I am having a similar problem on this link: Parallel error with GridSearchCV, works fine with other methods
I tried both of the solutions and neither one worked for me, as well.
When n_jobs = -1 in a grid search I get an error although n_jobs = -1 works fine for single models.
I tried updating sklearn but it did not help.
Here is the code I am trying:
rf = RandomForestClassifier()
rf_random = RandomizedSearchCV(estimator=rf,
param_distributions = random_grid,
n_iter = 100, cv = 3, verbose = 2, random_state = 42,
n_jobs = -1)
rf_random.fit(X_train, y_train)
I am getting this error:
ModuleNotFoundError: No module named
'sklearn.externals.joblib.externals.loky.backend.popen_loky_win32'
Tried the solution on the link but got the same error:
def randomsearcher():
clf = ensemble.RandomForestClassifier()
param_grid = random_grid
grid_s= model_selection.GridSearchCV(clf, cv=5, param_grid=param_grid
,n_jobs=-1,verbose=1)
grid_s.fit(X_train,y_train)
return grid_s
if __name__ == '__main__':
randomsearcher()
No problem with this code:
knn = KNeighborsClassifier(n_neighbors=50,
weights='distance',algorithm='auto',n_jobs = -1 )
I am working on a VM that has 8 virtual processors on 2 sockets.
Related
I've created a program that is supposed to take the question and entry from a user and copy it to the clipboard. It works fine as a regular program but when I try to adapt it in trying to adapt it to a GUI I am running into an issue. Currently the program is only copying the question and the entries are returning empty strings. I know that if a broke down each entry into its own named variable I could probably fix this issue but a loop seems like a much cleaner solution. Can anyone assist?
import tkinter as tk
from tkinter import *
import pyperclip
system = 'What is the system?'
product = 'What is the product?'
issue = 'What is the issue?'
error = 'Is there an error message?'
screenshot = 'Do you have a screenshot or documentation for this issue?'
impact = 'Is the floor impacted. If so, what is the impact?'
users = 'How many users is this affecting?'
troubleshooting = 'Was there troubleshooting performed?'
changes = 'Are you aware of any changes that may have led up to the issue?'
ticket = 'Do you have an internal ticket number?'
questions = (
system, product, issue, error,
screenshot, impact, users, troubleshooting,
changes, ticket)
entries = []
clip = []
index = 0
index=0
c=0
r=0
root = tk.Tk()
root.title('SysIt4')
top_frame=tk.Frame(root)
bottom_frame=tk.Frame(root)
top_frame.grid(column=0, row=0, sticky=W)
bottom_frame.grid(column=0, row=1)
canvas = tk.Canvas(root, width=600, height=800)
canvas.grid()
while index < 10:
label = tk.Label(top_frame, text=questions[index])
label.grid(columnspan=2, column=c, row=r, sticky=W)
r+=2
index += 1
for r in range(1,20,2):
entry = tk.Entry(top_frame, width=50)
entry.grid(columnspan=2, column=c, row=r, sticky=W, padx=10, pady=5)
entries.append(entry)
def enact_clip(entries, questions):
responses = []
outfile= open('copy.txt', 'w')
for entry in entries:
responses.append(entry.get())
clip = list(zip(questions, responses))
for line in clip:
outfile.write(str(line) + '\n')
outfile.close()
infile = open('copy.txt', 'r')
copy_contents = infile.read()
return pyperclip.copy(copy_contents)
infile.close()
clip_button = Button(bottom_frame, text='Clip', command= enact_clip(entries, questions))
clip_button.grid(column=0, row=1)
root.mainloop()
Doing things on Google Colab.
