We Keep Coding

unable to load the model [duplicate]

I want to load FaceNet in Keras but I am getting errors.
the modal facenet_keras.h5 is ready but I can't load it.
you can get facenet_keras.h5 from this link:
https://drive.google.com/drive/folders/1pwQ3H4aJ8a6yyJHZkTwtjcL4wYWQb7bn
My tensorflow version is:
tensorflow.__version__
'2.2.0'
and when i want to load data:
from tensorflow.keras.models import load_model
load_model('facenet_keras.h5')
get this error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-6-2a20f38e8217> in <module>
----> 1 load_model('facenet_keras.h5')
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/save.py in load_model(filepath, custom_objects, compile)
182 if (h5py is not None and (
183 isinstance(filepath, h5py.File) or h5py.is_hdf5(filepath))):
--> 184 return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
185
186 if sys.version_info >= (3, 4) and isinstance(filepath, pathlib.Path):
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/hdf5_format.py in load_model_from_hdf5(filepath, custom_objects, compile)
175 raise ValueError('No model found in config file.')
176 model_config = json.loads(model_config.decode('utf-8'))
--> 177 model = model_config_lib.model_from_config(model_config,
178 custom_objects=custom_objects)
179
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py in model_from_config(config, custom_objects)
53 '`Sequential.from_config(config)`?')
54 from tensorflow.python.keras.layers import deserialize # pylint: disable=g-import-not-at-top
---> 55 return deserialize(config, custom_objects=custom_objects)
56
57
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py in deserialize(config, custom_objects)
103 config['class_name'] = _DESERIALIZATION_TABLE[layer_class_name]
104
--> 105 return deserialize_keras_object(
106 config,
107 module_objects=globs,
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
367
368 if 'custom_objects' in arg_spec.args:
--> 369 return cls.from_config(
370 cls_config,
371 custom_objects=dict(
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in from_config(cls, config, custom_objects)
984 ValueError: In case of improperly formatted config dict.
985 """
--> 986 input_tensors, output_tensors, created_layers = reconstruct_from_config(
987 config, custom_objects)
988 model = cls(inputs=input_tensors, outputs=output_tensors,
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in reconstruct_from_config(config, custom_objects, created_layers)
2017 # First, we create all layers and enqueue nodes to be processed
2018 for layer_data in config['layers']:
-> 2019 process_layer(layer_data)
2020 # Then we process nodes in order of layer depth.
2021 # Nodes that cannot yet be processed (if the inbound node
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py in process_layer(layer_data)
1999 from tensorflow.python.keras.layers import deserialize as deserialize_layer # pylint: disable=g-import-not-at-top
2000
-> 2001 layer = deserialize_layer(layer_data, custom_objects=custom_objects)
2002 created_layers[layer_name] = layer
2003
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py in deserialize(config, custom_objects)
103 config['class_name'] = _DESERIALIZATION_TABLE[layer_class_name]
104
--> 105 return deserialize_keras_object(
106 config,
107 module_objects=globs,
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
367
368 if 'custom_objects' in arg_spec.args:
--> 369 return cls.from_config(
370 cls_config,
371 custom_objects=dict(
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py in from_config(cls, config, custom_objects)
988 def from_config(cls, config, custom_objects=None):
989 config = config.copy()
--> 990 function = cls._parse_function_from_config(
991 config, custom_objects, 'function', 'module', 'function_type')
992
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py in _parse_function_from_config(cls, config, custom_objects, func_attr_name, module_attr_name, func_type_attr_name)
1040 elif function_type == 'lambda':
1041 # Unsafe deserialization from bytecode
-> 1042 function = generic_utils.func_load(
1043 config[func_attr_name], globs=globs)
1044 elif function_type == 'raw':
~/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py in func_load(code, defaults, closure, globs)
469 except (UnicodeEncodeError, binascii.Error):
470 raw_code = code.encode('raw_unicode_escape')
--> 471 code = marshal.loads(raw_code)
472 if globs is None:
473 globs = globals()
ValueError: bad marshal data (unknown type code)
thank you.

