RandomSampler
RandomSampler 類別
keras_nlp.samplers.RandomSampler(seed=None, **kwargs)
隨機採樣器類別。
此採樣器會執行隨機採樣。簡而言之，隨機採樣器會從標記的整個分佈中隨機選擇一個標記，選擇機率由每個標記的機率決定。
參數
- seed：int。隨機數種子。預設為
None。
呼叫參數
{{call_args}}
範例
causal_lm = keras_nlp.models.GPT2CausalLM.from_preset("gpt2_base_en")
# Pass by name to compile.
causal_lm.compile(sampler="random")
causal_lm.generate(["Keras is a"])
# Pass by object to compile.
sampler = keras_nlp.samplers.RandomSampler(temperature=0.7)
causal_lm.compile(sampler=sampler)
causal_lm.generate(["Keras is a"])