Ping Yu comments

Results 66 comments of


                                            Ping Yu

"Cannot infer the missing size in [-1, 0] when there are 0 elements" when using padding in custom converted TFJS model

@FabioRomagnolo I took a look at the generated models, it is quite complex, seems ONNX turns constants into sparse representation, is it possible to disable that during conversion?

[Perf] The time of Conv2DBackpropInput is very long in BlazePose/hand_detector models in WebGL

@lina128 the UnpackProgram is the shader to unpack outputs from the previous kernel, the Conv2DDerInputProgram is the shader for Conv2DBackpropInput, which one supports unpacked texture.

[Perf] The time of Conv2DBackpropInput is very long in BlazePose/hand_detector models in WebGL

FYI @Linchenn

[tfjs-converter] Support for ops: `BitwiseXor`, `Bitcast`, `LeftShift`, `BitwiseOr`, `RightShift`

@josephrocca Thank you for submitting this issue and willing to contribute to the library. Here is the doc for [adding an new TF op to TFJS](https://github.com/tensorflow/tfjs/blob/master/CONTRIBUTING_MISSING_OP.md) Please let us know...

Unsupported Ops in the model before optimization TensorScatterUpdate

@PeterL1n Since this Op is very similar to ScatterNd op, we should be able to add the support fairly soon.

Unsupported Ops in the model before optimization [tensorflowjs_converter] Ops: PartitionedCall

Hi @github-jeff , can you share the saved_model file for us to reproduce the problem? thanks

Unsupported Ops in the model before optimization [tensorflowjs_converter] Ops: PartitionedCall

@github-jeff what is the TensorFlow python version you are using, we have a bug with the converter if you are using TensorFlow 2.10.0. We will release a fix soon, if...

Unsupported Ops in the model before optimization [tensorflowjs_converter] Ops: PartitionedCall

@github-jeff It is interesting that 3.11.0 works, but not anything higher. The partitionCall is the Tensorflow function start node in the saved model, when the function can not be inlined...

Move tfjs-examples to ESM

@paradite Thank you for pointing out this issue, I think it will be very beneficial to get the examples up to date. It will be greatly appreciated, if you can...

tf-backend-wasm.node.js occurred "memory out of bounds"

@liliquan0118 thank you for reporting this issue, are you running within a browser or in the node.js environment? I noticed a potential issue in the code you provided, the output...