The possible solutions to this error are shown below:
The Model might have been built and saved in Python 2.x and you might be using Python 3.x. Solution is to use the same Python Version using which the Model has been Built and Saved.
Use the same version of Keras (and, may be, tensorflow), on which your Model was Built and Saved.
The Saved Model might contain Custom Objects. If so, you need to load the Model using the code,
new_model = tf.keras.models.load_model('model.h5', custom_objects={'CustomLayer': CustomLayer})
If you can recreate the architecture (i.e. you have the original code used to generate it), you can instantiate the model from that code and then use model.load_weights('your_model_file.hdf5') to load in the weights. This isn't an option if you don't have the code used to create the original architecture.
For more details, please refer this Github Issue. For more details regarding Saving and Loading the Model with Custom Objects, please refer this Tensorflow Documentation and this Stack Overflow Answer.

I change python version(3.10 to 3.7) and its solved for me.

Raytune is throwing error: "module 'pickle' has no attribute 'PickleBuffer'" when attempting hyperparameter search

I am more or less following this example to integrate the ray tune hyperparameter library with the huggingface transformers library using my own dataset.
Here is my script:
import ray
from ray import tune
from ray.tune import CLIReporter
from ray.tune.examples.pbt_transformers.utils import download_data, \
build_compute_metrics_fn
from ray.tune.schedulers import PopulationBasedTraining
from transformers import glue_tasks_num_labels, AutoConfig, \
AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments
def get_model():
# tokenizer = AutoTokenizer.from_pretrained(model_name, additional_special_tokens = ['[CHARACTER]'])
model = ElectraForSequenceClassification.from_pretrained('google/electra-small-discriminator', num_labels=2)
model.resize_token_embeddings(len(tokenizer))
return model
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
def compute_metrics(pred):
labels = pred.label_ids
preds = pred.predictions.argmax(-1)
precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average='weighted')
acc = accuracy_score(labels, preds)
return {
'accuracy': acc,
'f1': f1,
'precision': precision,
'recall': recall
}
training_args = TrainingArguments(
"electra_hp_tune",
report_to = "wandb",
learning_rate=2e-5, # config
do_train=True,
do_eval=True,
evaluation_strategy="epoch",
load_best_model_at_end=True,
num_train_epochs=2, # config
per_device_train_batch_size=16, # config
per_device_eval_batch_size=16, # config
warmup_steps=0,
weight_decay=0.1, # config
logging_dir="./logs",
)
trainer = Trainer(
model_init=get_model,
args=training_args,
train_dataset=chunked_encoded_dataset['train'],
eval_dataset=chunked_encoded_dataset['validation'],
compute_metrics=compute_metrics
)
tune_config = {
"per_device_train_batch_size": 32,
"per_device_eval_batch_size": 32,
"num_train_epochs": tune.choice([2, 3, 4, 5])
}
scheduler = PopulationBasedTraining(
time_attr="training_iteration",
metric="eval_acc",
mode="max",
perturbation_interval=1,
hyperparam_mutations={
"weight_decay": tune.uniform(0.0, 0.3),
"learning_rate": tune.uniform(1e-5, 2.5e-5),
"per_device_train_batch_size": [16, 32, 64],
})
reporter = CLIReporter(
parameter_columns={
"weight_decay": "w_decay",
"learning_rate": "lr",
"per_device_train_batch_size": "train_bs/gpu",
"num_train_epochs": "num_epochs"
},
metric_columns=[
"eval_f1", "eval_loss", "epoch", "training_iteration"
])
from ray.tune.integration.wandb import WandbLogger
trainer.hyperparameter_search(
hp_space=lambda _: tune_config,
backend="ray",
n_trials=10,
scheduler=scheduler,
keep_checkpoints_num=1,
checkpoint_score_attr="training_iteration",
progress_reporter=reporter,
name="tune_transformer_gr")
The last function call (to trainer.hyperparameter_search) is when the error is raised. The error message is:
AttributeError: module 'pickle' has no attribute 'PickleBuffer'
And here is the full stack trace:
AttributeError Traceback (most recent call
last)
in ()
8 checkpoint_score_attr="training_iteration",
9 progress_reporter=reporter,
---> 10 name="tune_transformer_gr")
