Related
from torch import nn
from transformers.models.bert.modeling_bert import BertConfig
config = BertConfig.from_pretrained("bert-base-uncased")
self.x_head = nn.Linear(in_features=config.hidden_size, out_features=28)
word_embeddings = nn.Embedding( num_embeddings=979, embedding_dim=config.hidden_size ,padding_idx=0,)(ids_1).to(self.device)
vis_embeddings = nn.Embedding( num_embeddings=127, embedding_dim=config.hidden_size, padding_idx=0,)(ids_2).to(self.device)
input_embeds = torch.cat([word_embeddings , vis_embeddings] , dim =1).to(self.device)
in forward() method I have below code:
x_scores = self.x_head(input_embeds)
I am getting below error at x_scores(last line above)
~/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1050 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051 return forward_call(*input, **kwargs)
1052 # Do not call functions when jit is used
1053 full_backward_hooks, non_full_backward_hooks = [], []
~/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py in forward(self, *inputs, **kwargs)
166 return self.module(*inputs[0], **kwargs[0])
167 replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
--> 168 outputs = self.parallel_apply(replicas, inputs, kwargs)
169 return self.gather(outputs, self.output_device)
170
~/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py in parallel_apply(self, replicas, inputs, kwargs)
176
177 def parallel_apply(self, replicas, inputs, kwargs):
--> 178 return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
179
180 def gather(self, outputs, output_device):
~/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py in parallel_apply(modules, inputs, kwargs_tup, devices)
84 output = results[i]
85 if isinstance(output, ExceptionWrapper):
---> 86 output.reraise()
87 outputs.append(output)
88 return outputs
~/pytorch-env_py3.7/lib/python3.7/site-packages/torch/_utils.py in reraise(self)
423 # have message field
424 raise self.exc_type(message=msg)
--> 425 raise self.exc_type(msg)
426
427
RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/home/gems/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
output = module(*input, **kwargs)
File "/home/gems/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "", line 56, in forward
x_scores = self.x_head(input_embeds)
File "/home/gems/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/gems/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 96, in forward
return F.linear(input, self.weight, self.bias)
File "/home/gems/pytorch-env_py3.7/lib/python3.7/site-packages/torch/nn/functional.py", line 1847, in linear
return torch._C._nn.linear(input, weight, bias)
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling cublasCreate(handle)
Consider the following code:
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report, ndcg_score, make_scorer
from sklearn.svm import SVC
X_data = pd.DataFrame(np.random.randint(0,1,size=(100, 4)), columns=list('ABCD'))
X_data = sp.csr_matrix(X_data.to_numpy())
Y_data = pd.DataFrame(np.random.choice([0,1,5], 100), columns=['Y'])
# Set the parameters by cross-validation
param_grid = {'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
'C': [1, 10, 100, 1000]}
clf = GridSearchCV(SVC(), param_grid, scoring=ndcg_score, refit=True, verbose=3, n_jobs=-1, error_score='raise')
test = clf.fit(X_data, Y_data)
I am wondering why this would raise the following error:
Fitting 5 folds for each of 8 candidates, totalling 40 fits
---------------------------------------------------------------------------
_RemoteTraceback Traceback (most recent call last)
_RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\externals\loky\process_executor.py", line 431, in _process_worker
r = call_item()
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\externals\loky\process_executor.py", line 285, in __call__
return self.fn(*self.args, **self.kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\_parallel_backends.py", line 595, in __call__
return self.func(*args, **kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\parallel.py", line 262, in __call__
return [func(*args, **kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\parallel.py", line 262, in <listcomp>
return [func(*args, **kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\utils\fixes.py", line 222, in __call__
return self.function(*args, **kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\model_selection\_validation.py", line 625, in _fit_and_score
test_scores = _score(estimator, X_test, y_test, scorer, error_score)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\model_selection\_validation.py", line 687, in _score