transformers: 4.10.2
pytorch-lightning: 1.2.7
import torch
from torch.utils.data import DataLoader
from transformers import BertJapaneseTokenizer, BertForSequenceClassification
import pytorch_lightning as pl
dataset_for_loader = [
{'data':torch.tensor([0,1]), 'labels':torch.tensor(0)},
{'data':torch.tensor([2,3]), 'labels':torch.tensor(1)},
{'data':torch.tensor([4,5]), 'labels':torch.tensor(2)},
{'data':torch.tensor([6,7]), 'labels':torch.tensor(3)},
]
loader = DataLoader(dataset_for_loader, batch_size=2)
for idx, batch in enumerate(loader):
print(f'# batch {idx}')
print(batch)
category_list = [
'dokujo-tsushin',
'it-life-hack',
'kaden-channel',
'livedoor-homme',
'movie-enter',
'peachy',
'smax',
'sports-watch',
'topic-news'
]
tokenizer = BertJapaneseTokenizer.from_pretrained(MODEL_NAME)
max_length = 128
dataset_for_loader = []
for label, category in enumerate(tqdm(category_list)):
# file ./text has lots of articles, categorized by category
# and they are just plain texts, whose content begins from forth line
for file in glob.glob(f'./text/{category}/{category}*'):
lines = open(file).read().splitlines()
text = '\n'.join(lines[3:])
encoding = tokenizer(
text,
max_length=max_length,
padding='max_length',
truncation=True
)
encoding['labels'] = label
encoding = { k: torch.tensor(v) for k, v in encoding.items() }
dataset_for_loader.append(encoding)
SEED=lambda:0.0
# random.shuffle(dataset_for_loader) # ランダムにシャッフル
random.shuffle(dataset_for_loader,SEED)
n = len(dataset_for_loader)
n_train = int(0.6*n)
n_val = int(0.2*n)
dataset_train = dataset_for_loader[:n_train]
dataset_val = dataset_for_loader[n_train:n_train+n_val]
dataset_test = dataset_for_loader[n_train+n_val:]
dataloader_train = DataLoader(
dataset_train, batch_size=32, shuffle=True
)
dataloader_val = DataLoader(dataset_val, batch_size=256)
dataloader_test = DataLoader(dataset_test, batch_size=256)
class BertForSequenceClassification_pl(pl.LightningModule):
def __init__(self, model_name, num_labels, lr):
super().__init__()
self.save_hyperparameters()
self.bert_sc = BertForSequenceClassification.from_pretrained(
model_name,
num_labels=num_labels
)
def training_step(self, batch, batch_idx):
output = self.bert_sc(**batch)
loss = output.loss
self.log('train_loss', loss)
return loss
def validation_step(self, batch, batch_idx):
output = self.bert_sc(**batch)
val_loss = output.loss
self.log('val_loss', val_loss)
def test_step(self, batch, batch_idx):
labels = batch.pop('labels')
output = self.bert_sc(**batch)
labels_predicted = output.logits.argmax(-1)
num_correct = ( labels_predicted == labels ).sum().item()
accuracy = num_correct/labels.size(0)
self.log('accuracy', accuracy)
def configure_optimizers(self):
return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
checkpoint = pl.callbacks.ModelCheckpoint(
monitor='val_loss',
mode='min',
save_top_k=1,
save_weights_only=True,
dirpath='model/',
)
trainer = pl.Trainer(
gpus=1,
max_epochs=10,
callbacks = [checkpoint]
)
model = BertForSequenceClassification_pl(
MODEL_NAME, num_labels=9, lr=1e-5
)
### (a) ###
# I think this is where I am doing fine-tuning
trainer.fit(model, dataloader_train, dataloader_val)
# this is to score after fine-tuning
test = trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
But I am not really sure how to do a test before fine-tuning, in order to compare two models before and after fine-tuning, in order to show how effective fine-tuning is.
Inserting the following two lines to ### (a) ###:
test = trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
I got this result:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-13-c8b2c67f2d5c> in <module>()
9
10 # 6-19
---> 11 test = trainer.test(test_dataloaders=dataloader_test)
12 print(f'Accuracy: {test[0]["accuracy"]:.2f}')
13
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py in test(self, model, test_dataloaders, ckpt_path, verbose, datamodule)
896 self.verbose_test = verbose
897
--> 898 self._set_running_stage(RunningStage.TESTING, model or self.lightning_module)
899
900 # If you supply a datamodule you can't supply train_dataloader or val_dataloaders
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py in _set_running_stage(self, stage, model_ref)
563 the trainer and the model
564 """
--> 565 model_ref.running_stage = stage
566 self._running_stage = stage
567
AttributeError: 'NoneType' object has no attribute 'running_stage'
I noticed that Trainer.fit() can take None as arguments other than model, so I tried this:
trainer.fit(model)
test=trainer.test(test_dataloaders=dataloader_test)
print(f'Accuracy: {test[0]["accuracy"]:.2f}')
The result:
MisconfigurationException: No `train_dataloader()` method defined. Lightning `Trainer` expects as minimum a `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined.
