# Top **URL:** https://discuss.bayesflow.org/top.md [Latest](https://discuss.bayesflow.org/latest.md) · [Categories](https://discuss.bayesflow.org/categories.md) · [Tags](https://discuss.bayesflow.org/tags.md) --- ## [Dealing with time series (SDE model)](https://discuss.bayesflow.org/t/dealing-with-time-series-sde-model/103)
**Author:** [@kmedriano](https://discuss.bayesflow.org/u/kmedriano)\ **Replies:** 12\ **Last updated:** [August 7, 2024, 3:40pm UTC](https://discuss.bayesflow.org/t/dealing-with-time-series-sde-model/103 "2024-08-07T15:40:34Z")
Hi, I am trying to come up with a bf framework for estimation of the Ornstein-Uhlenbeck parameters (and eventually a hierarchical extension). The parameter recovery for 2 (out of 3) parameters is not so nice. Wondering … --- ## [BayesFlow on HPC Clusters](https://discuss.bayesflow.org/t/bayesflow-on-hpc-clusters/46)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 17\ **Last updated:** [February 8, 2024, 8:54pm UTC](https://discuss.bayesflow.org/t/bayesflow-on-hpc-clusters/46 "2024-02-08T20:54:08Z")
I have access to HPCs with a high number of CPUs running Windows Server. Using the examples of the tutorials and some other toy models, I have noticed that the speed of ‘training’ is actually slower compared to laptops a… --- ## [Difficulty Estimating a Multivariate Normal Outcome](https://discuss.bayesflow.org/t/difficulty-estimating-a-multivariate-normal-outcome/182)
**Author:** [@NathanielF](https://discuss.bayesflow.org/u/NathanielF)\ **Replies:** 28\ **Last updated:** [August 7, 2025, 3:08pm UTC](https://discuss.bayesflow.org/t/difficulty-estimating-a-multivariate-normal-outcome/182 "2025-08-07T15:08:39Z")
Hi All, I’m trying to develop a better understanding of the amortized bayesian inference procedures and maybe compare them with vanilla bayesian modelling and/or VAE methods. So i thought i’d try and do a parameter rec… --- ## [Cannot generate posterior samples after training](https://discuss.bayesflow.org/t/cannot-generate-posterior-samples-after-training/68)
**Author:** [@wyy](https://discuss.bayesflow.org/u/wyy)\ **Replies:** 21\ **Last updated:** [March 11, 2024, 3:34am UTC](https://discuss.bayesflow.org/t/cannot-generate-posterior-samples-after-training/68 "2024-03-11T03:34:41Z")
Recently I used the R package to generate some data as summary statistics and put it in Bayesflow for training. The data is in high dimension. I try a small size training, epochs=1, iterations\_per\_epoch=100, batch\_size=3… --- ## [Parameter Recovery Issues with Item Response Theory (IRT) Models](https://discuss.bayesflow.org/t/parameter-recovery-issues-with-item-response-theory-irt-models/191)
**Author:** [@VinzentJ](https://discuss.bayesflow.org/u/VinzentJ)\ **Replies:** 19\ **Last updated:** [August 28, 2025, 1:51pm UTC](https://discuss.bayesflow.org/t/parameter-recovery-issues-with-item-response-theory-irt-models/191 "2025-08-28T13:51:35Z")
Hi everyone, I’m working on estimating Item Response Theory (IRT) parameters with BayesFlow, specifically implementing a 2PL model where I want to estimate item discrimination (a) and difficulty (b) parameters from resp… --- ## [Getting error running Linear Regression Example](https://discuss.bayesflow.org/t/getting-error-running-linear-regression-example/143)
**Author:** [@Collins.282](https://discuss.bayesflow.org/u/Collins.282)\ **Replies:** 18\ **Last updated:** [June 10, 2025, 7:29am UTC](https://discuss.bayesflow.org/t/getting-error-running-linear-regression-example/143 "2025-06-10T07:29:42Z")
I am trying to become familiar with BayesFlow by going through the example scripts. I installed the latest version of Bayesflow and just tried to run the Linear\_Regression\_Starter example right from the Juypter notebook.… --- ## [Preferred way to deal with time series with non-equidistant time steps](https://discuss.bayesflow.org/t/preferred-way-to-deal-with-time-series-with-non-equidistant-time-steps/91)
