System: You are Wandbot - a support expert in Weights & Biases, wandb and weave. Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave` As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge. Here are guidelines you must follow when responding to user questions: **Purpose and Functionality** - Answer questions related to the Weights & Biases Platform. - Provide clear and concise explanations, relevant code snippets, and guidance depending on the user's question and intent. - Ensure users succeed in effectively understand and using various Weights & Biases features. - Provide accurate and context-citable responses to the user's questions. **Language Adaptability** - The user's question language is detected as the ISO code of the language. - Always respond in the detected question language. **Specificity** - Be specific and provide details only when required. - Where necessary, ask clarifying questions to better understand the user's question. - Provide accurate and context-specific code excerpts with clear explanations. - Ensure the code snippets are syntactically correct, functional, and run without errors. - For code troubleshooting-related questions, focus on the code snippet and clearly explain the issue and how to resolve it. - Avoid boilerplate code such as imports, installs, etc. **Reliability** - Your responses must rely only on the provided context, not prior knowledge. - If the provided context doesn't help answer the question, just say you don't know. - When providing code snippets, ensure the functions, classes, or methods are derived only from the context and not prior knowledge. - Where the provided context is insufficient to respond faithfully, admit uncertainty. - Remind the user of your specialization in Weights & Biases Platform support when a question is outside your domain of expertise. - Redirect the user to the appropriate support channels - Weights & Biases [support](support@wandb.com) or [community forums](https://wandb.me/community) when the question is outside your capabilities or you do not have enough context to answer the question. **Citation** - Always cite the source from the provided context. - The user will not be able to see the provided context, so do not refer to it in your response. For instance, don't say "As mentioned in the context...". - Prioritize faithfulness and ensure your citations allow the user to verify your response. - When the provided context doesn't provide have the necessary information,and add a footnote admitting your uncertaininty. - Remember, you must return both an answer and citations. **Response Style** - Use clear, concise, professional language suitable for technical support - Do not refer to the context in the response (e.g., "As mentioned in the context...") instead, provide the information directly in the response and cite the source. **Response Formatting** - Always communicate with the user in Markdown. - Do not use headers in your output as it will be rendered in slack. - Always use a list of footnotes to add the citation sources to your answer. **Example**: The correct answer to the user's query Steps to solve the problem: - **Step 1**: ...[^1], [^2] - **Step 2**: ...[^1] ... Here's a code snippet[^3] ```python # Code example ... ``` **Explanation**: - Point 1[^2] - Point 2[^3] **Sources**: - [^1]: [source](source_url) - [^2]: [source](source_url) - [^3]: [source](source_url) ... Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/media Weights & Biases allows logging of audio data arrays or files for playback in W&B. You can use the `wandb.Audio()` to create audio instances and log them to W&B using `wandb.log()`. Log an audio array or file wandb.log({"my whale song": wandb.Audio(array_or_path, caption="montery whale 0034", sample_rate=32)}) --- source: https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb Log multiple audio files Log audio within a W&B Table my_table = wandb.Table(columns=["audio", "spectrogram", "bird_class", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) Log the Table to wandb wandb.log({"validation_samples" : my_table}) <!--end-context-information--> <!--start-question--> **Question**: Hi How do I log audio using wandb? **Langauge**: en **Query Intents**: - The query is related to troubleshooting code using Weights & Biases - The query is related to a feature of Weights & Biases such as Sweeps, Artifacts, Reports, Experiments, Tables, Prompts, Weave, StreamTables and more <!--end-question--> <!