I'm writing my codes in dl4mt (an open source neural machine translation tool)
I encountered some weird problems in theano scan.
The following code was used to extract sub-tensor from a 3D tensor according to some indices.
the "indicesSub" in line 1098 is of shape (n_sample, window)
"sl" in 1099 is (n_sample, )
"cc_" in line 1100 is of shape (n_timestep, n_sample, dimctx),
the results of cc_result should be of shape (nsample, window, dimctx)
so in line 1116, where cc_ was already dimshuffled to shape (n_sample, n_timestep, dimctx), the three inputs are all sequences.
In the inner loop (_sub_step), indices is used as sequence parameter, the other two are non_sequences. The error occurs when training, which I will put on in the end. But when I use some trick to train a pseudo model and using it to test, the error doesn't show... Which is really weird because training and testing share the same codes.
The error is really weird, too. It says the input shape is (17, 256), (256, ), (), respectively. But according to my codes, the input shape should be (17, 256), (21, ), (), where 21 is window size.
I'm wondering if there's something that could change the input of scan? maybe a None input? I'm not sure. Please help me if you have any idea. Thank you
1098 indicesSub = indices_mask_[src_positions] # n_samples, window
1099 sl = sntlens.reshape([sntlens.shape[0], ]) # (n_sample, )
1100 ccshuffle = cc_.dimshuffle(1, 0, 2) # n_sample, n_timestep, dimctx
1101
1102 def _step_index(indices, cc_sub, sntlen_in):
1103 def _sub_step(indice_step, cc_step, len_step):
1104 # indice_step is a scalar
1105 # cc_step is (ntimestep * dimctx)
1106 # sntlen_in is a scalar
1107 r = tensor.switch(tensor.lt(indice_step, 0), 0, 1)
1108 l = tensor.switch(tensor.ge(indice_step, len_step), 0, 1)
1109 rt = ifelse(tensor.lt(r * l, 1), tensor.zeros([cc_step.shape[1], ]), cc_step[tensor.cast(indice_step, 'int64')])
1110 return rt
1111 ret, updt = theano.scan(_sub_step,
1112 sequences=indices,
1113 non_sequences=[cc_sub, sntlen_in])
1114 return ret
1115
1116 cc_result, upd = theano.scan(_step_index,
1117 sequences=[indicesSub, ccshuffle, sl])
1118
Error info:
24 File "theano/scan_module/scan_perform.pyx", line 397, in theano.scan_module.scan_perform.perform (/search/odin/chengshanbo/.theano/compiledir_Linux-2.6-el6.x86_64-x86_64-with-redhat-6.6-Santiago-x86_64-2.7. 11-64/scan_perform/mod.cpp:4193)
25 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/scan_module/scan_op.py", line 951, in rval
26 r = p(n, [x[0] for x in i], o)
27 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/scan_module/scan_op.py", line 940, in <lambda>
28 self, node)
29 File "theano/scan_module/scan_perform.pyx", line 405, in theano.scan_module.scan_perform.perform (/search/odin/chengshanbo/.theano/compiledir_Linux-2.6-el6.x86_64-x86_64-with-redhat-6.6-Santiago-x86_64-2.7. 11-64/scan_perform/mod.cpp:4316)
30 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/gof/link.py", line 314, in raise_with_op
31 reraise(exc_type, exc_value, exc_trace)
32 File "theano/scan_module/scan_perform.pyx", line 397, in theano.scan_module.scan_perform.perform (/search/odin/chengshanbo/.theano/compiledir_Linux-2.6-el6.x86_64-x86_64-with-redhat-6.6-Santiago-x86_64-2.7. 11-64/scan_perform/mod.cpp:4193)
