Getting Started Guide

pip install wandb

wandb login --host <your-host> <YOUR API TOKEN>

WANDB_BASE_URL = '<your-host>' #e.g company.wandb.io if on dedicated
wandb.login(host=os.getenv("WANDB_BASE_URL"), key=os.getenv("WANDB_API_KEY"))

import wandb

wandb.init(project="my-sample-project",   
           entity="<enter team name>",	        # Team
           group='my_group',	        # for organizing runs (e.g. distributed training)
           job_type='training',		# for organizing runs (e.g. preprocessing vs. training)
           config={'hyperparam1': 24,   # Hyperparams and other config
		   'hyperparam2': 'resnet'})

wandb.log({"my_metric": some_scalar_value})

wandb.init()

for i in range(5):
    wandb.log({"my_metric": i})

wandb.summary["my_metric"] = 2 # 2 instead of the default 4

wandb.finish()

wandb.log({"my_image": wandb.Image("my_image.jpg"))

# Add data as a list of lists or pandas dataframe
my_data = [
  [0, wandb.Image("img_0.jpg"), 0, 0],
  [1, wandb.Image("img_1.jpg"), 8, 0],
  [2, wandb.Image("img_2.jpg"), 7, 1],
  [3, wandb.Image("img_3.jpg"), 1, 1]
]
          
# create a wandb.Table() with corresponding columns
columns=["id", "image", "prediction", "truth"]
test_table = wandb.Table(data=my_data, columns=columns)

# Add data incrementally
for img_id, img in enumerate(mnist_test_data):
    true_label = mnist_test_data_labels[img_id]
    guess_label = my_model.predict(img)
    test_table.add_data(img_id, wandb.Image(img), \
                         guess_label, true_label)

wandb.log({"test_table": test_table})

# 1. Log a dataset version as an artifact
import wandb
import os

# Initialize a new W&B run to track this job
run = wandb.init(project="artifacts-quickstart", job_type="dataset-creation")

# Create a sample dataset to log as an artifact
f = open('my-dataset.txt', 'w')
f.write('Imagine this is a big dataset.')
f.close()

# Create a new artifact, which is a sample dataset
dataset = wandb.Artifact('my-dataset', type='dataset')
# Add files to the artifact, in this case a simple text file
dataset.add_file('my-dataset.txt')
# Log the artifact to save it as an output of this run
run.log_artifact(dataset)

wandb.finish()

import wandb
run = wandb.init()
# Indicate we are using a dependency
artifact = run.use_artifact('dummy-team/that_was_easy/my-dataset:v3', type='dataset')
artifact_dir = artifact.download()

f"{org_entity}/wandb-registry-{registry_name}/{collection_name}"

import wandb

# Initialize a run
run = wandb.init(entity="<team_entity>", project="<project>")

# Create an artifact object
artifact = wandb.Artifact(name="<artifact_name>", type="<artifact_type>")

# Define required registry definitions 
org_entity = "<organization_entity>"
registry_name = "<registry_name>"
collection_name = "<collection_name>"
target_path = f"{org_entity}/wandb-registry-{registry_name}/{collection_name}"

# Link the artifact to a collection
run.link_artifact(artifact = artifact, target_path = target_path)

run.finish()

{ORG_ENTITY_NAME}/wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}

import wandb
#Define team and org
TEAM_ENTITY_NAME = "<team_entity_name>"
ORG_ENTITY_NAME = "<org_entity_name>"

REGISTRY_NAME = "<registry_name>"  
COLLECTION_NAME = "<collection_name>"

run = wandb.init(
        entity=TEAM_ENTITY_NAME, project="<project_name>")

artifact = wandb.Artifact(name="<artifact_name>", type="<collection_type>")
artifact.add_file(local_path="<local_path_to_artifact>")

target_path=f"{ORG_ENTITY_NAME}/wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}"
run.link_artifact(artifact = artifact, target_path = target_path)

import wandb

ORG_ENTITY_NAME = '<org-entity-name>'
REGISTRY_NAME = '<registry-name>'
COLLECTION_NAME = '<collection-name>'
ALIAS = '<artifact-alias>'
INDEX = '<artifact-index>'

run = wandb.init()  # Optionally use the entity, project arguments to specify where the run should be created

registered_artifact_name = f"{ORG_ENTITY_NAME}/wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}:{ALIAS}"
registered_artifact = run.use_artifact(artifact_or_name=name)  # marks this artifact as an input to your run
artifact_dir = registered_artifact.download()  

# Artifact name with version index specified
f"{ORG_ENTITY}/wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}:v{INDEX}"

# Artifact name with alias specified
f"{ORG_ENTITY}/wandb-registry-{REGISTRY_NAME}/{COLLECTION_NAME}:{ALIAS}"

from lightning.pytorch.loggers import WandbLogger
from lightning.pytorch import Trainer
from lightning.pytorch.callbacks import ModelCheckpoint


checkpoint_callback = ModelCheckpoint(monitor='val_accuracy', mode='max')

wandb_logger = WandbLogger(project='MNIST', # group runs in "MNIST" project
                           entity='smle-demo',
                           log_model='all') # log all new checkpoints during training
trainer = Trainer(
    logger=wandb_logger,                    # W&B integration
    callbacks=[log_predictions_callback,    # logging of sample predictions
               checkpoint_callback],        # our model checkpoint callback
    accelerator="gpu",                      # use GPU
    max_epochs=5)        

os.environ["WANDB_PROJECT"] = "<my-amazing-project>"  # name your W&B project
os.environ["WANDB_LOG_MODEL"] = "checkpoint"  # log all model checkpoints

from transformers import TrainingArguments, Trainer

args = TrainingArguments(..., report_to="wandb")  # turn on W&B logging
trainer = Trainer(..., args=args) 

wandb.init(host="https://api.wandb.ai")

wandb.init(name="my_awesome_run")

os.environ["WANDB_SILENT"] = "true"

%env WANDB_SILENT=true

WANDB_SILENT=true