圖像分類：來自13個(gè)Kaggle項(xiàng)目的經(jīng)驗(yàn)總結(jié)
Intel Image Classification：https://www.kaggle.com/puneet6060/intel-image-classification
Recursion Cellular Image Classification：https://www.kaggle.com/c/recursion-cellular-image-classification SIIM-ISIC Melanoma Classification：https://www.kaggle.com/c/siim-isic-melanoma-classification APTOS 2019 Blindness Detection：https://www.kaggle.com/c/aptos2019-blindness-detection/notebooks Diabetic Retinopathy Detection：https://www.kaggle.com/c/diabetic-retinopathy-detection ML Project?—?Image Classification：https://www.kaggle.com/c/image-classification-fashion-mnist/notebooks Cdiscount’s Image Classification Challenge：https://www.kaggle.com/c/cdiscount-image-classification-challenge/notebooks Plant seedlings classifications： https://www.kaggle.com/c/plant-seedlings-classification/notebooks Aesthetic Visual Analysis： https://www.kaggle.com/c/aesthetic-visual-analysis/notebooks
數(shù)據(jù) 模型 損失函數(shù)
圖像預(yù)處理 + EDA
Visualisation： https://www.kaggle.com/allunia/protein-atlas-exploration-and-baseline#Building-a-baseline-model- Dealing with Class imbalance：https://www.kaggle.com/rohandeysarkar/ultimate-image-classification-guide-2020 Fill missing values (labels, features and, etc.)：https://www.kaggle.com/datafan07/analysis-of-melanoma-metadata-and-effnet-ensemble Normalisation?： https://www.kaggle.com/vincee/intel-image-classification-cnn-keras Pre-processing： https://www.kaggle.com/ratthachat/aptos-eye-preprocessing-in-diabetic-retinopathy#3.A-Important-Update-on-Color-Version-of-Cropping-&-Ben's-Preprocessing
數(shù)據(jù)增強(qiáng)
Horizontal Flip： https://www.kaggle.com/datafan07/analysis-of-melanoma-metadata-and-effnet-ensemble Random Rotate and Random Dihedral：https://www.kaggle.com/iafoss/pretrained-resnet34-with-rgby-0-460-public-lb Hue, Saturation, Contrast, Brightness, Crop：https://www.kaggle.com/cdeotte/triple-stratified-kfold-with-tfrecords Colour jitter： https://www.kaggle.com/nroman/melanoma-pytorch-starter-efficientnet
開發(fā)一個(gè)基線
開發(fā)一個(gè)足夠大可以過擬合的模型
添加更多層 使用更好的結(jié)構(gòu) 更完善的訓(xùn)練流程
Residual Networks Wide Residual Networks Inception EfficientNet Swish activation Residual Attention Network
Mixed-Precision Training Large Batch-Size Training Cross-Validation Set Weight Initialization Self-Supervised Training (Knowledge Distillation) Learning Rate Scheduler Learning Rate Warmup Early Stopping Differential Learning Rates Ensemble Transfer Learning Fine-Tuning
Adding Dropout： https://www.kaggle.com/allunia/protein-atlas-exploration-and-baseline Adding or changing the position of Batch Norm：https://www.kaggle.com/allunia/protein-atlas-exploration-and-baseline Data augmentation： https://www.kaggle.com/cdeotte/triple-stratified-kfold-with-tfrecords Mixup：https://arxiv.org/abs/1710.09412 Weight regularization： https://www.kaggle.com/allunia/protein-atlas-exploration-and-baseline Gradient clipping：https://www.kaggle.com/allunia/protein-atlas-exploration-and-baseline
Label smoothing Focal loss SparseMax loss and Weighted cross-entropy BCE loss, BCE with logits loss and Categorical cross-entropy loss Additive Angular Margin Loss for Deep Face Recognition
評估 + 錯(cuò)誤分析
Tracking metrics and Confusion matrix：https://www.kaggle.com/vincee/intel-image-classification-cnn-keras Grad CAM： https://arxiv.org/pdf/1610.02391v1.pdf Test Time Augmentation (TTA)：https://www.kaggle.com/iafoss/pretrained-resnet34-with-rgby-0-460-public-lb
實(shí)習(xí)/全職編輯記者招聘ing
加入我們，親身體驗(yàn)一家專業(yè)科技媒體采寫的每個(gè)細(xì)節(jié)，在最有前景的行業(yè)，和一群遍布全球最優(yōu)秀的人一起成長。坐標(biāo)北京·清華東門，在大數(shù)據(jù)文摘主頁對話頁回復(fù)“招聘”了解詳情。簡歷請直接發(fā)送至[email protected]
評論
圖片
表情