scores = scorer(estimator, X_test, y_test)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\utils\validation.py", line 74, in inner_f
return f(**kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\metrics\_ranking.py", line 1564, in ndcg_score
y_true = check_array(y_true, ensure_2d=False)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "C:\Users\test\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\utils\validation.py", line 710, in check_array
array = array.astype(np.float64)
TypeError: float() argument must be a string or a number, not 'SVC'
"""
The above exception was the direct cause of the following exception:
TypeError Traceback (most recent call last)
<ipython-input-45-93a8890b095c> in <module>
18
19 clf = GridSearchCV(SVC(), param_grid, scoring=ndcg_score, refit=True, verbose=3, n_jobs=-1, error_score='raise')
---> 20 test = clf.fit(X_data, Y_data)
21 #print(test.best_score_)
~\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\utils\validation.py in inner_f(*args, **kwargs)
61 extra_args = len(args) - len(all_args)
62 if extra_args <= 0:
---> 63 return f(*args, **kwargs)
64
65 # extra_args > 0
~\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
839 return results
840
--> 841 self._run_search(evaluate_candidates)
842
843 # multimetric is determined here because in the case of a callable
~\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
1294 def _run_search(self, evaluate_candidates):
1295 """Search all candidates in param_grid"""
-> 1296 evaluate_candidates(ParameterGrid(self.param_grid))
1297
1298
~\Anaconda3\envs\kaggleSVM\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params, cv, more_results)
793 n_splits, n_candidates, n_candidates * n_splits))
794
--> 795 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
796 X, y,
797 train=train, test=test,
~\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1052
1053 with self._backend.retrieval_context():
-> 1054 self.retrieve()
1055 # Make sure that we get a last message telling us we are done
1056 elapsed_time = time.time() - self._start_time
~\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\parallel.py in retrieve(self)
931 try:
932 if getattr(self._backend, 'supports_timeout', False):
--> 933 self._output.extend(job.get(timeout=self.timeout))
934 else:
935 self._output.extend(job.get())
~\Anaconda3\envs\kaggleSVM\lib\site-packages\joblib\_parallel_backends.py in wrap_future_result(future, timeout)
540 AsyncResults.get from multiprocessing."""
541 try:
--> 542 return future.result(timeout=timeout)
543 except CfTimeoutError as e:
544 raise TimeoutError from e
~\Anaconda3\envs\kaggleSVM\lib\concurrent\futures\_base.py in result(self, timeout)
442 raise CancelledError()
443 elif self._state == FINISHED:
--> 444 return self.__get_result()
445 else:
446 raise TimeoutError()
~\Anaconda3\envs\kaggleSVM\lib\concurrent\futures\_base.py in __get_result(self)
387 if self._exception:
388 try:
--> 389 raise self._exception
390 finally:
391 # Break a reference cycle with the exception in self._exception
TypeError: float() argument must be a string or a number, not 'SVC'
I am not quite sure why this would result in a TypeError.
I cannot recreate the error you are reporting, but using error_score="raise" and n_jobs=1 (not strictly necessary, but the output is a little easier to read), and wrapping ndcg_score with make_scorer with needs_proba=True, I get this one:
Only ('multilabel-indicator', 'continuous-multioutput', 'multiclass-multioutput') formats are supported. Got multiclass instead
which supports my first comment: NDCG assumes multilabel format. That suggests you need to understand whether NDCG is really appropriate for your task, and if so either turn your problem into a multilabel one or write a custom scorer that converts the multiclass output into a multilabel (one-hot encoded) one before computing the score.
How do I run the run_language_modeling.py script from hugging face using the pretrained roberta case model to fine-tune using my own data on the Azure databricks with a GPU cluster.
Using Transformer version 2.9.1 and 3.0 .
Python 3.6
Torch `1.5.0
torchvision 0.6
This is the script I ran below on Azure databricks
%run '/dbfs/FileStore/tables/dev/run_language_modeling.py' \
--output_dir='/dbfs/FileStore/tables/final_train/models/roberta_base_reduce_n' \
--model_type=roberta \
--model_name_or_path=roberta-base \
--do_train \
--num_train_epochs 5 \
--train_data_file='/dbfs/FileStore/tables/final_train/train_data/all_data_desc_list_full.txt' \
--mlm
This is the error I get after running the above command.