33 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/scan_module/scan_op.py", line 951, in rval
34 r = p(n, [x[0] for x in i], o)
35 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/scan_module/scan_op.py", line 940, in <lambda>
36 self, node)
37 File "theano/scan_module/scan_perform.pyx", line 405, in theano.scan_module.scan_perform.perform (/search/odin/chengshanbo/.theano/compiledir_Linux-2.6-el6.x86_64-x86_64-with-redhat-6.6-Santiago-x86_64-2.7. 11-64/scan_perform/mod.cpp:4316)
38 File "/search/speech/chengshanbo/tools/anaconda2/lib/python2.7/site-packages/Theano-0.8.0-py2.7.egg/theano/gof/link.py", line 314, in raise_with_op
39 reraise(exc_type, exc_value, exc_trace)
40 File "theano/scan_module/scan_perform.pyx", line 397, in theano.scan_module.scan_perform.perform (/search/odin/chengshanbo/.theano/compiledir_Linux-2.6-el6.x86_64-x86_64-with-redhat-6.6-Santiago-x86_64-2.7. 11-64/scan_perform/mod.cpp:4193)
41 IndexError: index out of bounds
42 Apply node that caused the error: GpuIncSubtensor{Inc;int64}(GpuElemwise{add,no_inplace}.0, if{inplace,gpu}.0, ScalarFromTensor.0)
43 Toposort index: 5
44 Inputs types: [CudaNdarrayType(float32, matrix), CudaNdarrayType(float32, vector), Scalar(int64)]
45 Inputs shapes: [(17, 256), (256,), ()]
46 Inputs strides: [(256, 1), (1,), ()]
47 Inputs values: ['not shown', 'not shown', 17]
48 Outputs clients: [['output']]
49
Related
Relevant Code :
from transformers import (
AdamW,
MT5ForConditionalGeneration,
AutoTokenizer,
get_linear_schedule_with_warmup
)
tokenizer = AutoTokenizer.from_pretrained('google/byt5-small', use_fast=True)
model=MT5ForConditionalGeneration.from_pretrained("working/result/",
return_dict=True)
def generate(text):
model.eval()
# print(model)
# input_ids = tokenizer.encode("WebNLG:{} </s>".format(text),
# return_tensors="pt")
input_ids = tokenizer.batch_encode_plus(
[text], max_length=512, pad_to_max_length=True, return_tensors="pt"
).to(device)
source_ids = input_ids["input_ids"].squeeze()
print(tokenizer.decode(source_ids))
print(type(input_ids.input_ids))
input_ids.input_ids.to(device)
print(input)
outputs = model.generate(input_ids.input_ids)
print(outputs)
print(outputs[0])
return tokenizer.decode(outputs[0])
Calling above function
input_str = "Title: %s Category: %s" % ("10 Min Quick Food Recipe","Food")
input_str = "Title: %s Category: %s" % ("I am marathon runner and going to run 21km on 4th dec in Thane","Fitness")
print(input_str)
print(generate(input_str))
Output:
Title: I am marathon runner and going to run 21km on 4th dec in Thane Category: Fitness
Title: I am marathon runner and going to run 21km on 4th dec in Thane Category: Fitness</s><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad><pad>
<class 'torch.Tensor'>
<bound method Kernel.raw_input of <ipykernel.ipkernel.IPythonKernel object at 0x7ff645eed970>>
tensor([[ 0, 259, 266, 259, 3659, 390, 259, 262, 48580, 288,
259, 262, 38226, 5401, 259, 1]], device='cuda:0')
tensor([ 0, 259, 266, 259, 3659, 390, 259, 262, 48580, 288,
259, 262, 38226, 5401, 259, 1], device='cuda:0')
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In [30], line 5