**Author:** [@nw95](https://discuss.bayesflow.org/u/nw95)\ **Replies:** 10\ **Last updated:** [August 8, 2024, 5:25pm UTC](https://discuss.bayesflow.org/t/preferred-way-to-deal-with-time-series-with-non-equidistant-time-steps/91 "2024-08-08T17:25:13Z")
I am currently testing bayesflow with different ODE-based models. Recently I turned my attention to model outputs with varying number of outputs and varying time step points. For example one model output could be at time… --- ## [Graphs in Vector Format like PDF/SVG](https://discuss.bayesflow.org/t/graphs-in-vector-format-like-pdf-svg/69)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 12\ **Last updated:** [April 18, 2024, 3:59pm UTC](https://discuss.bayesflow.org/t/graphs-in-vector-format-like-pdf-svg/69 "2024-04-18T15:59:39Z")
Is it possible to have the BayesFlow graphs (for example, posteriors or recovery graphs ) in vector formats like SVG or PDF? --- ## [Question about ordered model output and context variables](https://discuss.bayesflow.org/t/question-about-ordered-model-output-and-context-variables/198)
**Author:** [@deakj](https://discuss.bayesflow.org/u/deakj)\ **Replies:** 11\ **Last updated:** [September 16, 2025, 3:37pm UTC](https://discuss.bayesflow.org/t/question-about-ordered-model-output-and-context-variables/198 "2025-09-16T15:37:39Z")
Hi all, Thanks in advance for any help. This may be long. My set up is quite similar to the one defined here Fitting a value-based decision model with trial-level context variables . The model I am using predicts fixat… --- ## [Neual likelihood estimation](https://discuss.bayesflow.org/t/neual-likelihood-estimation/158)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 12\ **Last updated:** [June 2, 2025, 1:08pm UTC](https://discuss.bayesflow.org/t/neual-likelihood-estimation/158 "2025-06-02T13:08:40Z")
Hi everyone, I’m currently building a likelihood estimator using BayesFlow v1. The model setup is relatively simple — we aim to estimate the likelihood p(y∣θ), where θ is a two-dimensional parameter vector and y is a sc… --- ## [Some questions about the split network](https://discuss.bayesflow.org/t/some-questions-about-the-split-network/44)
**Author:** [@chrisliu](https://discuss.bayesflow.org/u/chrisliu)\ **Replies:** 9\ **Last updated:** [January 16, 2024, 1:22am UTC](https://discuss.bayesflow.org/t/some-questions-about-the-split-network/44 "2024-01-16T01:22:50Z")
Can split network use hierarchical network? This sounds weird, but it’s a very real use case of mine. I have some data of the shape (1, subjects, time, observations). The observations come from two different sources, t… --- ## [Error when using loaded approximator](https://discuss.bayesflow.org/t/error-when-using-loaded-approximator/170)
**Author:** [@tdj2000](https://discuss.bayesflow.org/u/tdj2000)\ **Replies:** 9\ **Last updated:** [June 17, 2025, 3:18pm UTC](https://discuss.bayesflow.org/t/error-when-using-loaded-approximator/170 "2025-06-17T15:18:50Z")
When I try to use .sample when using a loaded approximator I get the following error: ValueError: Cannot call forward with strict=False before calling forward with strict=True. The issue does not come up when I try to … --- ## [Keras ValueError: For a \`build()\` method with more than one argument, all arguments should have a \`\_shape\` suffix and match an argument from \`call()\`](https://discuss.bayesflow.org/t/keras-valueerror-for-a-build-method-with-more-than-one-argument-all-arguments-should-have-a-shape-suffix-and-match-an-argument-from-call/206)