14 frames
/usr/local/lib/python3.7/dist-packages/transformers/trainer.py in
hyperparameter_search(self, hp_space, compute_objective, n_trials,
direction, backend, hp_name, **kwargs) 1666 1667
run_hp_search = run_hp_search_optuna if backend ==
HPSearchBackend.OPTUNA else run_hp_search_ray
-> 1668 best_run = run_hp_search(self, n_trials, direction, **kwargs) 1669 1670 self.hp_search_backend = None
/usr/local/lib/python3.7/dist-packages/transformers/integrations.py in
run_hp_search_ray(trainer, n_trials, direction, **kwargs)
231
232 analysis = ray.tune.run(
--> 233 ray.tune.with_parameters(_objective, local_trainer=trainer),
234 config=trainer.hp_space(None),
235 num_samples=n_trials,
/usr/local/lib/python3.7/dist-packages/ray/tune/utils/trainable.py in
with_parameters(trainable, **kwargs)
294 prefix = f"{str(trainable)}_"
295 for k, v in kwargs.items():
--> 296 parameter_registry.put(prefix + k, v)
297
298 trainable_name = getattr(trainable, "name", "tune_with_parameters")
/usr/local/lib/python3.7/dist-packages/ray/tune/registry.py in
put(self, k, v)
160 self.to_flush[k] = v
161 if ray.is_initialized():
--> 162 self.flush()
163
164 def get(self, k):
/usr/local/lib/python3.7/dist-packages/ray/tune/registry.py in
flush(self)
169 def flush(self):
170 for k, v in self.to_flush.items():
--> 171 self.references[k] = ray.put(v)
172 self.to_flush.clear()
173
/usr/local/lib/python3.7/dist-packages/ray/_private/client_mode_hook.py
in wrapper(*args, **kwargs)
45 if client_mode_should_convert():
46 return getattr(ray, func.name)(*args, **kwargs)
---> 47 return func(*args, **kwargs)
48
49 return wrapper
/usr/local/lib/python3.7/dist-packages/ray/worker.py in put(value)
1512 with profiling.profile("ray.put"): 1513 try:
-> 1514 object_ref = worker.put_object(value) 1515 except ObjectStoreFullError: 1516 logger.info(
/usr/local/lib/python3.7/dist-packages/ray/worker.py in
put_object(self, value, object_ref)
259 "inserting with an ObjectRef")
260
--> 261 serialized_value = self.get_serialization_context().serialize(value)
262 # This must be the first place that we construct this python
263 # ObjectRef because an entry with 0 local references is created when
/usr/local/lib/python3.7/dist-packages/ray/serialization.py in
serialize(self, value)
322 return RawSerializedObject(value)
323 else:
--> 324 return self._serialize_to_msgpack(value)
/usr/local/lib/python3.7/dist-packages/ray/serialization.py in
_serialize_to_msgpack(self, value)
302 metadata = ray_constants.OBJECT_METADATA_TYPE_PYTHON
303 pickle5_serialized_object =
--> 304 self._serialize_to_pickle5(metadata, python_objects)
305 else:
306 pickle5_serialized_object = None
/usr/local/lib/python3.7/dist-packages/ray/serialization.py in
_serialize_to_pickle5(self, metadata, value)
262 except Exception as e:
263 self.get_and_clear_contained_object_refs()
--> 264 raise e
265 finally:
266 self.set_out_of_band_serialization()
/usr/local/lib/python3.7/dist-packages/ray/serialization.py in
_serialize_to_pickle5(self, metadata, value)
259 self.set_in_band_serialization()
260 inband = pickle.dumps(
--> 261 value, protocol=5, buffer_callback=writer.buffer_callback)
262 except Exception as e:
263 self.get_and_clear_contained_object_refs()
/usr/local/lib/python3.7/dist-packages/ray/cloudpickle/cloudpickle_fast.py
in dumps(obj, protocol, buffer_callback)
71 file, protocol=protocol, buffer_callback=buffer_callback
72 )
---> 73 cp.dump(obj)
74 return file.getvalue()
75
/usr/local/lib/python3.7/dist-packages/ray/cloudpickle/cloudpickle_fast.py
in dump(self, obj)
578 def dump(self, obj):
579 try:
--> 580 return Pickler.dump(self, obj)
581 except RuntimeError as e:
582 if "recursion" in e.args[0]:
/usr/local/lib/python3.7/dist-packages/pyarrow/io.pxi in
pyarrow.lib.Buffer.reduce_ex()
AttributeError: module 'pickle' has no attribute 'PickleBuffer'
My environment set-up:
Am using Google Colab
Platform: Linux-5.4.109+-x86_64-with-Ubuntu-18.04-bionic
Python version: 3.7.10
Transformers version: 4.6.1
ray version: 1.3.0
What I have tried:
Updating pickle
Installed and imported pickle5 as pickle
Made sure that I did not have a python file with the name of 'pickle' in my immediate directory
Where is this bug coming from and how can I resolve it?