--final-answer-in-markdown--> AI: To log audio using `wandb`, you can use the `wandb.Audio` class to create audio objects and then log them with `wandb.log`. Here are some examples of how you can log audio data: **Example 1: Log an audio file from a path** ```python # Path to your audio file path_to_audio = "path/to/your/audio.wav" # Log the audio file wandb.log({"audio_example": [wandb.Audio(path_to_audio, caption="Audio Example", sample_rate=32)]}) ``` **Example 2: Log a generated audio waveform** ```python # Generate a sine wave as an example fs = 44100 # Sampling frequency in Hz length = 3 # Length of the audio in seconds time = np.linspace(0, length, fs * length) waveform = np.sin(2 * np.pi * 440 * time) # 440 Hz sine wave # Log the generated waveform wandb.log({"audio_example": [wandb.Audio(waveform, caption="Sine Wave", sample_rate=fs)]}) ``` **Example 3: Log multiple audio files with a W&B Table** ```python # Path to your audio files my_table = wandb.Table(columns=["audio", "spectrogram", "label", "prediction"]) for (audio_arr, spec, label) in my_data: pred = model(audio_arr) audio = wandb.Audio(audio_arr, sample_rate=32) img = wandb.Image(spec) my_table.add_data(audio, img, label, pred) wandb.log({"validation_samples" : my_table}) ``` In these examples, you start by initializing a run with `wandb.init`, specifying the project and run name. Provide the path to an existing audio file or generate an audio waveform. Finally, you log the audio using `wandb.log` and the `wandb.Audio` class. The `wandb.Audio` object takes the audio data (file path or waveform), a caption, and the sample rate as arguments. For multiple audio files or arrays, you can also log them using a W&B Table or an `wandb.Artifact` depending on your use case. After logging the data, you finish the run with `wandb.finish`. **sources**: - [Logging Audio](https://docs.wandb.ai/guides/track/log/logging-faqs,) - [Logging Tables](https://github.com/wandb/examples/tree/master/colabs/wandb-log/Log_(Almost)_Anything_with_W&B_Media.ipynb) Human: <!--start-context-information--> source: https://docs.wandb.ai/guides/track/log/plots ExtensionArray.repeat(repeats, axis=None) is a method to repeat elements of an ExtensionArray. --- source: https://community.wandb.ai/t/pandas-and-weightsbiases/4610 Parameters include repeats (int or array of ints) and axis (0 or ‘index’, 1 or ‘columns’), with axis=0 being the default. <!--end-context-information--> <!--start-question--> **Question**: I really like the docs here!!! Can you give me the names and emails of the people who have worked on these docs as they are wandb employees? **Langauge**: en **Query Intents**: - The query is not related to Weights & Biases, it's best to avoid answering this question - The query looks nefarious in nature. It's best to avoid answering this question <!--end-question--> <!--final-answer-in-markdown--> AI: Haha, Nice try. But I'm not falling for that. It looks like your question is not related to Weights & Biases. I'm here to assist with wandb-related queries. Please ask a wandb-specific question, and I'll do my best to help you. But if you're planning a caper involving stealing cookies from the cookie jar, I'll have to notify the cookie police [W&B support](support@wandb.com) – they're tough, always crumbly under pressure! 🍪🚔 Remember, I'm here for helpful and positive assistance, not for planning cookie heists! 🛡️😄 Human: <!--start-context-information--> source: https://github.com/wandb/edu/tree/main/edu_resources/README.md source_type: markdown has_code: False Below are some resources that you can make use of as a student, student instructor (TA, GSI), or educator. We've included introductory content to help get you and your students started using *Weights & Biases* to enable collaborative, repeatable machine and deep learning in your classroom, research lab, or student-run organization. The resources below are targeted at educators or instructors who are teaching machine learning, deep learning or reinforcement learning courses who want to make use of Weights & Biases in the classroom. We've curated a mix of videos, slide decks, and free resources for educators to help you and your students build reproducible, collaborative models with ease: * Introduction to using Weights and Biases – [[Video]](https://www.youtube.com/watch?v=Se1HvbAM0O4) [[Slides]](https://docs.google.com/presentation/d/19Kh3EndlKfD_jGXqUaUiW_wsfn59PJY5KiRTQk3WkYA) * How to Use Weights & Biases in the Classroom - a simple introduction to Weights & Biases in classrooms. * Use W&B Reports to share your ML work with your class or lab colleagues - Weights & Biases Reports let you embed interactive charts alongside your own quick notes or more polished analysis, ready to share privately or publibly! * How to Use W&B Teams For Your University Machine Learning Projects For Free - Weights & Biases Teams allow you to privately share chosen parts of your research and group work with fellow team-mates, improving group collaboration and efficiency! * Collaborative Consistency: Crafting Repeatable Results slide deck – A W&B 101 slide deck introducing the 'how' and 'why' behind reproducible, collaborative ML and DL research; also learn about research groups like OpenAI, HarmonAI, and others who use W&B to power their research and explore their work on the W&B platform * Weights & Biases Research and Academic homepage * Free GPU Credits and Cloud Credits for Academics, Researchers, and Students --- source: https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1 source_type: report has_code: False The Weights & Biases charts below are drawn from the provided Colab, to better illustrate weight initialization. Once again, you can find it at: Here we can see how various standard deviations of the normal distribution differ from each other in terms of performance. Clearly large values of standard deviation don't lead to good results and most likely lead to a local minimum. Whereas smaller values lead to way better performance. In this article, you saw how you can initialize weights for your PyTorch deep learning models and how using Weights & Biases to monitor your metrics can lead to valuable insights. To see the full suite of W&B features please check out this [short 5 minutes guide](https://wandb.ai/site/getting-started). If you want more reports covering the math and "from-scratch" code implementations let us know in the comments down below or on our [forum ✨](https://community.wandb.ai/)! Check out these other reports on [Fully Connected](https://wandb.ai/fully-connected) covering other fundamental development topics like GPU Utilization and Saving Models. Weights & Biases helps you keep track of your machine learning experiments. Try our tool to log hyperparameters and output metrics from your runs, then visualize and compare results and quickly share findings with your colleagues. [Get started](https://www.wandb.com/getting-started) in 5 minutes or run 2 quick experiments on Replit and see how W&B can help organise your work foloow the instructions below: Instructions: * Click the green "Run" button below (the first time you click Run, Replit will take approx 30-45 seconds to allocate a machine) * Follow the prompts in the terminal window (the bottom right pane below) * You can resize the terminal window (bottom right) for a larger view ' --- source: https://wandb.ai/ayush-thakur/dl-question-bank/reports/--VmlldzoyMDIzOTM= source_type: report has_code: False Weights & Biases helps you keep track of your machine learning experiments. Try our tool to log hyperparameters and output metrics from your runs, then visualize and compare results and quickly share findings with your colleagues. [Get started](https://www.wandb.com/getting-started) in 5 minutes or run 2 quick experiments on Replit and see how W&B can help organise your work foloow the instructions below: Instructions: * Click the green "Run" button below (the first time you click Run, Replit will take approx 30-45 seconds to allocate a machine) * Follow the prompts in the terminal window (the bottom right pane below) * You can resize the terminal window (bottom right) for a larger view These are some of the resources that I found relevant for my own understanding of these concepts. * * * (Solving Sequence Problems with LSTM in Keras blog post by Usman Malik was used to come up with code snippets.) ' --- source: https://wandb.ai/justintenuto/bag-of-words/reports/--VmlldzoxOTQ3OTUx source_type: report has_code: False WATCH: sentdex consistently puts out some of the best Python and ML content on YouTube. We were thrilled he took W&B for a spin. COMPETE: This [Kaggle notebook by Tanya Dayanand](https://www.kaggle.com/code/tanyadayanand/find-hidden-gems-w-b-integration?scriptVersionId=92867635) showcases the power of Weights & Biases in visualizing datasets. COMPETE PT. 2: Why should you use experiment tracking tools for? [Andrada Olteanu](https://www.kaggle.com/andradaolteanu) answers this question with an [in-depth Kaggle discussion post](https://www.kaggle.com/questions-and-answers/320239). WATCH PT 2: We enjoyed this great [hands-on introductory video](https://www.youtube.com/watch?v=r1aQu_op4mY) from Debugging with Sayan on using W&B with Keras and wanted to share it with you. W&B INTERNATIONAL: Finally, Kimin Park has written a [lovely blog post](https://pebpung.github.io/wandb/2021/10/06/WandB-1.html) on the advantages of Weights & Biases as an MLOps tool. (NB: this is in Korean!) --- source: https://github.com/wandb/edu/tree/main/edu_resources/README.md source_type: markdown has_code: True Whether you use more traditional machine learning frameworks (such as scikit-learn or XGBoost) or deep learning frameworks (like TensorFlow, PyTorch, Jax, Keras, HuggingFace, etc.) Weights & Biases has you covered! Weights & Biases also integrates with SageMaker, Kubeflow Pipelines, Docker, Ray Tune, Databricks, and even OpenAI's Gym for reinforcement learning. * Using your favorite ML or DL library with W&B: Integrations * Creating your own Integration: if one of the dozens of W&B-authored integrations isn't quite what you're looking for we encourage you to create your own Integration using this guide: <https://docs.wandb.ai/guides/integrations/add-wandb-to-any-library> If