5 commits

Author	SHA1	Message	Date
Xu Xing	0d7cf301a1	[js/webgpu] Add activation Tanh (#21540) ... Bug:https://github.com/microsoft/onnxruntime/issues/21467 ### Description <!-- Describe your changes. --> ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->	2024-07-29 11:05:34 -07:00
Jiajia Qin	ccbe264a39	[js/webgpu] Add LeakyRelu activation for fusedConv (#19369) ... ### Description This PR 1) adds LeakyRelu activation for fusedConv; 2) makes `vec4<f16>` value work with `float32` uniforms attributes. For example: `clamp(value, vec4<f16>(uniforms.clip_min), vec4<f16>(uniforms.clip_max)` will throw compilation errors since `uniforms.clip_min` and `uniforms.clip_min` are `f32` not `f16`. So we need to change it to `clamp(value, vec4<f16>(f16(uniforms.clip_min)), vec4<f16>(f16(uniforms.clip_max))` And above problem was introduced when we make activation attributes as uniforms instead of constant. BTW, after adding LeakyRelu, `realesrgan-t256` model can pass.	2024-02-02 09:06:38 -08:00
Jiajia Qin	90883a366a	[js/webgpu] Add hardSigmoid activation for fusedConv (#19233) ... ### Description Add hardSigmoid activation for fusedConv. It will be used by mobilenetv3-small-100 model.	2024-01-30 16:28:53 -08:00
Xu Xing	61610ff986	[js/webgpu] Add FusedConv clip test case (#18900) ... Bug: https://github.com/microsoft/onnxruntime/issues/18899	2024-01-23 08:25:05 -08:00
satyajandhyala	a2e9ba72d5	[JS/Web]Added FusedConv. (#17766) ... ### Description Added FusedConv and FusedConvTranspose ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Improve performance	2023-11-01 15:34:51 -07:00