InvalidArgumentError (see above for traceback): indices[29,33] = 102685
Opened this issue · 0 comments
pengcao commented
你好，在运行/udc_train.py的时候报错，请问该怎么解决？ Thanks!
InvalidArgumentError (see above for traceback): indices[29,33] = 102685 is not in [0, 91620)
[[node embed_context (defined at F:\05.study\code\chatbot-retrieval\models\dual_encoder.py:37) = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, _class=["loc:@OptimizeLoss/train/update_word_embeddings/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](word_embeddings/read, read_batch_features_train/fifo_queue_Dequeue, embed_context/axis)]]