/dbfs/FileStore/tables/dev/run_language_modeling.py in <module>
279
280 if __name__ == "__main__":
--> 281 main()
/dbfs/FileStore/tables/dev/run_language_modeling.py in main()
243 else None
244 )
--> 245 trainer.train(model_path=model_path)
246 trainer.save_model()
247 # For convenience, we also re-save the tokenizer to the same directory,
/databricks/python/lib/python3.7/site-packages/transformers/trainer.py in train(self, model_path)
497 continue
498
--> 499 tr_loss += self._training_step(model, inputs, optimizer)
500
501 if (step + 1) % self.args.gradient_accumulation_steps == 0 or (
/databricks/python/lib/python3.7/site-packages/transformers/trainer.py in _training_step(self, model, inputs, optimizer)
620 inputs["mems"] = self._past
621
--> 622 outputs = model(**inputs)
623 loss = outputs[0] # model outputs are always tuple in transformers (see doc)
624
/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
/databricks/python/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py in forward(self, *inputs, **kwargs)
153 return self.module(*inputs[0], **kwargs[0])
154 replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
--> 155 outputs = self.parallel_apply(replicas, inputs, kwargs)
156 return self.gather(outputs, self.output_device)
157
/databricks/python/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py in parallel_apply(self, replicas, inputs, kwargs)
163
164 def parallel_apply(self, replicas, inputs, kwargs):
--> 165 return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
166
167 def gather(self, outputs, output_device):
/databricks/python/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py in parallel_apply(modules, inputs, kwargs_tup, devices)
83 output = results[i]
84 if isinstance(output, ExceptionWrapper):
---> 85 output.reraise()
86 outputs.append(output)
87 return outputs
/databricks/python/lib/python3.7/site-packages/torch/_utils.py in reraise(self)
393 # (https://bugs.python.org/issue2651), so we work around it.
394 msg = KeyErrorMessage(msg)
--> 395 raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/databricks/python/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker
output = module(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_roberta.py", line 239, in forward
output_hidden_states=output_hidden_states,
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_bert.py", line 762, in forward
output_hidden_states=output_hidden_states,
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_bert.py", line 439, in forward
output_attentions,
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_bert.py", line 371, in forward
hidden_states, attention_mask, head_mask, output_attentions=output_attentions,
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_bert.py", line 315, in forward
hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, output_attentions,
File "/databricks/python/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/databricks/python/lib/python3.7/site-packages/transformers/modeling_bert.py", line 240, in forward
attention_scores = attention_scores / math.sqrt(self.attention_head_size)
RuntimeError: CUDA out of memory. Tried to allocate 96.00 MiB (GPU 0; 11.17 GiB total capacity; 10.68 GiB already allocated; 95.31 MiB free; 10.77 GiB reserved in total by PyTorch)```
Please how do I resolve this
The out of memory error is likely caused by not cleaning up the session and or freeing up the GPU.
From the similar Github issue.
It is because of mini-batch of data does not fit on to GPU memory. Just decrease the batch size. When I set batch size = 256 for cifar10 dataset I got the same error; Then I set the batch size = 128, it is solved.
I was wondering if tensorflow 2.2 dataset has an issue on Windows release.
Here is my diagnostic code
import numpy as np
import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_datasets as tfds
print("Version: ", tf.__version__)
print("Eager mode: ", tf.executing_eagerly())
print("Hub version: ", hub.__version__)
print("GPU is", "available" if tf.config.experimental.list_physical_devices("GPU") else "NOT AVAILABLE")
Version: 2.2.0
Eager mode: True
Hub version: 0.8.0
GPU is available
I can load the list of datasets
tfds.list_builders()
['abstract_reasoning',
'aeslc',
'aflw2k3d',
'amazon_us_reviews',
'anli',
.
.
.