I had the same error when trying to use pickle.dump(), for me it worked to downgrade pickle5 from version 0.0.11 to 0.0.10

I also encountered this error on Google Colab trying ray tune hyperparameter search with the huggingface transformers.
This helped me:
!pip install pickle5
Then
import pickle5 as pickle
After the first run there will be the pickle warning to restart the notebook and the same error. After the second “Restart and run all” the ray tune hyperparameter search begins.

Not a "real" solution but at least a workaround. For me this issue was occurring on Python 3.7. Switching to Python 3.8 solved the issue.

UnicodeDecodeError: 'utf-8' codec can't decode byte Error in script

import sys
sys.path.append('E:\MLDS\resparser')
​
from resume_parser import ResumeParser
​
data = ResumeParser(filename).get_extracted_data()
This thought the following output, which I am not able to understand what is causing it because the same script runs smoothly on a different computer with a similar version installation.
---------------------------------------------------------------------------
UnicodeDecodeError Traceback (most recent call last)
<ipython-input-52-d48f50eae8f2> in <module>
4 from resume_parser import ResumeParser
5
----> 6 data = ResumeParser(filename).get_extracted_data()
E:\MLDS\resparser\resume_parser.py in __init__(self, resume, skills_file, custom_regex)
13 def __init__(self, resume, skills_file=None, custom_regex=None):
14 nlp = spacy.load("en_core_web_sm")
---> 15 custom_nlp = spacy.load(os.path.dirname(os.path.abspath(__file__)))
16 self.__skills_file = skills_file
17 self.__custom_regex = custom_regex
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\__init__.py in load(name, **overrides)
28 if depr_path not in (True, False, None):
29 warnings.warn(Warnings.W001.format(path=depr_path), DeprecationWarning)
---> 30 return util.load_model(name, **overrides)
31
32
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\util.py in load_model(name, **overrides)
170 return load_model_from_package(name, **overrides)
171 if Path(name).exists(): # path to model data directory
--> 172 return load_model_from_path(Path(name), **overrides)
173 elif hasattr(name, "exists"): # Path or Path-like to model data
174 return load_model_from_path(name, **overrides)
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\util.py in load_model_from_path(model_path, meta, **overrides)
220 component = nlp.create_pipe(factory, config=config)
221 nlp.add_pipe(component, name=name)
--> 222 return nlp.from_disk(model_path, exclude=disable)
223
224
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\language.py in from_disk(self, path, exclude, disable)
972 # Convert to list here in case exclude is (default) tuple
973 exclude = list(exclude) + ["vocab"]
--> 974 util.from_disk(path, deserializers, exclude)
975 self._path = path
976 return self
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\util.py in from_disk(path, readers, exclude)
688 # Split to support file names like meta.json
689 if key.split(".")[0] not in exclude:
--> 690 reader(path / key)
691 return path
692
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\language.py in <lambda>(p)
958 deserializers["meta.json"] = deserialize_meta
959 deserializers["vocab"] = deserialize_vocab
--> 960 deserializers["tokenizer"] = lambda p: self.tokenizer.from_disk(
961 p, exclude=["vocab"]
962 )
tokenizer.pyx in spacy.tokenizer.Tokenizer.from_disk()
tokenizer.pyx in spacy.tokenizer.Tokenizer.from_bytes()
C:\Miniconda-38\envs\env3.8\lib\site-packages\spacy\util.py in from_bytes(bytes_data, setters, exclude)
664
665 def from_bytes(bytes_data, setters, exclude):
--> 666 msg = srsly.msgpack_loads(bytes_data)
667 for key, setter in setters.items():
668 # Split to support file names like meta.json
C:\Miniconda-38\envs\env3.8\lib\site-packages\srsly\_msgpack_api.py in msgpack_loads(data, use_list)
27 # msgpack-python docs suggest disabling gc before unpacking large messages
28 gc.disable()
---> 29 msg = msgpack.loads(data, raw=False, use_list=use_list)
30 gc.enable()
31 return msg
C:\Miniconda-38\envs\env3.8\lib\site-packages\srsly\msgpack\__init__.py in unpackb(packed, **kwargs)
58 object_hook = kwargs.get('object_hook')
59 kwargs['object_hook'] = functools.partial(_decode_numpy, chain=object_hook)
---> 60 return _unpackb(packed, **kwargs)
61
62
C:\Miniconda-38\envs\env3.8\lib\site-packages\srsly\msgpack\_unpacker.pyx in srsly.msgpack._unpacker.unpackb()
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xda in position 0: invalid continuation byte
I tried changing the spacy model to _lg but of no use, I did try the ''python -m spacy validate '' to validate the models and the output was following:
TYPE NAME MODEL VERSION
package en-core-web-sm en_core_web_sm 2.3.1 ✔
package en-core-web-lg en_core_web_lg 2.3.1 ✔
I will appreciate any help which could point me in the right direction.

