org.apache.clojure-mxnet.random — org.apache.clojure-mxnet/clojure-mxnet 0.1.0-SNAPSHOT

normal clj

(normal loc scale shape-vec)

(normal loc scale shape-vec {:keys [ctx out] :as opts})

Generate normal(Gaussian) distribution N(mean, stdvar^^2) with shape. loc: The standard deviation of the normal distribution scale: The upper bound of distribution. shape-vec: vector shape of the ndarray generated. opts-map { ctx: Context of output ndarray, will use default context if not specified. out: Output place holder} returns: The result ndarray with generated result./

seed clj

(seed seed-state)

Seed the random number generators in mxnet. This seed will affect behavior of functions in this module, as well as results from executors that contains Random number such as Dropout operators.

seed-state: The random number seed to set to all devices. note: The random number generator of mxnet is by default device specific. This means if you set the same seed, the random number sequence generated from GPU0 can be different from CPU.

uniform clj

(uniform low high shape-vec)

(uniform low high shape-vec {:keys [ctx out] :as opts})

Generate uniform distribution in [low, high) with shape. low: The lower bound of distribution. high: The upper bound of distribution. shape-vec: vector shape of the ndarray generated. opts-map { ctx: Context of output ndarray, will use default context if not specified. out: Output place holder} returns: The result ndarray with generated result./