**Author:** [@freund](https://discuss.bayesflow.org/u/freund)\ **Replies:** 10\ **Last updated:** [November 6, 2025, 7:41am UTC](https://discuss.bayesflow.org/t/keras-valueerror-for-a-build-method-with-more-than-one-argument-all-arguments-should-have-a-shape-suffix-and-match-an-argument-from-call/206 "2025-11-06T07:41:45Z")
Hello, I’m encountering this error when attempting to run the minimal working example on current github readme. For troubleshooting, I’ve attempted bayesflow 2.0.7 and 2.0.6, jax GPU, jax CPU, tensorflow CPU backends, … --- ## [BayesFlow Neo (V2) Now Available](https://discuss.bayesflow.org/t/bayesflow-neo-v2-now-available/134)
**Author:** [@KLDivergence](https://discuss.bayesflow.org/u/KLDivergence)\ **Replies:** 0\ **Last updated:** [March 19, 2025, 3:05pm UTC](https://discuss.bayesflow.org/t/bayesflow-neo-v2-now-available/134 "2025-03-19T15:05:29Z")
Friends, The new version preview (pre-release) of BayesFlow is out there, along with updated tutorials and completely revamped codebase for the next generation of amortized Bayesian inference. You can now use any deep … --- ## [Our new preprint on consistency models for posterior estimation](https://discuss.bayesflow.org/t/our-new-preprint-on-consistency-models-for-posterior-estimation/30)
**Author:** [@KLDivergence](https://discuss.bayesflow.org/u/KLDivergence)\ **Replies:** 2\ **Last updated:** [December 21, 2023, 9:29pm UTC](https://discuss.bayesflow.org/t/our-new-preprint-on-consistency-models-for-posterior-estimation/30 "2023-12-21T21:29:30Z")
Check out our freshly baked preprint on a new free-form neural sampler based on consistency models! Any feedback is greatly appreciated. :grinning: P.S. Continuous models (along with flow matching and denoising diffus… --- ## [New preprint on estimating and comparing models with time-varying parameters](https://discuss.bayesflow.org/t/new-preprint-on-estimating-and-comparing-models-with-time-varying-parameters/51)
**Author:** [@LuSchumacher](https://discuss.bayesflow.org/u/LuSchumacher)\ **Replies:** 0\ **Last updated:** [January 16, 2024, 5:02pm UTC](https://discuss.bayesflow.org/t/new-preprint-on-estimating-and-comparing-models-with-time-varying-parameters/51 "2024-01-16T17:02:15Z")
Hello there, we just published a new preprint on the validation and comparison of non-stationary diffusion decision models: https://arxiv.org/abs/2401.08626 We used BayesFlow for parameter estimation and model comparis… --- ## [Preprint on "Amortized Bayesian Multilevel Models"](https://discuss.bayesflow.org/t/preprint-on-amortized-bayesian-multilevel-models/111)
**Author:** [@Daniel](https://discuss.bayesflow.org/u/Daniel)\ **Replies:** 3\ **Last updated:** [September 15, 2024, 6:21pm UTC](https://discuss.bayesflow.org/t/preprint-on-amortized-bayesian-multilevel-models/111 "2024-09-15T18:21:25Z")
I’m happy to announce our recently published preprint on Amortized Bayesian Multilevel Models: \[2408.13230\] Amortized Bayesian Multilevel Models Any feedback is greatly appreciated. We are also currently working on intr… --- ## [Installation Error "zsh: illegal hardware instruction"](https://discuss.bayesflow.org/t/installation-error-zsh-illegal-hardware-instruction/56)
**Author:** [@eodol](https://discuss.bayesflow.org/u/eodol)\ **Replies:** 1\ **Last updated:** [February 2, 2024, 10:40am UTC](https://discuss.bayesflow.org/t/installation-error-zsh-illegal-hardware-instruction/56 "2024-02-02T10:40:52Z")
If normal installation fails for MacOS there may be an issue in the dependencies. During my installation process I ran into the following problems: - error could not build “grpcio” wheels - xcrun error: invalid develo… --- ## [Model Misspecification Diffusion model for conflict tasks](https://discuss.bayesflow.org/t/model-misspecification-diffusion-model-for-conflict-tasks/41)