'xnli',
'xsum',
'yelp_polarity_reviews']
However, I am unable to load any dataset
imdb, info = tfds.load('imdb_reviews', with_info=True, as_supervised=True)
I receive the following errors
---------------------------------------------------------------------------
UnimplementedError Traceback (most recent call last)
c:\python37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in try_reraise(*args, **kwargs)
398 try:
--> 399 yield
400 except Exception: # pylint: disable=broad-except
c:\python37\lib\site-packages\tensorflow_datasets\core\registered.py in builder(name, **builder_init_kwargs)
243 prefix="Failed to construct dataset {}".format(name)):
--> 244 return builder_cls(name)(**builder_kwargs)
245
c:\python37\lib\site-packages\wrapt\wrappers.py in __call__(self, *args, **kwargs)
602 return self._self_wrapper(self.__wrapped__, self._self_instance,
--> 603 args, kwargs)
604
c:\python37\lib\site-packages\tensorflow_datasets\core\api_utils.py in disallow_positional_args_dec(fn, instance, args, kwargs)
68 _check_required(fn, kwargs)
---> 69 return fn(*args, **kwargs)
70
c:\python37\lib\site-packages\tensorflow_datasets\core\dataset_builder.py in __init__(self, data_dir, config, version)
205 else: # Use the code version (do not restore data)
--> 206 self.info.initialize_from_bucket()
207
c:\python37\lib\site-packages\tensorflow_datasets\core\dataset_info.py in initialize_from_bucket(self)
422 tmp_dir = tempfile.mkdtemp("tfds")
--> 423 data_files = gcs_utils.gcs_dataset_info_files(self.full_name)
424 if not data_files:
c:\python37\lib\site-packages\tensorflow_datasets\core\utils\gcs_utils.py in gcs_dataset_info_files(dataset_dir)
69 """Return paths to GCS files in the given dataset directory."""
---> 70 return gcs_listdir(posixpath.join(GCS_DATASET_INFO_DIR, dataset_dir))
71
c:\python37\lib\site-packages\tensorflow_datasets\core\utils\gcs_utils.py in gcs_listdir(dir_name)
62 root_dir = gcs_path(dir_name)
---> 63 if _is_gcs_disabled or not tf.io.gfile.exists(root_dir):
64 return None
c:\python37\lib\site-packages\tensorflow\python\lib\io\file_io.py in file_exists_v2(path)
266 try:
--> 267 _pywrap_file_io.FileExists(compat.as_bytes(path))
268 except errors.NotFoundError:
UnimplementedError: File system scheme 'gs' not implemented (file: 'gs://tfds-data/dataset_info/imdb_reviews/plain_text/1.0.0')
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-36-06930b64f980> in <module>
1 #tfds.list_builders()
----> 2 imdb, info = tfds.load('imdb_reviews', with_info=True, as_supervised=True)
c:\python37\lib\site-packages\wrapt\wrappers.py in __call__(self, *args, **kwargs)
562
563 return self._self_wrapper(self.__wrapped__, self._self_instance,
--> 564 args, kwargs)
565
566 class BoundFunctionWrapper(_FunctionWrapperBase):
c:\python37\lib\site-packages\tensorflow_datasets\core\api_utils.py in disallow_positional_args_dec(fn, instance, args, kwargs)
67 _check_no_positional(fn, args, ismethod, allowed=allowed)
68 _check_required(fn, kwargs)
---> 69 return fn(*args, **kwargs)
70
71 return disallow_positional_args_dec(wrapped) # pylint: disable=no-value-for-parameter
c:\python37\lib\site-packages\tensorflow_datasets\core\registered.py in load(name, split, data_dir, batch_size, shuffle_files, download, as_supervised, decoders, read_config, with_info, builder_kwargs, download_and_prepare_kwargs, as_dataset_kwargs, try_gcs)
366 data_dir = constants.DATA_DIR
367
--> 368 dbuilder = builder(name, data_dir=data_dir, **builder_kwargs)
369 if download:
370 download_and_prepare_kwargs = download_and_prepare_kwargs or {}
c:\python37\lib\site-packages\tensorflow_datasets\core\registered.py in builder(name, **builder_init_kwargs)
242 with py_utils.try_reraise(
243 prefix="Failed to construct dataset {}".format(name)):
--> 244 return builder_cls(name)(**builder_kwargs)
245
246
c:\python37\lib\contextlib.py in __exit__(self, type, value, traceback)
128 value = type()
129 try:
--> 130 self.gen.throw(type, value, traceback)
131 except StopIteration as exc:
132 # Suppress StopIteration *unless* it's the same exception that
c:\python37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in try_reraise(*args, **kwargs)
399 yield
400 except Exception: # pylint: disable=broad-except
--> 401 reraise(*args, **kwargs)
402
403
c:\python37\lib\site-packages\tensorflow_datasets\core\utils\py_utils.py in reraise(prefix, suffix)
390 suffix = '\n' + suffix if suffix else ''
391 msg = prefix + str(exc_value) + suffix
--> 392 six.reraise(exc_type, exc_type(msg), exc_traceback)
393
394
TypeError: __init__() missing 2 required positional arguments: 'op' and 'message'
Is the library broken? As mentioned, I am on Windows 10 machine and using Jupyter Lab.
