tfjs
tfjs copied to clipboard
A WebGL accelerated JavaScript library for training and deploying ML models.
This fixes the error in WebGPU-backed unit tests: OperationError: Failed to execute 'importExternalTexture' on 'GPUDevice': Failed to import texture from video element that doesn't have back resource. To see the...
This PR moves CodeSnippet to benchmark from server sider to client side. Specifically: Previously, CodeSnippet is hard-coded in a server file (benchmark_model.js), which will be executed by BrowserStack instances. This...
This only works on WebGPU. TODO: refine API docs; Add more dtype. Use case: ``` const shape: Shape = [16]; const gpuReadData = new tf.GPUReadData(aBuffer, shape, dtype); const a =...
This may not be considered a bug as the code may be functioning properly so I wanted to drop this here. **System information** - Tested on Ubuntu 22.04 and Windows...
Seems the cloud build still having trouble to correctly compute the pip deps. Manually set the protobuf version to be the same as tensorflow. ref https://github.com/tensorflow/tfjs/issues/6698 We can find the...
Uncaught (in promise) TypeError: Cannot read properties of undefined (reading 'length') at Module.inferFromImplicitShape (util_base.js:304:21) i have been hitting my head in this issue since two weeks, can you please help...
Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:bug_template **System information**...
**System information** - OS Platform and Distribution: MacOS 12.4 M1 - TensorFlow.js version: [0a9fdbd](https://github.com/tensorflow/tfjs/commit/0a9fdbd4501f7f99a6617f619414f47219b3d5d5) - Browser version: Google Chrome 102.0.5005.61 **Describe the current behavior** 6 tests failed with the following...
**System information** - Have I written custom code (as opposed to using a stock example script provided in TensorFlow.js): Yes, I have written custom code - OS Platform and Distribution...
I went through the pure GPU pipeline example provided by @lina128 for the webgl backend. Is there any example for webgpu backend as well? I wanted to use the inference...