2 input_str = "Title: %s Category: %s" % ("I am marathon runner and going to run 21km on 4th dec in Thane","Fitness")
4 print(input_str)
----> 5 print(generate(input_str))
Cell In [29], line 18, in generate(text)
16 print(outputs)
17 print(outputs[0])
---> 18 return tokenizer.decode(outputs[0])
File ~/T5/t5_venv/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:3436, in PreTrainedTokenizerBase.decode(self, token_ids, skip_special_tokens, clean_up_tokenization_spaces, **kwargs)
3433 # Convert inputs to python lists
3434 token_ids = to_py_obj(token_ids)
-> 3436 return self._decode(
3437 token_ids=token_ids,
3438 skip_special_tokens=skip_special_tokens,
3439 clean_up_tokenization_spaces=clean_up_tokenization_spaces,
3440 **kwargs,
3441 )
File ~/T5/t5_venv/lib/python3.8/site-packages/transformers/tokenization_utils.py:949, in PreTrainedTokenizer._decode(self, token_ids, skip_special_tokens, clean_up_tokenization_spaces, spaces_between_special_tokens, **kwargs)
947 current_sub_text.append(token)
948 if current_sub_text:
--> 949 sub_texts.append(self.convert_tokens_to_string(current_sub_text))
951 if spaces_between_special_tokens:
952 text = " ".join(sub_texts)
File ~/T5/t5_venv/lib/python3.8/site-packages/transformers/models/byt5/tokenization_byt5.py:243, in ByT5Tokenizer.convert_tokens_to_string(self, tokens)
241 tok_string = token.encode("utf-8")
242 else:
--> 243 tok_string = bytes([ord(token)])
244 bstring += tok_string
245 string = bstring.decode("utf-8", errors="ignore")
ValueError: bytes must be in range(0, 256)
I tried to change the max_length param to 256 but can't seems to get it work.
Any leads highly appreciated. Thanks in Advance.
Got it. I was doing a silly mistake. I was trying different pre-trained tokenizer and T5 models.
During training I had used google/mt5-base but during inference I used google/byt5-small which created this issue. Changed back to google/mt5-base to fix the issue. Now inference working fine.
I am trying to make a model to classify knee MRIs. I am using the torchio library and I have succesfully train a classifier to the raw data. Now, I am adding masks to the MRI object and I want to pass them to a model. I use the same code but now I am getting this error:
RuntimeError Traceback (most recent call last)
<ipython-input-56-2a7d5ddf84fc> in <module>()
26 for epoch in range(1, num_epochs+1):
27
---> 28 train_loss, train_accuracy = training(epoch,model,train_loader,optimizer,criterion)
29 valid_loss, valid_accuracy = validation(epoch,model,valid_loader,criterion)
30
6 frames
<ipython-input-55-59a55a26f2b7> in training(epoch, model, train_loader, optimizer, criterion)
8 model.train()
9
---> 10 for i, batch in tqdm(enumerate(train_loader,0)):
11 images = batch['t1'][tio.DATA].cuda()
12 labels = batch['label']
/usr/local/lib/python3.7/dist-packages/tqdm/notebook.py in __iter__(self)
255 def __iter__(self):
256 try:
--> 257 for obj in super(tqdm_notebook, self).__iter__():
258 # return super(tqdm...) will not catch exception
259 yield obj
/usr/local/lib/python3.7/dist-packages/tqdm/std.py in __iter__(self)
1193
1194 try:
-> 1195 for obj in iterable:
1196 yield obj
1197 # Update and possibly print the progressbar.
