busishengui
busishengui
@mitchelldehaven No，I have not solved this problem. Which dataset do you use? Is it WSJ?
@YiwenShaoStephen Thank you very much for your reply. I'll give it a try.
@YiwenShaoStephen You deleted Chainloss function in loss.py，but what is the new loss function？
@YiwenShaoStephen I have tried the three methods you told me, but no matter on the training set or the verification set, the loss function does not converge, and still can...
E/tnn: ConvertHalfLayerResource [File source/tnn/interpreter/layer_resource_generator.cc][Line 109] Error: param is nil E/tnn: InitLayers [File source/tnn/core/default_network.cc][Line 321] Error Init layer Relu (err: 4096 or 0x1000)
> Hello,I cannot look for the batch inference sample, can you give me a sample?Thanks. you can use bert, or any transformers
@jdemouth-nvidia Anyone has some suggestion?
我也遇到了一样的问题