When I set the infomerconfig.input_size = 1, I find a bug, but I don’t know how to fix it.
- Function Name :
create_network_inputs
time_feat = (
torch.cat(
(
past_time_features[:, self._past_length - self.config.context_length :, ...],
future_time_features,
),
dim=1,
)
if future_values is not None
else past_time_features[:, self._past_length - self.config.context_length :, ...]
)
print(self._past_length)
# target
if past_observed_mask is None:
past_observed_mask = torch.ones_like(past_values)
context = past_values[:, -self.config.context_length :]
observed_context = past_observed_mask[:, -self.config.context_length :]
_, loc, scale = self.scaler(context, observed_context)
inputs = (
(torch.cat((past_values, future_values), dim=1) - loc) / scale
if future_values is not None
else (past_values - loc) / scale
)
print(loc.shape, scale.shape, inputs.shape)
# static features
log_abs_loc = loc.abs().log1p() if self.config.input_size == 1 else loc.squeeze(1).abs().log1p()
log_scale = scale.log() if self.config.input_size == 1 else scale.squeeze(1).log()
print(f"log_abs_loc: {log_abs_loc.shape}, {log_scale.shape}")
print(time_feat.shape, self.config.input_size)
static_feat = torch.cat((log_abs_loc, log_scale), dim=1)
print(time_feat.shape, static_feat.shape)
if static_real_features is not None:
static_feat = torch.cat((static_real_features, static_feat), dim=1)
if static_categorical_features is not None:
embedded_cat = self.embedder(static_categorical_features)
static_feat = torch.cat((embedded_cat, static_feat), dim=1)
print(time_feat.shape, static_feat.shape)
expanded_static_feat = static_feat.unsqueeze(1).expand(-1, time_feat.shape[1], -1)
# all features
features = torch.cat((expanded_static_feat, time_feat), dim=-1)
# lagged features
subsequences_length = (
self.config.context_length + self.config.prediction_length
if future_values is not None
else self.config.context_length
)
lagged_sequence = self.get_lagged_subsequences(sequence=inputs, subsequences_length=subsequences_length)
lags_shape = lagged_sequence.shape
reshaped_lagged_sequence = lagged_sequence.reshape(lags_shape[0], lags_shape[1], -1)
if reshaped_lagged_sequence.shape[1] != time_feat.shape[1]:
raise ValueError(
f"input length {reshaped_lagged_sequence.shape[1]} and time feature lengths {time_feat.shape[1]} does not match"
)
# transformer inputs
transformer_inputs = torch.cat((reshaped_lagged_sequence, features), dim=-1)
return transformer_inputs, loc, scale, static_feat
As we can see, I add some print sentence in the library to see the shape, now the bug is:
Traceback (most recent call last):
File "/home/wjt/luck/FinalWork/alert_models/informer_based_model_3_cpu.py", line 820, in <module>
pipline.train_model()
File "/home/wjt/luck/FinalWork/alert_models/informer_based_model_3_cpu.py", line 466, in train_model
outputs = model(
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/transformers/models/informer/modeling_informer.py", line 1844, in forward
outputs = self.model(
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/transformers/models/informer/modeling_informer.py", line 1568, in forward
transformer_inputs, loc, scale, static_feat = self.create_network_inputs(
File "/home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages/transformers/models/informer/modeling_informer.py", line 1386, in create_network_inputs
expanded_static_feat = static_feat.unsqueeze(1).expand(-1, time_feat.shape[1], -1)
RuntimeError: expand(torch.cuda.FloatTensor{[32, 1, 2, 1]}, size=[-1, 27, -1]): the number of sizes provided (3) must be greater or equal to the number of dimensions in the tensor (4)
- First
log_abs_loc = loc.abs().log1p() if self.config.input_size == 1 else loc.squeeze(1).abs().log1p() log_scale = scale.log() if self.config.input_size == 1 else scale.squeeze(1).log()
If the input_size is 1, loc.squeeze will not execute, but now the loc.shape is (bsz, 1, 1), so it will be a hidden issue, and
- second
static_feat.unsqueeze(1) will execute, then the error will be reported
I don’t know whether it’s clear to clarify the problem, but I really need a help.
- environment
Name: transformers
Version: 4.52.3
Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Home-page: https://github.com/huggingface/transformers
Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)
Author-email: transformers@huggingface.co
License: Apache 2.0 License
Location: /home/wjt/.conda/envs/luckluck/lib/python3.9/site-packages
Requires: filelock, huggingface-hub, numpy, pack
Linux
python3.9.21