Method evaluate

model/Dynamic_network/DualPrompt.py:244–245 · view source on GitHub ↗

(self, round, infer_task_id, task)

Source from the content-addressed store, hash-verified

242	json.dump(df, file, ensure_ascii=False)
243
244	def evaluate(self, round, infer_task_id, task):
245	self.evaluate_one_task(round, infer_task_id, task)

nothing calls this directly

evaluate_one_taskMethod · 0.95

no test coverage detected