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in __next__(self)
519 if self._sampler_iter is None:
520 self._reset()
--> 521 data = self._next_data()
522 self._num_yielded += 1
523 if self._dataset_kind == _DatasetKind.Iterable and \
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in _next_data(self)
1201 else:
1202 del self._task_info[idx]
-> 1203 return self._process_data(data)
1204
1205 def _try_put_index(self):
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in _process_data(self, data)
1227 self._try_put_index()
1228 if isinstance(data, ExceptionWrapper):
-> 1229 data.reraise()
1230 return data
1231
/usr/local/lib/python3.7/dist-packages/torch/_utils.py in reraise(self)
432 # instantiate since we don't know how to
433 raise RuntimeError(msg) from None
--> 434 raise exception
435
436
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
return self.collate_fn(data)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in <dictcomp>
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in <dictcomp>
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 56, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: result type Float can't be cast to the desired output type Byte
The training() function is this:
def training(epoch, model, train_loader, optimizer, criterion):
"Training over an epoch"
metric_monitor = MetricMonitor()
model.train()
for i, batch in tqdm(enumerate(train_loader,0)):
images = batch['t1'][tio.DATA].cuda()
labels = batch['label'].cuda()
if images.sum() != 0:
output = F.softmax(model(images), dim =1)
loss = criterion(output, labels)
output = output.data.max(dim=1,keepdim=True)[1]
output = output.view(-1)
acc = calculate_acc(output, labels)
metric_monitor.update("Loss", loss.item())
metric_monitor.update("Accuracy", acc)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print("[Epoch: {epoch:03d}] Train | {metric_monitor}".format(epoch=epoch, metric_monitor=metric_monitor))
return metric_monitor.metrics['Loss']['avg'], metric_monitor.metrics['Accuracy']['avg']
When I run the code some batches pass but it stops on some batches and produces this error. I have checked my data and all of them are torch.FloatTensor
The labels are integers. Does anybody know how to fix this ?
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.
I am novice python data analyst trying to preprocess the text data (jsonl format) before it goes into Neural networks for topic modelling(VAE). I was able to clean the data and turn it into numpy array, further I wanted to apply label encoding to the cleaned text data but fail to do so. **How can one apply label encoding to list of list data format **?. The input data into label encoding is list of list and ouput has to be in same format.
numpy array format (type: <class 'numpy.ndarray'>)
[array([1131, 713, 857, 1130..........])
array([ 142, 1346, 1918, 1893, 61, 62, 1922,967......]) ])
array([135, 148, 14, 104, 154, 159, 136, 94, 149, 135, 117, 62, 130....])
array([135, 148, 14, 104, 154, 159, 136......])...................................]
The code is this way(after cleaning):(list of list -strings)
dictionary = gensim.corpora.Dictionary(process_texts) # creating a dictionary
label_covid_data =[list(filter(lambda x: x != -1, dictionary.doc2idx(doc))) for doc in process_texts] # converint it into numeric according to dictionary
covid_train_data,covid_test_data = train_test_split(label_covid_data, test_size=0.2, random_state = 3456) # dividing into train and test data
covid_train_narray = np.array([np.array(i) for i in covid_train_data]) # converting into numpy array format
label = preprocessing.LabelEncoder() # applying label encoding
covid_data_labels = label.fit_transform([label.fit_transform(i) for i in covid_train_narray])
Error I am getting:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\_label.py in _encode(values, uniques, encode, check_unknown)
111 try:
--> 112 res = _encode_python(values, uniques, encode)
113 except TypeError:
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\_label.py in _encode_python(values, uniques, encode)
59 if uniques is None:
---> 60 uniques = sorted(set(values))
61 uniques = np.array(uniques, dtype=values.dtype)
TypeError: unhashable type: 'numpy.ndarray'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-217-ebce4e37aad8> in <module>
4 label = preprocessing.LabelEncoder()
5 #movie_line_labels = label.fit_transform(covid_train_narray[0])
----> 6 covid_data_labels = label.fit_transform([label.fit_transform(i) for i in covid_train_narray])
7 covid_data_labels
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\_label.py in fit_transform(self, y)
250 """
251 y = column_or_1d(y, warn=True)
--> 252 self.classes_, y = _encode(y, encode=True)
253 return y
254
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\_label.py in _encode(values, uniques, encode, check_unknown)
112 res = _encode_python(values, uniques, encode)
113 except TypeError:
--> 114 raise TypeError("argument must be a string or number")
115 return res
116 else:
TypeError: argument must be a string or number
this is the main code. The images size is 420*420
import os
import chainer
from chainer import training
from chainer.training import extensions
batchsize = 64
epoch = 10
gpu = 0
dataset = "/content/gdrive/My Drive/images/"
out = "/content/gdrive/My Drive/DCGAN/"
resume = ""
n_hidden = 100
seed = 0
snapshot_interval = 200
display_interval = 100
# Set up a neural network to train
gen = Generator(n_hidden=n_hidden)
dis = Discriminator()
if gpu >= 0:
# Make a specified GPU current
chainer.backends.cuda.get_device_from_id(gpu).use()
gen.to_gpu() # Copy the model to the GPU
dis.to_gpu()
# Setup an optimizer
def make_optimizer(model, alpha=0.0002, beta1=0.5):
optimizer = chainer.optimizers.Adam(alpha=alpha, beta1=beta1)
optimizer.setup(model)
optimizer.add_hook(
chainer.optimizer_hooks.WeightDecay(0.0001), 'hook_dec')
return optimizer
opt_gen = make_optimizer(gen)
opt_dis = make_optimizer(dis)
if dataset == '':
# Load the CIFAR10 dataset if args.dataset is not specified
train, _ = chainer.datasets.get_cifar10(withlabel=False, scale=255.)