**Author:** [@SimonSchaefer](https://discuss.bayesflow.org/u/SimonSchaefer)\ **Replies:** 5\ **Last updated:** [January 20, 2024, 8:41am UTC](https://discuss.bayesflow.org/t/model-misspecification-diffusion-model-for-conflict-tasks/41 "2024-01-20T08:41:26Z")
Dear all, we are currently trying to apply Bayesflow to a reaction time and error rate based cognitive model (Diffusion model for conflict tasks, Ulrich et al., 2015). Despite very good parameter recoveries (r \> .85), w… --- ## [Cannot do offline training with summary network](https://discuss.bayesflow.org/t/cannot-do-offline-training-with-summary-network/27)
**Author:** [@masonyoungblood](https://discuss.bayesflow.org/u/masonyoungblood)\ **Replies:** 5\ **Last updated:** [December 9, 2023, 4:12am UTC](https://discuss.bayesflow.org/t/cannot-do-offline-training-with-summary-network/27 "2023-12-09T04:12:13Z")
Hello! I am using BayesFlow for the first time, and having some issues doing offline training with a summary network (everything works fine if I exclude it and just supply the data to the inference network). Basically, … --- ## [Problems on Priors for Hierarchical Model](https://discuss.bayesflow.org/t/problems-on-priors-for-hierarchical-model/50)
**Author:** [@YufeiWu](https://discuss.bayesflow.org/u/YufeiWu)\ **Replies:** 8\ **Last updated:** [January 24, 2024, 11:27pm UTC](https://discuss.bayesflow.org/t/problems-on-priors-for-hierarchical-model/50 "2024-01-24T23:27:24Z")
Hi, I would like to fit a hierarchical Ratcliff drift diffusion model with BayesFlow. The parameters I have are: \\delta\_1, \\delta\_2: two drift rates \\alpha: boundary separation \\beta: response bias \\tau: non-decision… --- ## [Welcome to BayesFlow Forums! 👋](https://discuss.bayesflow.org/t/welcome-to-bayesflow-forums/5)
**Author:** [@system](https://discuss.bayesflow.org/u/system)\ **Replies:** 0\ **Last updated:** [November 30, 2023, 11:44pm UTC](https://discuss.bayesflow.org/t/welcome-to-bayesflow-forums/5 "2023-11-30T23:44:13Z")
We are so glad you joined us. BayesFlow Forums The BayesFlow Forums provide a community for asking and answering questions about all aspects of BayesFlow and amortized Bayesian workflows. Here are some things you can… --- ## [Some questions related to Likelihood network](https://discuss.bayesflow.org/t/some-questions-related-to-likelihood-network/59)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 8\ **Last updated:** [February 12, 2024, 7:25pm UTC](https://discuss.bayesflow.org/t/some-questions-related-to-likelihood-network/59 "2024-02-12T19:25:35Z")
I am trying to learn a likelihood network using BayesFlow. The simulation budget is 800 training datasets. I followed the steps in JANA paper for the joint learning of posterior and likelihood, I have a few questions, ho… --- ## [Adding manual summary statistics to summary network](https://discuss.bayesflow.org/t/adding-manual-summary-statistics-to-summary-network/63)
**Author:** [@hazhir](https://discuss.bayesflow.org/u/hazhir)\ **Replies:** 5\ **Last updated:** [August 6, 2024, 10:16pm UTC](https://discuss.bayesflow.org/t/adding-manual-summary-statistics-to-summary-network/63 "2024-08-06T22:16:55Z")
Hi, In some experiments with stochastic ODE models we are finding it take a lot of data and training for the summary networks (either TimeSeriesTransformer or SequenceNetwork) to learn the process and measurement noise … --- ## [Is it worthwhile to alter the module structure to make writing easier like bf.benchmarks.\_\_\_\_\_?](https://discuss.bayesflow.org/t/is-it-worthwhile-to-alter-the-module-structure-to-make-writing-easier-like-bf-benchmarks/38)
