search

alibaba-edu / simple-effective-text-matching-pytorch

A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Apache License 2.0
304 stars 54 forks source link

Abalation error #12

Closed Jch520 closed 2 years ago

Jch520 commented 2 years ago

Hi，when I did the abalation experiment, an error occurred in the residual connection module Traceback (most recent call last): File "train.py", line 49, in main() File "train.py", line 32, in main states = trainer.train() File "/hy-tmp/res_ave/src/trainer.py", line 52, in train stats = model.update(batch) File "/hy-tmp/res_ave/src/model.py", line 69, in update output = self.network(inputs) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, kwargs) File "/hy-tmp/res_ave/src/network.py", line 59, in forward a_enc = block['encoder'](a, mask_a) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, *kwargs) File "/hy-tmp/res_ave/src/modules/encoder.py", line 38, in forward x = encoder(x) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(input, kwargs) File "/hy-tmp/res_ave/src/modules/init.py", line 105, in forward return torch.cat([encoder(x) for encoder in self.model], dim=-1) File "/hy-tmp/res_ave/src/modules/init.py", line 105, in return torch.cat([encoder(x) for encoder in self.model], dim=-1) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, *kwargs) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward input = module(input) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(input, **kwargs) File "/usr/local/miniconda3/envs/res_torch/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 187, in forward self.padding, self.dilation, self.groups) RuntimeError: Given groups=1, weight of size [150, 450, 3], expected input[256, 150, 38] to have 450 channels, but got 150 channels instead. Thank you

hitvoice commented 2 years ago

Could you provide your config file?

Jch520 commented 2 years ago

I use the config file the github provide.I only do the connectio abalation

Jch520 commented 2 years ago

[ // residual connection { name: 'residual-conn', parents: [ 'default', 'data/snli', ], connection: 'residual', repeat: 4, }, { name: 'residual-conn', parents: [ 'default', 'data/scitail', ], repeat: 4, connection: 'residual' }, { name: 'residual-conn', parents: [ 'default', 'data/quora', ], repeat: 4, connection: 'residual' }, ]

hitvoice commented 2 years ago

OK, I'll look into it later.

hitvoice commented 2 years ago

@Jch520 fix by 4ce190e88f5dbc19f16fb69229e641e5ac50aa73

Background: The original experiments are run in Tensorflow. This pytorch implementation is a re-implementation that was created later. I checked the "default" experiment results and some of the ablations are the same as the Tensorflow version, but not all due to the time limit. In Tensorflow the dimensions are auto-assigned but in PyTorch we'll have to compute the exact numbers for all weights, so I overlooked this difference when first implementing it.