After I reported the issue on GitHub, the problem was fixed in version 3.2.1.
I created a Variational Autoencoder model. To do the sampling, I created the following method:
from keras import backend as k
def sampling(args):
z_mean , z_log_var=args
batch=k.shape(z_mean)[0]
dim=k.int_shape(z_mean)[1]
epsilon=k.random_normal(shape=(batch,dim))
return z_mean + k.exp(0.5 * z_log_var) * epsilon
this is the model architecture:
def create_variationalModel(original_dim):
input_shape=(original_dim,)
intermidiate_dim=58
batch_size=10
latent_dim=3
epochs=100
inputs=Input(shape=input_shape,name="encoder_input")
x= Dense(units=original_dim,activation="tanh")(inputs)
x= Dense(units=int(original_dim/2),activation="tanh")(x)
x1= Dense(units=int(original_dim/4),activation="tanh")(x)
x2= Dense(units=int(original_dim/8),activation="tanh")(x1)
x3= Dense(units=10,activation="tanh")(x2)
z_mean=Dense(latent_dim,name="z_mean")(x3)
z_log_var=Dense(latent_dim,name="z_log_var")(x3)
z=Lambda(sampling,output_shape=(latent_dim,),name="z")([z_mean,z_log_var])
encoder=Model(inputs,[z_mean,z_log_var,z],name="encoder")
encoder.summary()
latent_inputs=Input(shape=(latent_dim,),name="z_sampling")
x= Dense(units=10,activation="tanh")(latent_inputs)
x1=Dense(units=int(original_dim/8),activation="tanh")(x)
x2=Dense(units=int(original_dim/4),activation="tanh")(x1)
x3=Dense(units=int(original_dim/2),activation="tanh")(x2)
x3=Dense(units=original_dim,activation="tanh")(x3)
outputs=Dense(units=original_dim,activation="sigmoid")(x3)
decoder=Model(latent_inputs,outputs,name="decoder")
decoder.summary()
outputs=decoder(encoder(inputs)[2])
vae = Model(inputs,outputs,name="vae_mlp")
reconstruction_loss=mse(inputs,outputs)
reconstruction_loss*=original_dim
kl_loss = 1 + z_log_var -k.square(z_mean) - k.exp(z_log_var)
kl_loss=k.sum(kl_loss,axis=-1)
kl_loss*=-0.5
vae_loss=k.mean(reconstruction_loss+kl_loss)
vae.add_loss(vae_loss)
plot_model(vae,to_file='vae.png',show_shapes=True)
vae.compile(optimizer=RMSprop(),loss="mean_squared_error",metrics=["mae"])
return vae
the after training the model and test it, I decide to save it like this:
vae.save("./models/vae.h5")
but when I tried to load the model like this:
model = load_model("./models/vae.h5")
I have this issue:
--------------------------------------------------------------------------- NameError Traceback (most recent call
last) in
1 #load model
----> 2 model = load_model("./models/vae.h5")
3 # summarize model.