**Author:** [@Adya](https://discuss.bayesflow.org/u/Adya)\ **Replies:** 1\ **Last updated:** [January 4, 2024, 11:15pm UTC](https://discuss.bayesflow.org/t/is-it-worthwhile-to-alter-the-module-structure-to-make-writing-easier-like-bf-benchmarks/38 "2024-01-04T23:15:53Z")
Hi, I am trying to use the benchmarks submodule but only importing Bayesflow does not call the benchmarks submodule, instead, it has to be imported explicitly. Is it worth changing the structure so that this submodule c… --- ## [Handling missing data in summary and inference networks](https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43)
**Author:** [@chrisliu](https://discuss.bayesflow.org/u/chrisliu)\ **Replies:** 5\ **Last updated:** [January 16, 2024, 2:11pm UTC](https://discuss.bayesflow.org/t/handling-missing-data-in-summary-and-inference-networks/43 "2024-01-16T14:11:52Z")
Hi, I’m wondering whether it is of any interest to include the ability for sequential networks or invariant networks to handle missing data. Some of our subjects have only partial data, but it would be a huge waste to ju… --- ## [How to define coupling type?](https://discuss.bayesflow.org/t/how-to-define-coupling-type/65)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 6\ **Last updated:** [February 25, 2024, 11:33pm UTC](https://discuss.bayesflow.org/t/how-to-define-coupling-type/65 "2024-02-25T23:33:50Z")
I usually choose the affine layers to train the model, which is good enough for my problem. When I tried neural spline, it seems to be more difficult and need much more time to train model. I read some papers related to … --- ## [macOS GPU (TensorFlow-metal)](https://discuss.bayesflow.org/t/macos-gpu-tensorflow-metal/81)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 5\ **Last updated:** [March 18, 2024, 7:19am UTC](https://discuss.bayesflow.org/t/macos-gpu-tensorflow-metal/81 "2024-03-18T07:19:07Z")
After I installed tensorflow-metal, I saw a huge increase in training time on macOS. As you might already know, I get the following warning: “2.11+ optimizer tf.keras.optimizers.Adam runs slowly on M1/M2 Macs, please us… --- ## [ONNX Probabilistic Programming Working Group – Collaboration with the BayesFlow Community](https://discuss.bayesflow.org/t/onnx-probabilistic-programming-working-group-collaboration-with-the-bayesflow-community/238)
**Author:** [@bparbhu](https://discuss.bayesflow.org/u/bparbhu)\ **Replies:** 0\ **Last updated:** [April 15, 2026, 12:16pm UTC](https://discuss.bayesflow.org/t/onnx-probabilistic-programming-working-group-collaboration-with-the-bayesflow-community/238 "2026-04-15T12:16:18Z")
Hi everyone, I wanted to share that a new ONNX Working Group focused on Probabilistic Programming has recently been formed and invite participation from the BayesFlow community. The goal of this working group is to bri… --- ## [Custom Learning Rate](https://discuss.bayesflow.org/t/custom-learning-rate/64)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 3\ **Last updated:** [February 19, 2024, 3:28pm UTC](https://discuss.bayesflow.org/t/custom-learning-rate/64 "2024-02-19T15:28:58Z")
Hi, We have found that resetting the learning rate and introducing new data (and discarding the old one) in discrete rounds yields better performance for our model. Is it possible to have a similar mechanism in round-ba… --- ## [Simple negative binomial inference](https://discuss.bayesflow.org/t/simple-negative-binomial-inference/99)