else:
all_files = os.listdir(dataset)
image_files = [f for f in all_files if ('png' in f or 'jpg' in f)]
print('{} contains {} image files'
.format(dataset, len(image_files)))
train = chainer.datasets\
.ImageDataset(paths=image_files, root=dataset)
# Setup an iterator
train_iter = chainer.iterators.SerialIterator(train, batchsize)
# Setup an updater
updater = DCGANUpdater(
models=(gen, dis),
iterator=train_iter,
optimizer={
'gen': opt_gen, 'dis': opt_dis},
device=gpu)
# Setup a trainer
trainer = training.Trainer(updater, (epoch, 'epoch'), out=out)
snapshot_interval = (snapshot_interval, 'iteration')
display_interval = (display_interval, 'iteration')
trainer.extend(
extensions.snapshot(filename='snapshot_iter_{.updater.iteration}.npz'),
trigger=snapshot_interval)
trainer.extend(extensions.snapshot_object(
gen, 'gen_iter_{.updater.iteration}.npz'), trigger=snapshot_interval)
trainer.extend(extensions.snapshot_object(
dis, 'dis_iter_{.updater.iteration}.npz'), trigger=snapshot_interval)
trainer.extend(extensions.LogReport(trigger=display_interval))
trainer.extend(extensions.PrintReport([
'epoch', 'iteration', 'gen/loss', 'dis/loss',
]), trigger=display_interval)
trainer.extend(extensions.ProgressBar(update_interval=10))
trainer.extend(
out_generated_image(
gen, dis,
420, 420, seed, out),
trigger=snapshot_interval)
if resume:
# Resume from a snapshot
chainer.serializers.load_npz(resume, trainer)
# Run the training
trainer.run()
Full error code
Exception in main training loop:
Invalid operation is performed in: LinearFunction (Forward)
Expect: x.shape[1] == W.shape[1]
Actual: 1384448 != 8192
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/chainer/training/trainer.py", line 315, in run
update()
File "/usr/local/lib/python3.6/dist-packages/chainer/training/updaters/standard_updater.py", line 165, in update
self.update_core()
File "<ipython-input-3-1c9eda353b43>", line 37, in update_core
y_real = dis(x_real)
File "/usr/local/lib/python3.6/dist-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "<ipython-input-2-8321f7283f65>", line 81, in forward
return self.l4(h)
File "/usr/local/lib/python3.6/dist-packages/chainer/link.py", line 242, in __call__
out = forward(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/chainer/links/connection/linear.py", line 138, in forward
return linear.linear(x, self.W, self.b, n_batch_axes=n_batch_axes)
File "/usr/local/lib/python3.6/dist-packages/chainer/functions/connection/linear.py", line 289, in linear
y, = LinearFunction().apply(args)
File "/usr/local/lib/python3.6/dist-packages/chainer/function_node.py", line 245, in apply
self._check_data_type_forward(in_data)
File "/usr/local/lib/python3.6/dist-packages/chainer/function_node.py", line 330, in _check_data_type_forward
self.check_type_forward(in_type)
File "/usr/local/lib/python3.6/dist-packages/chainer/functions/connection/linear.py", line 27, in check_type_forward
x_type.shape[1] == w_type.shape[1],
File "/usr/local/lib/python3.6/dist-packages/chainer/utils/type_check.py", line 546, in expect
expr.expect()
File "/usr/local/lib/python3.6/dist-packages/chainer/utils/type_check.py", line 483, in expect
'{0} {1} {2}'.format(left, self.inv, right))
Will finalize trainer extensions and updater before reraising the exception.
