tracebloc Python SDK

pip install "tracebloc[pytorch]>=1.2.47"                       # most users
# pip install "tracebloc[sklearn]>=1.2.47"                     # scikit-learn, incl. XGBoost / CatBoost / LightGBM
# pip install "tracebloc[xgboost]>=1.2.47"                     # one boosting backend only (or: catboost, lightgbm)
# pip install "tracebloc[lifelines,scikit-survival]>=1.2.47"   # survival analysis
# pip install "tracebloc[all]>=1.2.47"                         # pytorch + sklearn + lifelines + scikit-survival
# pip install "tracebloc[training]>=1.2.82"                    # the training versions, to convert your model (Python 3.11–3.13)

from tracebloc import User

# 1. Log in to your tracebloc account
user = User()  # prompts for email and password

# 2. Upload a model file (must be in your current directory or provide a path)
user.upload_model(model_name="densenet.py")

# To upload with pretrained weights (weights file must be in the same directory):
# user.upload_model(model_name="densenet.py", weights=True)

# 3. Link model with a dataset from your use case
#    Find the Dataset ID on your use case page at ai.tracebloc.io
training_plan = user.link_model_dataset(dataset_id="YOUR_DATASET_ID")

# 4. Configure training parameters
training_plan.experiment_name("My first experiment")
training_plan.epochs(10)
training_plan.optimizer("adam")
training_plan.learning_rate({"type": "constant", "value": 0.001})
training_plan.validation_split(0.2)

# 5. Review the experiment's settings
training_plan.get_training_plan()

# 6. Start training
training_plan.start()

# 7. Log out when done
user.logout()

model_dir = "model-zoo/model_zoo/<task>/pytorch"

# Writes <template>_weights.pkl next to <template>.py
user.fetch_seed_weights("<template>", directory=model_dir)
user.upload_model(model_name=f"{model_dir}/<template>.py", weights=True)