**Author:** [@mrazo](https://discuss.bayesflow.org/u/mrazo)\ **Replies:** 6\ **Last updated:** [January 23, 2025, 11:16pm UTC](https://discuss.bayesflow.org/t/simple-negative-binomial-inference/99 "2025-01-23T23:16:20Z")
Dear BayesFlow team, I am trying to get a feel for how to work with the codebase by using a very simple example related to the real inference I want to work on. The simple exercise consists of training a neural network … --- ## [Training data with additive noise](https://discuss.bayesflow.org/t/training-data-with-additive-noise/82)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 8\ **Last updated:** [March 25, 2024, 11:21am UTC](https://discuss.bayesflow.org/t/training-data-with-additive-noise/82 "2024-03-25T11:21:12Z")
Hi, all, I added noise to training data in BayesFlow, such as Gaussian noise, but I found the the model performance after training is not as good as those without noise. I tried to tune the model for a while, the issue … --- ## [How to Prevent Overfitting with a Very Small Dataset?](https://discuss.bayesflow.org/t/how-to-prevent-overfitting-with-a-very-small-dataset/135)
**Author:** [@philippreiser](https://discuss.bayesflow.org/u/philippreiser)\ **Replies:** 7\ **Last updated:** [March 26, 2025, 12:36pm UTC](https://discuss.bayesflow.org/t/how-to-prevent-overfitting-with-a-very-small-dataset/135 "2025-03-26T12:36:53Z")
Hi everyone, I’m working with a very small dataset (only 16 model evaluations: four prior evaluations and for each four likelihood evaluations). With this setup the networks overfit quickly. Here’s an example: import … --- ## [Setting up TimeSeriesTransformer](https://discuss.bayesflow.org/t/setting-up-timeseriestransformer/61)
**Author:** [@hazhir](https://discuss.bayesflow.org/u/hazhir)\ **Replies:** 8\ **Last updated:** [February 14, 2024, 10:46pm UTC](https://discuss.bayesflow.org/t/setting-up-timeseriestransformer/61 "2024-02-14T22:46:54Z")
I am trying to compare the performance of SequenceNetwork and TimeSeriesTransformer for summary networks for time series data (e.g. the simulation model generates 3 time series of 300 time points each), but have a hard t… --- ## [Dealing with different driving data for different units](https://discuss.bayesflow.org/t/dealing-with-different-driving-data-for-different-units/53)
**Author:** [@hazhir](https://discuss.bayesflow.org/u/hazhir)\ **Replies:** 3\ **Last updated:** [January 27, 2024, 2:01pm UTC](https://discuss.bayesflow.org/t/dealing-with-different-driving-data-for-different-units/53 "2024-01-27T14:01:20Z")
Hi, I am considering applications of Bayesflow to dynamic models (typically differential equations, but also agent based), where the amortization can add value when estimating the model for a large number of units (e.g.… --- ## [Out of domain posterior samples](https://discuss.bayesflow.org/t/out-of-domain-posterior-samples/71)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 3\ **Last updated:** [March 5, 2024, 6:19pm UTC](https://discuss.bayesflow.org/t/out-of-domain-posterior-samples/71 "2024-03-05T18:19:54Z")
Hi, I used the trained model to generate posterior sample, however, I found that some posterior samples were out of domain, such as samples falling outside upper or lower bounds. Does BaysFlow provide some contraints to… --- ## [Discussion of Normalizing flow](https://discuss.bayesflow.org/t/discussion-of-normalizing-flow/96)
**Author:** [@Jice](https://discuss.bayesflow.org/u/Jice)\ **Replies:** 7\ **Last updated:** [May 26, 2026, 2:20pm UTC](https://discuss.bayesflow.org/t/discussion-of-normalizing-flow/96 "2026-05-26T14:20:53Z")
Hi, I have applied the BayesFlow framework to my area, and the performance has been fairly good so far. The mechanism of BayesFlow relies on the use of normalizing flow (NF). Here, I would like to discuss some aspects o… --- ## [Posterior Point Estimates Options](https://discuss.bayesflow.org/t/posterior-point-estimates-options/177)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 3\ **Last updated:** [July 14, 2025, 1:32pm UTC](https://discuss.bayesflow.org/t/posterior-point-estimates-options/177 "2025-07-14T13:32:04Z")
