Jiajia Qin 64dacc2892 [js/webgpu] Add BatchNormalization Op (#18468) ... ### Description This PR adds `BatchNormalization` with `float` support. Some Todos: 1. all inputs don't have same data type. For example, x/y is float16, but bias/scale is float32 or double. 2. training mode support. We see many models are using `BatchNormalization` ops. However, due to the missing in jsep, all of them run on cpu, which result very poor performance. With this PR's support, densenet-9 model becomes 20.29 ms from 250.69 ms.		2023-11-22 15:58:06 -08:00
..
binding	[js/web/training] Add CreateTrainingSession (#17891)	2023-10-26 09:22:10 -07:00
jsep	[js/webgpu] Add BatchNormalization Op (#18468)	2023-11-22 15:58:06 -08:00
proxy-worker	[js/web] set noUnusedParameters to true and fix a few bugs (#18404)	2023-11-15 09:16:29 -08:00
proxy-messages.ts	[js/web/training] Add CreateTrainingSession (#17891)	2023-10-26 09:22:10 -07:00
proxy-wrapper.ts	[js/web/training] Add CreateTrainingSession (#17891)	2023-10-26 09:22:10 -07:00
run-options.ts
session-handler-inference.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
session-handler-training.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
session-options.ts	[WebNN EP] Support numThreads option for WebNN CPU device (#18054)	2023-11-12 16:45:10 -08:00
wasm-common.ts	[js/webgpu] support IO binding (#17480)	2023-09-29 11:24:42 -07:00
wasm-core-impl.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
wasm-factory.ts	Add "glue" between training WASM artifacts and training web (#17474)	2023-10-12 11:16:56 -07:00
wasm-training-core-impl.ts	[js/web/training] runTrainStep implementation (#18006)	2023-11-02 08:32:50 -07:00
wasm-utils.ts