---------------------------------------------------------------------------
InvalidType Traceback (most recent call last)
<ipython-input-8-a0fb675be455> in <module>()
89
90 # Run the training
---> 91 trainer.run()
92
93
/usr/local/lib/python3.6/dist-packages/chainer/training/trainer.py in run(self, show_loop_exception_msg)
327 f.write('Will finalize trainer extensions and updater before '
328 'reraising the exception.\n')
--> 329 six.reraise(*sys.exc_info())
330 finally:
331 for _, entry in extensions:
/usr/local/lib/python3.6/dist-packages/six.py in reraise(tp, value, tb)
691 if value.__traceback__ is not tb:
692 raise value.with_traceback(tb)
--> 693 raise value
694 finally:
695 value = None
/usr/local/lib/python3.6/dist-packages/chainer/training/trainer.py in run(self, show_loop_exception_msg)
313 self.observation = {}
314 with reporter.scope(self.observation):
--> 315 update()
316 for name, entry in extensions:
317 if entry.trigger(self):
/usr/local/lib/python3.6/dist-packages/chainer/training/updaters/standard_updater.py in update(self)
163
164 """
--> 165 self.update_core()
166 self.iteration += 1
167
<ipython-input-3-1c9eda353b43> in update_core(self)
35 batchsize = len(batch)
36
---> 37 y_real = dis(x_real)
38
39 z = Variable(xp.asarray(gen.make_hidden(batchsize)))
/usr/local/lib/python3.6/dist-packages/chainer/link.py in __call__(self, *args, **kwargs)
240 if forward is None:
241 forward = self.forward
--> 242 out = forward(*args, **kwargs)
243
244 # Call forward_postprocess hook
<ipython-input-2-8321f7283f65> in forward(self, x)
79 h = F.leaky_relu(add_noise(self.bn2_1(self.c2_1(h))))
80 h = F.leaky_relu(add_noise(self.bn3_0(self.c3_0(h))))
---> 81 return self.l4(h)
/usr/local/lib/python3.6/dist-packages/chainer/link.py in __call__(self, *args, **kwargs)
240 if forward is None:
241 forward = self.forward
--> 242 out = forward(*args, **kwargs)
243
244 # Call forward_postprocess hook
/usr/local/lib/python3.6/dist-packages/chainer/links/connection/linear.py in forward(self, x, n_batch_axes)
136 in_size = functools.reduce(operator.mul, x.shape[1:], 1)
137 self._initialize_params(in_size)
--> 138 return linear.linear(x, self.W, self.b, n_batch_axes=n_batch_axes)
/usr/local/lib/python3.6/dist-packages/chainer/functions/connection/linear.py in linear(x, W, b, n_batch_axes)
287 args = x, W, b
288
--> 289 y, = LinearFunction().apply(args)
290 if n_batch_axes > 1:
291 y = y.reshape(batch_shape + (-1,))
/usr/local/lib/python3.6/dist-packages/chainer/function_node.py in apply(self, inputs)
243
244 if configuration.config.type_check:
--> 245 self._check_data_type_forward(in_data)
246
247 hooks = chainer.get_function_hooks()
/usr/local/lib/python3.6/dist-packages/chainer/function_node.py in _check_data_type_forward(self, in_data)