Hi all, When the posterior has different modes (like a very high peak with some minor but long tales), what would be a better alternative for calculating the aggregate value of samples other than ‘mean’ or ‘median’? I r… --- ## [How to implement a go/nogo paradigm](https://discuss.bayesflow.org/t/how-to-implement-a-go-nogo-paradigm/94)
**Author:** [@AminGhaderi](https://discuss.bayesflow.org/u/AminGhaderi)\ **Replies:** 4\ **Last updated:** [June 25, 2024, 3:12pm UTC](https://discuss.bayesflow.org/t/how-to-implement-a-go-nogo-paradigm/94 "2024-06-25T15:12:34Z")
Hello Bayesflow team, I wonder whether it is possible to implement a go/nogo task in Bayeflow, wherein incorrectly inhibited go trials (omission) and correctly inhibited no-go trials only have responses, but no RTs? ki… --- ## [V2 BayesFlow and Hierarchal Modeling](https://discuss.bayesflow.org/t/v2-bayesflow-and-hierarchal-modeling/136)
**Author:** [@tooweisian](https://discuss.bayesflow.org/u/tooweisian)\ **Replies:** 1\ **Last updated:** [April 3, 2025, 11:38am UTC](https://discuss.bayesflow.org/t/v2-bayesflow-and-hierarchal-modeling/136 "2025-04-03T11:38:33Z")
Hello, I had a quick question about the interface for hierarchal models; are hierarchal models supported in BayesFlow V2? I remember there were several methods in V1 that supported hierarchal models. If so, how would yo… --- ## [What is a good loss value?](https://discuss.bayesflow.org/t/what-is-a-good-loss-value/60)
**Author:** [@ali](https://discuss.bayesflow.org/u/ali)\ **Replies:** 1\ **Last updated:** [February 11, 2024, 5:51pm UTC](https://discuss.bayesflow.org/t/what-is-a-good-loss-value/60 "2024-02-11T17:51:49Z")
In the tutorials, there are several examples of different training losses. In some cases, the loss reaches -2, but in others (e.g., the ODE example), it reaches -15. What are the criteria for an acceptable loss value? If… --- ## [Context arrays being flattened when passed from meta() to simulator function](https://discuss.bayesflow.org/t/context-arrays-being-flattened-when-passed-from-meta-to-simulator-function/173)
**Author:** [@BShevlin](https://discuss.bayesflow.org/u/BShevlin)\ **Replies:** 2\ **Last updated:** [June 20, 2025, 1:57pm UTC](https://discuss.bayesflow.org/t/context-arrays-being-flattened-when-passed-from-meta-to-simulator-function/173 "2025-06-20T13:57:59Z")
Hi everyone, I’m encountering what appears to be a bug where multi-dimensional numpy arrays returned from the meta() function are being flattened when passed to the simulator function. Here are the details: Problem Des… --- ## [Confused in training \`AmortizedPosteriorEstimator\`](https://discuss.bayesflow.org/t/confused-in-training-amortizedposteriorestimator/84)
**Author:** [@smabbasht](https://discuss.bayesflow.org/u/smabbasht)\ **Replies:** 6\ **Last updated:** [April 23, 2024, 6:27am UTC](https://discuss.bayesflow.org/t/confused-in-training-amortizedposteriorestimator/84 "2024-04-23T06:27:45Z")
I am fairly new to Bayesflow and BayesianFlowNetworks in general, I was previously developing a Bayesian Neural Network using tensorflow\_probability but moved to BFN once I saw Bayesflow. I have simulated data related t… --- ## [Reinforcement Learning Cognitive Models](https://discuss.bayesflow.org/t/reinforcement-learning-cognitive-models/89)
**Author:** [@BShevlin](https://discuss.bayesflow.org/u/BShevlin)\ **Replies:** 5\ **Last updated:** [June 9, 2024, 3:38pm UTC](https://discuss.bayesflow.org/t/reinforcement-learning-cognitive-models/89 "2024-06-09T15:38:08Z")
Has anyone had success adapting a reinforcement learning (RL) model using BayesFlow? I’ve built a basic framework combining RL with the drift diffusion model (DDM). While I’ve had success recovering the DDM parameters (… --- ## [Time Series Dimension Errors in HierarchicalNetwork](https://discuss.bayesflow.org/t/time-series-dimension-errors-in-hierarchicalnetwork/122)