4 model.summary()
5 with open("./models/LabelEncoders_dic.pickle","rb") as f:
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in load_wrapper(*args, **kwargs)
490 os.remove(tmp_filepath)
491 return res
--> 492 return load_function(*args, **kwargs)
493
494 return load_wrapper
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in load_model(filepath, custom_objects, compile)
582 if H5Dict.is_supported_type(filepath):
583 with H5Dict(filepath, mode='r') as h5dict:
--> 584 model = _deserialize_model(h5dict, custom_objects, compile)
585 elif hasattr(filepath, 'write') and callable(filepath.write):
586 def load_function(h5file):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in _deserialize_model(h5dict, custom_objects, compile)
272 raise ValueError('No model found in config.')
273 model_config = json.loads(model_config.decode('utf-8'))
--> 274 model = model_from_config(model_config, custom_objects=custom_objects)
275 model_weights_group = h5dict['model_weights']
276
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in model_from_config(config, custom_objects)
625 'Sequential.from_config(config)?')
626 from ..layers import deserialize
--> 627 return deserialize(config, custom_objects=custom_objects)
628
629
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/init.py
in deserialize(config, custom_objects)
163 globs['Model'] = models.Model
164 globs['Sequential'] = models.Sequential
--> 165 return deserialize_keras_object(config,
166 module_objects=globs,
167 custom_objects=custom_objects,
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/utils/generic_utils.py
in deserialize_keras_object(identifier, module_objects,
custom_objects, printable_module_name)
142 custom_objects = custom_objects or {}
143 if has_arg(cls.from_config, 'custom_objects'):
--> 144 return cls.from_config(
145 config['config'],
146 custom_objects=dict(list(_GLOBAL_CUSTOM_OBJECTS.items()) +
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in from_config(cls, config, custom_objects) 1054 # First,
we create all layers and enqueue nodes to be processed 1055
for layer_data in config['layers']:
-> 1056 process_layer(layer_data) 1057 1058 # Then we process nodes in order of layer depth.
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in process_layer(layer_data) 1039 from ..layers import
deserialize as deserialize_layer 1040
-> 1041 layer = deserialize_layer(layer_data, 1042 custom_objects=custom_objects) 1043
created_layers[layer_name] = layer
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/init.py
in deserialize(config, custom_objects)
163 globs['Model'] = models.Model
164 globs['Sequential'] = models.Sequential
--> 165 return deserialize_keras_object(config,
166 module_objects=globs,
167 custom_objects=custom_objects,
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/utils/generic_utils.py
in deserialize_keras_object(identifier, module_objects,
custom_objects, printable_module_name)
142 custom_objects = custom_objects or {}
143 if has_arg(cls.from_config, 'custom_objects'):
--> 144 return cls.from_config(
145 config['config'],
146 custom_objects=dict(list(_GLOBAL_CUSTOM_OBJECTS.items()) +
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in from_config(cls, config, custom_objects) 1073
node_data = node_data_list[node_index] 1074
try:
-> 1075 process_node(layer, node_data) 1076 1077 # If the node does not have all
inbound layers
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in process_node(layer, node_data) 1023 # and building
the layer if needed. 1024 if input_tensors:
-> 1025 layer(unpack_singleton(input_tensors), **kwargs) 1026 1027 def process_layer(layer_data):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/backend/tensorflow_backend.py
in symbolic_fn_wrapper(*args, **kwargs)
73 if _SYMBOLIC_SCOPE.value:
74 with get_graph().as_default():
---> 75 return func(*args, **kwargs)
76 else:
77 return func(*args, **kwargs)
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/base_layer.py
in call(self, inputs, **kwargs)
487 # Actually call the layer,
488 # collecting output(s), mask(s), and shape(s).
--> 489 output = self.call(inputs, **kwargs)
490 output_mask = self.compute_mask(inputs, previous_mask)
491
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/core.py
in call(self, inputs, mask)
714 else:
715 self._input_dtypes = K.dtype(inputs)
--> 716 return self.function(inputs, **arguments)
717
718 def compute_mask(self, inputs, mask=None):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/core.py
in sampling(args)
NameError: name 'k' is not defined
K comes from from keras import backend as k. even y adding this importation, I have the same error. Can anyone know how to fix this ?