pytorch RuntimeError: CUDA error: device-side assert triggered

I've a notebook on google colab that fails with following error
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
93 exception = e
---> 94 raise e
95 finally: cb_handler.on_train_end(exception)
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
83 xb, yb = cb_handler.on_batch_begin(xb, yb)
---> 84 loss = loss_batch(model, xb, yb, loss_func, opt, cb_handler)
85 if cb_handler.on_batch_end(loss): break
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in loss_batch(model, xb, yb, loss_func, opt, cb_handler)
24 if opt is not None:
---> 25 loss = cb_handler.on_backward_begin(loss)
26 loss.backward()
/usr/local/lib/python3.6/dist-packages/fastai/callback.py in on_backward_begin(self, loss)
223 for cb in self.callbacks:
--> 224 a = cb.on_backward_begin(**self.state_dict)
225 if a is not None: self.state_dict['last_loss'] = a
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in on_backward_begin(self, smooth_loss, **kwargs)
266 if self.pbar is not None and hasattr(self.pbar,'child'):
--> 267 self.pbar.child.comment = f'{smooth_loss:.4f}'
268
/usr/local/lib/python3.6/dist-packages/torch/tensor.py in __format__(self, format_spec)
377 if self.dim() == 0:
--> 378 return self.item().__format__(format_spec)
379 return object.__format__(self, format_spec)
RuntimeError: CUDA error: device-side assert triggered
During handling of the above exception, another exception occurred:
RuntimeError Traceback (most recent call last)
<ipython-input-33-dd390b1c8108> in <module>()
----> 1 lr_find(learn)
2 learn.recorder.plot()
/usr/local/lib/python3.6/dist-packages/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, **kwargs)
26 cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div)
27 a = int(np.ceil(num_it/len(learn.data.train_dl)))
---> 28 learn.fit(a, start_lr, callbacks=[cb], **kwargs)
29
30 def to_fp16(learn:Learner, loss_scale:float=512., flat_master:bool=False)->Learner:
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks)
160 callbacks = [cb(self) for cb in self.callback_fns] + listify(callbacks)
161 fit(epochs, self.model, self.loss_func, opt=self.opt, data=self.data, metrics=self.metrics,
--> 162 callbacks=self.callbacks+callbacks)
163
164 def create_opt(self, lr:Floats, wd:Floats=0.)->None:
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in fit(epochs, model, loss_func, opt, data, callbacks, metrics)
93 exception = e
94 raise e
---> 95 finally: cb_handler.on_train_end(exception)
96
97 loss_func_name2activ = {'cross_entropy_loss': partial(F.softmax, dim=1), 'nll_loss': torch.exp, 'poisson_nll_loss': torch.exp,
/usr/local/lib/python3.6/dist-packages/fastai/callback.py in on_train_end(self, exception)
254 def on_train_end(self, exception:Union[bool,Exception])->None:
255 "Handle end of training, `exception` is an `Exception` or False if no exceptions during training."
--> 256 self('train_end', exception=exception)
257
258 class AverageMetric(Callback):
/usr/local/lib/python3.6/dist-packages/fastai/callback.py in __call__(self, cb_name, call_mets, **kwargs)
185 "Call through to all of the `CallbakHandler` functions."
186 if call_mets: [getattr(met, f'on_{cb_name}')(**self.state_dict, **kwargs) for met in self.metrics]
--> 187 return [getattr(cb, f'on_{cb_name}')(**self.state_dict, **kwargs) for cb in self.callbacks]
188
189 def on_train_begin(self, epochs:int, pbar:PBar, metrics:MetricFuncList)->None:
/usr/local/lib/python3.6/dist-packages/fastai/callback.py in <listcomp>(.0)
185 "Call through to all of the `CallbakHandler` functions."
186 if call_mets: [getattr(met, f'on_{cb_name}')(**self.state_dict, **kwargs) for met in self.metrics]
--> 187 return [getattr(cb, f'on_{cb_name}')(**self.state_dict, **kwargs) for cb in self.callbacks]
