning-prediction-with-chaid-and-time-series-splitting
Executes binary classification using DNN and CNN models, with and without CHAID feature selection, using a rolling time-series training window. Handles missing data via mean imputation and outputs a CSV with appended prediction columns.
ECNU-ICALK
data-ai
machine-learning
304
ev-recommendation-with-weighted-criteria-scoring
Recommends top electric vehicles based on user-defined technical constraints (features, range, body type, brand) and calculates a weighted percentage match score for ranking.
ECNU-ICALK
data-ai
machine-learning
304
extract-pre-softmax-embeddings-to-dictionary
Extracts embedding vectors from the layer immediately preceding the Softmax layer of a pre-trained model (e.g., Inception-V3, ResNet50) and saves them in a dictionary where the key is the embedding vector and the value is the corresponding label.
ECNU-ICALK
data-ai
machine-learning
304
julia-matrix-data-operations
Эксперт по Julia для реализации функций условного изменения размерности данных (reshape) и последовательного повторения элементов матрицы с соблюдением строгих типизаций.
ECNU-ICALK
data-ai
machine-learning
304
keras-grid-search-script-generator
Generates a Python script using Keras and scikit-learn to perform grid search hyperparameter tuning. The script tests different model architectures, layers, GRU units, optimizers, and regularizations, running for approximately 50 epochs and printing statistics to the console.
ECNU-ICALK
data-ai
machine-learning
304
matlab-arima-model-selection-and-forecasting
Generates MATLAB code to perform time series forecasting by testing multiple ARIMA models, selecting the best one based on AIC, and plotting the forecast.
ECNU-ICALK
data-ai
machine-learning
304
matlab-ldr-matrix-decomposition
Implements an iterative LDR decomposition of a real matrix X using QR factorization, following specific initialization, update rules, and convergence criteria.
ECNU-ICALK
data-ai
machine-learning
304
matlab-traffic-flow-simulation-with-car-following-models
Generate executable MATLAB code to simulate traffic flow on a single lane using specified car-following models (e.g., IDM, Gipps, Krauss). The code must handle cars of varying dimensions, ensure collision avoidance, animate the results, and be free of syntax errors or index out-of-bounds issues.
ECNU-ICALK
data-ai
machine-learning
304
plot-catboost-feature-importance-with-custom-styling
Generates a Python function to train a CatBoost model on a DataFrame and plot feature importances. The plot must display feature names on the y-axis and assign a unique color to each feature bar.
ECNU-ICALK
data-ai
machine-learning
304
python-pandas-conditional-column-transformation
A skill to conditionally update a target column in a pandas DataFrame based on a reference column and specific string matching rules, handling nulls and type errors.
ECNU-ICALK
data-ai
machine-learning
304
pytorch-accuracy-calculation-conversion-crossentropy-to-mse
Converts PyTorch training loop code from using CrossEntropyLoss to MSELoss, specifically updating the accuracy calculation logic from argmax-based comparison to rounding-based comparison to handle regression outputs.
ECNU-ICALK
data-ai
machine-learning
304
pytorch-classification-for-variable-length-1d-arrays
A skill to classify samples from two lists of variable-length 1D arrays using PyTorch. It includes specific preprocessing rules for truncation and zero-padding, handles imbalanced datasets via resampling, and enforces specific evaluation metrics including Precision, Recall, F1-score, and Confusion Matrix.
ECNU-ICALK
data-ai
machine-learning
304
pytorch-csv-image-data-loading-and-vgg-training
Load flattened image data from a CSV file with specific schema (label + pixel columns), create train/validation/test data loaders, and train a retrained VGG classification network.
ECNU-ICALK
data-ai