328 in_type = type_check.get_types(in_data, 'in_types', False)
329 with type_check.get_function_check_context(self):
--> 330 self.check_type_forward(in_type)
331
332 def check_type_forward(self, in_types):
/usr/local/lib/python3.6/dist-packages/chainer/functions/connection/linear.py in check_type_forward(self, in_types)
25 x_type.ndim == 2,
26 w_type.ndim == 2,
---> 27 x_type.shape[1] == w_type.shape[1],
28 )
29 if type_check.eval(n_in) == 3:
/usr/local/lib/python3.6/dist-packages/chainer/utils/type_check.py in expect(*bool_exprs)
544 for expr in bool_exprs:
545 assert isinstance(expr, Testable)
--> 546 expr.expect()
547
548
/usr/local/lib/python3.6/dist-packages/chainer/utils/type_check.py in expect(self)
481 raise InvalidType(
482 '{0} {1} {2}'.format(self.lhs, self.exp, self.rhs),
--> 483 '{0} {1} {2}'.format(left, self.inv, right))
484
485
InvalidType:
Invalid operation is performed in: LinearFunction (Forward)
Expect: x.shape[1] == W.shape[1]
Actual: 1384448 != 8192
The Discriminator
class Discriminator(chainer.Chain):
def __init__(self, bottom_width=4, ch=512, wscale=0.02):
w = chainer.initializers.Normal(wscale)
super(Discriminator, self).__init__()
with self.init_scope():
self.c0_0 = L.Convolution2D(3, ch // 8, 3, 1, 1, initialW=w)
self.c0_1 = L.Convolution2D(ch // 8, ch // 4, 4, 2, 1, initialW=w)
self.c1_0 = L.Convolution2D(ch // 4, ch // 4, 3, 1, 1, initialW=w)
self.c1_1 = L.Convolution2D(ch // 4, ch // 2, 4, 2, 1, initialW=w)
self.c2_0 = L.Convolution2D(ch // 2, ch // 2, 3, 1, 1, initialW=w)
self.c2_1 = L.Convolution2D(ch // 2, ch // 1, 4, 2, 1, initialW=w)
self.c3_0 = L.Convolution2D(ch // 1, ch // 1, 3, 1, 1, initialW=w)
self.l4 = L.Linear(bottom_width * bottom_width * ch, 1, initialW=w)
self.bn0_1 = L.BatchNormalization(ch // 4, use_gamma=False)
self.bn1_0 = L.BatchNormalization(ch // 4, use_gamma=False)
self.bn1_1 = L.BatchNormalization(ch // 2, use_gamma=False)
self.bn2_0 = L.BatchNormalization(ch // 2, use_gamma=False)
self.bn2_1 = L.BatchNormalization(ch // 1, use_gamma=False)
self.bn3_0 = L.BatchNormalization(ch // 1, use_gamma=False)
def forward(self, x):
h = add_noise(x)
h = F.leaky_relu(add_noise(self.c0_0(h)))
h = F.leaky_relu(add_noise(self.bn0_1(self.c0_1(h))))
h = F.leaky_relu(add_noise(self.bn1_0(self.c1_0(h))))
h = F.leaky_relu(add_noise(self.bn1_1(self.c1_1(h))))
h = F.leaky_relu(add_noise(self.bn2_0(self.c2_0(h))))
h = F.leaky_relu(add_noise(self.bn2_1(self.c2_1(h))))
h = F.leaky_relu(add_noise(self.bn3_0(self.c3_0(h))))
return self.l4(h)
So the problem was the value of bottom_width in the Discriminator it should be equal to the (image size)/(2^3). in this case it would be 420/2^3 = 52.5 but if the result is a float then you get the int value which is 52