188
189 def on_train_begin(self, epochs:int, pbar:PBar, metrics:MetricFuncList)->None:
/usr/local/lib/python3.6/dist-packages/fastai/callbacks/lr_finder.py in on_train_end(self, **kwargs)
45 # restore the valid_dl we turned of on `__init__`
46 self.data.valid_dl = self.valid_dl
---> 47 self.learn.load('tmp')
48 if hasattr(self.learn.model, 'reset'): self.learn.model.reset()
49 print('LR Finder complete, type {learner_name}.recorder.plot() to see the graph.')
/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py in load(self, name, device)
202 "Load model `name` from `self.model_dir` using `device`, defaulting to `self.data.device`."
203 if device is None: device = self.data.device
--> 204 self.model.load_state_dict(torch.load(self.path/self.model_dir/f'{name}.pth', map_location=device))
205 return self
206
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in load(f, map_location, pickle_module)
356 f = open(f, 'rb')
357 try:
--> 358 return _load(f, map_location, pickle_module)
359 finally:
360 if new_fd:
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in _load(f, map_location, pickle_module)
527 unpickler = pickle_module.Unpickler(f)
528 unpickler.persistent_load = persistent_load
--> 529 result = unpickler.load()
530
531 deserialized_storage_keys = pickle_module.load(f)
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in persistent_load(saved_id)
493 if root_key not in deserialized_objects:
494 deserialized_objects[root_key] = restore_location(
--> 495 data_type(size), location)
496 storage = deserialized_objects[root_key]
497 if view_metadata is not None:
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in restore_location(storage, location)
376 elif isinstance(map_location, torch.device):
377 def restore_location(storage, location):
--> 378 return default_restore_location(storage, str(map_location))
379 else:
380 def restore_location(storage, location):
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in default_restore_location(storage, location)
102 def default_restore_location(storage, location):
103 for _, _, fn in _package_registry:
--> 104 result = fn(storage, location)
105 if result is not None:
106 return result
/usr/local/lib/python3.6/dist-packages/torch/serialization.py in _cuda_deserialize(obj, location)
84 'to an existing device.'.format(
85 device, torch.cuda.device_count()))
---> 86 return obj.cuda(device)
87
88
/usr/local/lib/python3.6/dist-packages/torch/_utils.py in _cuda(self, device, non_blocking, **kwargs)
74 else:
75 new_type = getattr(torch.cuda, self.__class__.__name__)
---> 76 return new_type(self.size()).copy_(self, non_blocking)
77
78
RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorCopy.cpp:20
There is no information about the real cause, I tried to get the stack trace by forcing cuda to run on one gpu (as suggested here) using a cell like this
!export CUDA_LAUNCH_BLOCKING=1
But this does not seem to work, still having the same error with.
Is there another way that works with Google Colab?

Be sure that your targets values starts from zero to number of classes - 1. Ex: you have 100 classification class so your target should be from 0 to 99

!export FOO=blah is usually not useful to run in a notebook because ! means run the following command in a sub-shell, so the effect of the statement is gone by the time the ! returns.
You might have more success by storing your python code in a file and then executing that file in a subshell:
In one cell:
%%writefile foo.py
[...your code...]
In the next cell:
!export CUDA_LAUNCH_BLOCKING=1; python3 foo.py
(or s/python3/python2/ if you're writing py2)

Switch Hardware Accelerator Type to "None" under Runtime->Change Runtime Type . This should give you a more meaningful error message.