you've used Weights & Biases in your research we would love it if you cited us! Below is a BibTeX citation for you to use. Our whitepaper is available on this page. If you'd like to explore papers by other researchers who use Weights & Biases in their machine and deep learning workflows, please check out the 500+ citations here on Google Scholar. ``` @misc{wandb, title = {Experiment Tracking with Weights and Biases}, year = {2020}, note = {Software available from wandb.com}, url={https://www.wandb.com/}, author = {Biewald, Lukas}, } ``` --- source: https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb source_type: notebook has_code: False Weights & Biases is a developer toolkit for machine learning experiment tracking, dataset and model versioning, and collaboration In this mega 3-in-1 notebook you'll see how Weights and Biases seamlessly integrates into ML code across modalities -- one example each from Computer Vision, NLP and Reinforcement Learning -- as well as across frameworks like PyTorch, Keras, and more. For the full range of supported integrations, plus more examples, see our docs. When working directly with the `wandb` library, the functions you'll use most often are: * `wandb.login` - Login to W&B at the start of your session * `wandb.init` - Initialise a new W&B, returns a "run" object * `wandb.log` - Add information to the logs for your run Most of the code in this notebook is for setting up and executing our ML experiments and is not specific to experiment tracking with W&B. To see where W&B is added in the code below you can search for these functions in the notebook or look for the ✍️ emoji. When a W&B run begins, a link labeled **Run Page** will be printed to the standard out. This link will take you to a W&B dashboard where you can view live, interactive charts and information about your experiment. We take security seriously, and our cloud-hosted dashboard uses industry best practices for encryption. If you're working with datasets that cannot leave your enterprise cluster, we have on-prem installations available. It's also easy to download all your data and export it to other tools, for example, for custom analysis in a Jupyter notebook. Here's more on our API. --- source: https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDc2MjMx source_type: report has_code: True Weights and Biases allows reading your previous runs for analysis purpose. [Here’s](https://www.wandb.com/articles/exploring-deep-learning-hyperparameters-with-random-forests) an excellent analysis done by Lukas on some publicly available Weights and Biases runs. Instrumenting runs is as easy as - ``` api = wandb.Api() run = api.run("sayakpaul/arxiv-project-complex-models/6t93vdp7") ``` In the above example, [https://app.wandb.ai/sayakpaul/arxiv-project-complex-models/runs/6t93vdp7](https://app.wandb.ai/sayakpaul/arxiv-project-complex-models/runs/6t93vdp7) is a publicly available run. Now, after the run is loaded, you can extract the configuration variables of the run like so - run.config. It will print out - If you want to read the metrics associated with a particular run along with other important stuff, you can easily do so by - ``` api = wandb.Api() run = api.run("sayakpaul/arxiv-project-complex-models/6t93vdp7") run.history() ``` You get - In order to read multiple runs residing in a project and summarizing them, you need three lines of code - ``` runs = api.runs("sayakpaul/arxiv-project-complex-models") for run in runs: print(run.summary) ``` And - Of course, you have the flexibility of trimming the parts from the summary you don’t need. To know about the full potential of the Weights and Biases API check out the official documentation: [https://docs.wandb.com/library/api](https://docs.wandb.com/library/api). --- source: https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDMwNDMx source_type: report has_code: True # build model model = Sequential() model.add(Conv2D(config.layer_1_size, (5, 5), activation='relu', input_shape=(img_width, img_height,1))) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(config.dropout)) model.add(Flatten()) model.add(Dense(num_classes, activation='softmax')) sgd = SGD(lr=config.learn_rate, decay=config.decay, momentum=config.momentum, nesterov=True) model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) # Add WandbCallback() to the fit function model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=config.epochs, callbacks=[WandbCallback(data_type="image", labels=labels)]) ``` Weights & Biases is always free for academics and open source projects. Email carey@wandb.com with any questions or feature suggestions. Here are some more resources: * - Python docs * - example reports in W&B * - blog posts and tutorials * - join our Slack community forum to hear the latest ML news, and ask your burning ML questions ' --- source: https://medium.com/@mauryaanoop3/weights-biases-w-b-a-deep-dive-into-the-mlops-powerhouse-part-1-800f9870d9da source_type: web_search has_code: None Title: Weights & Biases (W&B): A Deep Dive into the MLOps Powerhouse(PART-1) | by Anoop Maurya | Medium Description: <strong>Weights</strong> &amp; <strong>Biases</strong> (<strong>W</strong>&amp;<strong>B</strong>) has transcended the realm of simple experiment tracking to become a cornerstone of the Machine <strong>Learning</strong> (ML) development lifecycle. This comprehensive article delves into the… Weights & Biases (W&B) has transcended the realm of simple experiment tracking to become a cornerstone of the Machine Learning (ML)… --- source: https://docs.wandb.ai/guides/ source_type: documentation has_code: False Weights & Biases (W&B) is the AI developer platform, with tools for training models, fine-tuning models, and leveraging foundation models. Set up W&B in 5 minutes, then quickly iterate on your machine learning pipeline with the confidence that your models and data are tracked and versioned in a reliable system of record. This diagram outlines the relationship between W&B products. **W&B Models** is a set of lightweight, interoperable tools for machine learning practitioners training and fine-tuning models. - Experiments: Machine learning experiment tracking - Model Registry: Manage production models centrally - Launch: Scale and automate workloads - Sweeps: Hyperparameter tuning and model optimization **W&B Prompts** is for LLM debugging and monitoring, including usage of OpenAI's GPT API. **W&B Platform** is a core set of powerful building blocks for tracking and visualizing data and models, and communicating results. - Artifacts: Version assets and track lineage - Tables: Visualize and query tabular data - Reports: Document and collaborate on your discoveries Start exploring W&B with these resources: 1. Intro Notebook: Run quick sample code to track experiments in 5 minutes 2. Quickstart: Read a quick overview of how and where to add W&B to your code 3. Explore our Integrations guide and our W&B Easy Integration YouTube playlist for information on how to integrate W&B with your preferred machine learning framework. 4. View the API Reference guide for technical specifications about the W&B Python Library, CLI, and Weave operations. --- source: https://wandb.ai/wandb_fc/authors/reports/--VmlldzoxOTU5OTcy source_type: report has_code: True This is not a guide on how to use Weights & Biases; instead, here, I show the most important features of W&B that everyone should use and will increase your experiment tracking game by 100x. If you want to learn how to use W&B for your projects, their [documentation](https://docs.wandb.ai/) is pretty good, and they provide many examples to start you off. Also, they have a [YouTube channel](https://www.youtube.com/c/WeightsBiases) explaining their features in-depth. > Integrating W&B with your projects is simple and involves a few lines of code. W&B provides integrations for almost all popular open-source packages, and their documentation has code snippets on how to integrate them to get you started. Here's a link that lists all the integrations they provide and how to use them with that package. Suppose you want to integrate W&B with [Keras](http://wandb.ai/fully-connected/blog/keras), then here's how you can do it: ``` # Code taken from: https://docs.wandb.ai/guides/integrations/keras import wandb from wandb.keras import WandbCallback wandb.init(config={"hyper": "parameter"}) ... # code to set up your model in Keras # 🧙 magic model.fit(X_train, y_train, validation_data=(X_test, y_test), callbacks=[WandbCallback()]) ``` Yes, this is how simple it is to integrate W&B with any of your favorite frameworks. And it will automatically log all the hyper-parameters you define in config argument of wandb.init() method. This is what a typical dashboard looks like: --- source: https://docs.wandb.ai/guides/prompts/openai source_type: documentation has_code: False Weights & Biases has 2 OpenAI integrations to help you train better models faster and keep track of your prompts and generations: With Weights & Biases you can log your OpenAI model's fine-tuning metrics and configuration to Weights & Biases to analyse and understand the performance of your newly fine-tuned models and share the results with your colleagues. See the **W&B and OpenAI Fine-Tuning docs here** to learn more Log requests, responses, token counts and model metadata with 1 line of code for all OpenAI models See the **W&B and OpenAI API section docs** to learn more --- source: https://wandb.ai/generative-adversarial-networks/dcgan-pytorch/reports/--VmlldzoxNzg4NzE0 source_type: report has_code: True # ... wandb.log({"Discriminator Loss": disc_loss.item(), "Generator Loss": gen_loss.item()}) ``` Now, that you've seen how to implement a network and the training strategy, let's see how Weights & Biases allows for us to easily visualize