**Author:** [@ng96](https://discuss.bayesflow.org/u/ng96)\ **Replies:** 3\ **Last updated:** [January 17, 2025, 7:06pm UTC](https://discuss.bayesflow.org/t/time-series-dimension-errors-in-hierarchicalnetwork/122 "2025-01-17T19:06:55Z")
Hi! I’ve recently been trying out BayesFlow for a use case at my organization for the first time (it seems really cool!), but I’ve bumped into an error when trying to use the HierarchicalNetwork with some hierarchical ti… --- ## [Enabling multi‐GPU (2× GPUs) training in BayesFlow](https://discuss.bayesflow.org/t/enabling-multi-gpu-2x-gpus-training-in-bayesflow/171)
**Author:** [@Noura](https://discuss.bayesflow.org/u/Noura)\ **Replies:** 7\ **Last updated:** [November 21, 2025, 7:30pm UTC](https://discuss.bayesflow.org/t/enabling-multi-gpu-2x-gpus-training-in-bayesflow/171 "2025-11-21T19:30:16Z")
Hi BayesFlow team, I’m running BayesFlow v1’s train\_online on a single GPU but would like to leverage two GPUs (for both simulation-heavy and neural network phases). Does the Trainer offer built in data, or model paral… --- ## [Attention mask for the TimeSeriesTransformer summary network](https://discuss.bayesflow.org/t/attention-mask-for-the-timeseriestransformer-summary-network/32)
**Author:** [@leo](https://discuss.bayesflow.org/u/leo)\ **Replies:** 5\ **Last updated:** [December 15, 2023, 9:04am UTC](https://discuss.bayesflow.org/t/attention-mask-for-the-timeseriestransformer-summary-network/32 "2023-12-15T09:04:05Z")
Hi! I am trying to use time series data of different lengths with the TimeSeriesTransformer as summary network. To avoid having to make batches of time series of the same length I was thinking of padding them to a fixed… --- ## [How to correctly load a trained ModelComparisonApproximator model?](https://discuss.bayesflow.org/t/how-to-correctly-load-a-trained-modelcomparisonapproximator-model/169)
**Author:** [@dizyd](https://discuss.bayesflow.org/u/dizyd)\ **Replies:** 7\ **Last updated:** [June 17, 2025, 9:26am UTC](https://discuss.bayesflow.org/t/how-to-correctly-load-a-trained-modelcomparisonapproximator-model/169 "2025-06-17T09:26:51Z")
Hi everyone, I am starting to learn more about using Bayesflow, but I don’t have much experience with keras before, so this might be a trivial question. After training my network using a ModelComparisonApproximator I sa… --- ## [Getting Error using ModelComparisonSimulator in BF 2.0.1](https://discuss.bayesflow.org/t/getting-error-using-modelcomparisonsimulator-in-bf-2-0-1/150)
**Author:** [@dizyd](https://discuss.bayesflow.org/u/dizyd)\ **Replies:** 1\ **Last updated:** [April 25, 2025, 10:14am UTC](https://discuss.bayesflow.org/t/getting-error-using-modelcomparisonsimulator-in-bf-2-0-1/150 "2025-04-25T10:14:37Z")
Hey, I am trying to use the new BayesFlow version (2.0.1) and workflow to make individual-level comparisons between a set of some cognitive process models. I oriented myself on the “Simple Model Comparison - One Sample… --- ## [Plotting of the loss](https://discuss.bayesflow.org/t/plotting-of-the-loss/168)
**Author:** [@tdj2000](https://discuss.bayesflow.org/u/tdj2000)\ **Replies:** 2\ **Last updated:** [June 7, 2025, 12:57pm UTC](https://discuss.bayesflow.org/t/plotting-of-the-loss/168 "2025-06-07T12:57:38Z")
Hi all, I have been training some models using different summary networks. One of the things I am interested in is the decay of the loss function, especially in the first few epochs. However, when using f = bf.diagnosti… [Next page](https://discuss.bayesflow.org/top.md?page=1&per_page=50)