The proper way to set environmental variables in Google Colab is to use os:
import os
os.environ['CUDA_LAUNCH_BLOCKING'] = "1"
Using the os library will allow you to set whatever environmental variables you need. Setting CUDA_LAUNCH_BLOCKING this way enables proper CUDA tracebacks in Google Colab.

Unable to load spacy English model - 'WindowsPath' object has no attribute 'read'

I installed spacy using pip and then downloaded the English model using
$ python -m spacy download en
which after downloading gave me the message
You can now load the model via spacy.load('en')
Using IPython,
import spacy
nlp=spacy.load('en')
AttributeError Traceback (most recent call last)
<ipython-input-5-a32b6d2b36d8> in <module>()
----> 1 nlp=spacy.load('en')
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\__init__.pyc in load(n
ame, **overrides)
13 from .deprecated import resolve_load_name
14 name = resolve_load_name(name, **overrides)
---> 15 return util.load_model(name, **overrides)
16
17
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in load_model
(name, **overrides)
102 if isinstance(name, basestring_):
103 if name in set([d.name for d in data_path.iterdir()]): # in data
dir / shortcut
--> 104 return load_model_from_link(name, **overrides)
105 if is_package(name): # installed as package
106 return load_model_from_package(name, **overrides)
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in load_model
_from_link(name, **overrides)
121 "Cant' load '%s'. If you're using a shortcut link, make sure
it "
122 "points to a valid model package (not just a data directory)
." % name)
--> 123 return cls.load(**overrides)
124
125
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\data\en\__init__.pyc i
n load(**overrides)
10
11 def load(**overrides):
---> 12 return load_model_from_init_py(__file__, **overrides)
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in load_model
_from_init_py(init_file, **overrides)
165 if not model_path.exists():
166 raise ValueError("Can't find model directory: %s" % path2str(dat
a_path))
--> 167 return load_model_from_path(data_path, meta, **overrides)
168
169
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in load_model
_from_path(model_path, meta, **overrides)
148 component = nlp.create_pipe(name, config=config)
149 nlp.add_pipe(component, name=name)
--> 150 return nlp.from_disk(model_path)
151
152
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\language.pyc in from_d
isk(self, path, disable)
571 if not (path / 'vocab').exists():
572 exclude['vocab'] = True
--> 573 util.from_disk(path, deserializers, exclude)
574 return self
575
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in from_disk(
path, readers, exclude)
495 for key, reader in readers.items():
496 if key not in exclude:
--> 497 reader(path / key)
498 return path
499
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\language.pyc in <lambd
a>(p)
558 path = util.ensure_path(path)
559 deserializers = OrderedDict((
--> 560 ('vocab', lambda p: self.vocab.from_disk(p)),
561 ('tokenizer', lambda p: self.tokenizer.from_disk(p, vocab=Fa
lse)),
562 ('meta.json', lambda p: p.open('w').write(json_dumps(self.me
ta)))
vocab.pyx in spacy.vocab.Vocab.from_disk()
vectors.pyx in spacy.vectors.Vectors.from_disk()
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\spacy\util.pyc in from_disk(
path, readers, exclude)
495 for key, reader in readers.items():
496 if key not in exclude:
--> 497 reader(path / key)
498 return path
499
vectors.pyx in spacy.vectors.Vectors.from_disk.load_keys()
C:\Users\PARVATHY SARAT\Anaconda2\lib\site-packages\numpy\lib\npyio.pyc in load(
file, mmap_mode, allow_pickle, fix_imports, encoding)
389 _ZIP_PREFIX = asbytes('PK\x03\x04')
390 N = len(format.MAGIC_PREFIX)
--> 391 magic = fid.read(N)
392 fid.seek(-N, 1) # back-up
393 if magic.startswith(_ZIP_PREFIX):
AttributeError: 'WindowsPath' object has no attribute 'read'
I have the English model files(en_core_web_sm) downloaded to the working directory, am I missing something? Do I need to set a path variable? Any help is much appreciated, thanks!

If anybody else receives this error : I opened this as an issue with spaCy's developers on Github. I was suggested using Python 3.6 instead of 2.7 for the moment as there is no alternate workaround to the problem. The next spaCy version should cover this bugfix (I'm told).

Yes, there is glitch involving language downloads in anaconda environments. Here is the pending pull request
https://github.com/explosion/spaCy/pull/1792