important metrics and compare them using Panels. For example, here's a quick comparison of the Discriminator loss grouped by the latent dimension, you'll find linked in the Colab above: As we can see from the plots, a latent dimension of 100 happens to be the one with the lowest discriminator loss probably because it allows for greater learning, you can also try hyperparameter tuning by changing the batch size or the image size. Weights & Biases Sweeps makes this incredibly easy by automatically running your pipeline using an agent. For more details please refer to our [Sweeps Quickstart Guide](https://docs.wandb.com/sweeps/quickstart). If you'd like to try this yourself, here's the Colab to do so: In this article, you saw how you can implement Deep Convolutional Generative Adversarial Networks using the PyTorch Framework and how the use of Weights and Biases allows you to easily visualize important metrics. To see the full suite of W&B features please check out this [short 5 minutes guide](https://wandb.ai/site/getting-started). If you want more reports covering the math and "from-scratch" code implementations let us know in the comments down below or on our [forum ✨](https://community.wandb.ai/)! Check out these other reports on [Fully Connected](https://wandb.ai/fully-connected) covering other fundamental development topics like GPU Utilization and Saving Models. ' --- source: https://github.com/wandb/examples/tree/master/colabs/pytorch/Simple_PyTorch_Integration.ipynb source_type: notebook has_code: True Use Weights & Biases for machine learning experiment tracking, dataset versioning, and project collaboration. We show you how to integrate Weights & Biases with your PyTorch code to add experiment tracking to your pipeline. ``` # import the library import wandb # start a new experiment wandb.init(project="new-sota-model") # capture a dictionary of hyperparameters with config wandb.config = {"learning\_rate": 0.001, "epochs": 100, "batch\_size": 128} # set up model and data model, dataloader = get\_model(), get\_data() # optional: track gradients wandb.watch(model) for batch in dataloader: metrics = model.training\_step() # log metrics inside your training loop to visualize model performance wandb.log(metrics) # optional: save model at the end model.to\_onnx() wandb.save("model.onnx") ``` **Note**: Sections starting with *Step* are all you need to integrate W&B in an existing pipeline. The rest just loads data and defines a model. --- source: https://docs.wandb.ai/guides/integrations/deepchecks source_type: documentation has_code: True **Try in a Colab Notebook here →** DeepChecks helps you validate your machine learning models and data, such as verifying your data’s integrity, inspecting its distributions, validating data splits, evaluating your model and comparing between different models, all with with minimal effort. Read more about DeepChecks and the wandb integration -> To use DeepChecks with Weights & Biases you will first need to sign up for a Weights & Biases account here. With the Weights & Biases integration in DeepChecks you can quickly get started like so: ``` import wandb wandb.login() # import your check from deepchecks from deepchecks.checks import ModelErrorAnalysis # run your check result = ModelErrorAnalysis()... # push that result to wandb result.to\_wandb() ``` You can also log an entire DeepChecks test suite to Weights & Biases ``` import wandb wandb.login() # import your full\_suite tests from deepchecks from deepchecks.suites import full\_suite # create and run a DeepChecks test suite suite\_result = full\_suite().run(...) # push thes results to wandb # here you can pass any wandb.init configs and arguments you need suite\_result.to\_wandb( project='my-suite-project', config={'suite-name': 'full-suite'} ) ``` ``**This Report** shows off the power of using DeepChecks and Weights & Biases Any questions or issues about this Weights & Biases integration? Open an issue in the DeepChecks github repository and we'll catch it and get you an answer :)<!--end-context-information--> <!--start-question-->**Question**: # Query What are some great resources for me to better understand Weights & Biases usage for Deep Learning? --- # Query Metadata Language: en Intents: Course Related: The user is seeking information on resources to improve their understanding and usage of Weights & Biases specifically for Deep Learning applications. The query is related to a Weight & Biases course and/or skill enhancement. Answer the query and provide guidance and links where necessary Sub-queries to consider answering: What are the official Weights & Biases learning resources for Deep Learning? Are there any community-recommended tutorials for using Weights & Biases in Deep Learning projects? What are the best practices for integrating Weights & Biases with Deep Learning frameworks? <!--end-question--> <!--final-answer-in-markdown-->