Thanks.
The Trainer needs to call its .fit() in order to set up a lot of things and then only you can do .test() or other methods.
You are right about putting a .fit() just before .test() but the fit call needs to a valid one. You have to feed a dataloader/datamodule to it. But since you don't want to do a training/validation in this fit call, just pass limit_[train/val]_batches=0 while Trainer construction.
trainer = Trainer(gpus=..., ..., limit_train_batches=0, limit_val_batches=0)
trainer.fit(model, dataloader_train, dataloader_val)
trainer.test(model, dataloader_test) # without fine-tuning
The fit call here will just set things up for you and skip training/validation. And then the testing follows. Next time run the same code but without the limit_[train/val]_batches, this will do the pretraining for you
trainer = Trainer(gpus=..., ...)
trainer.fit(model, dataloader_train, dataloader_val)
trainer.test(model, dataloader_test) # with fine-tuning
Clarifying a bit about .fit() taking None for all but model: Its not quite true - you must provide either a DataLoader or a DataModule.
Tensorflow: 2.4.0
This is the Full Error Message:
ValueError: Graph disconnected: cannot obtain value for tensor KerasTensor(type_spec=TensorSpec(shape=(None, 64, 64, 3), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'input_1'") at layer "flatten". The following previous layers were accessed without issue: []
I have been trying to make a controllable Autoencoder where I have 10 features I can variy to get an image (64x64 RGB)
And i have been having Trouble getting it working. I want to seperate the Neural Network into a full model which i can fit and an Decoder which i can use to later after training parse values into to generate images
btw i know this is not the perfect way to do an autoencoder it's just the simplest i can think of.
def Create_Generator(Image_Shape):
Input_Layer = Input(shape=Image_Shape)
Flatten_Layer1 = Flatten()(Input_Layer)
Dense_Layer1 = Dense(12288,activation="relu")(Flatten_Layer1)
Dense_Layer2 = Dense(6144,activation="relu")(Dense_Layer1)
Dense_Layer3 = Dense(1024, activation="relu")(Dense_Layer2)
Dense_Layer4 = Dense(10,activation="relu")(Dense_Layer3)
Dense_Layer5 = Dense(1024, activation="relu")(Dense_Layer4)
Dense_Layer6 = Dense(6144,activation="relu")(Dense_Layer5)
Dense_Layer7 = Dense(12288,activation="relu")(Dense_Layer6)
Reshape_Layer = Reshape(Image_Shape)(Dense_Layer7)
AutoEncoder = Model(Input_Layer,Reshape_Layer)
AutoEncoder.compile(optimizer='adam', loss ='binary_crossentropy')
encoded_input = Input(shape=(10,))
Decoder = Model([encoded_input,Dense_Layer5,Dense_Layer6,Dense_Layer7],Reshape_Layer)
return AutoEncoder,Decoder
data = np.load("data.npz")
X_train = data['X']
AutoEncoder,Decoder = Create_Generator((64,64,3))
#Just for testing if it works
print(AutoEncoder.predict([X_train[0]]))
print(Decoder([[1,1,1,1,1,1,1,1,1,1]]))
I think you have an error here:
Decoder = Model([encoded_input,Dense_Layer5,Dense_Layer6,Dense_Layer7],Reshape_Layer)
Dense_Layer5, Dense_Layer6, Dense_Layer7 are not tf.keras.layers.Input. You can not create Decoder this way.
I am working on a deep learning problem. I am solving it using pytorch. I have two GPU's which are on the same machine (16273MiB,12193MiB). I want to use both the GPU's for my training (video dataset).
I get a warning:
There is an imbalance between your GPUs. You may want to exclude GPU 1 which
has less than 75% of the memory or cores of GPU 0. You can do so by setting
the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
environment variable.
warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
I also get an error:
raise TypeError('Broadcast function not implemented for CPU tensors')
TypeError: Broadcast function not implemented for CPU tensors
if __name__ == '__main__':
opt.scales = [opt.initial_scale]
for i in range(1, opt.n_scales):
opt.scales.append(opt.scales[-1] * opt.scale_step)
opt.arch = '{}-{}'.format(opt.model, opt.model_depth)
opt.mean = get_mean(opt.norm_value)
opt.std = get_std(opt.norm_value)
print("opt",opt)
with open(os.path.join(opt.result_path, 'opts.json'), 'w') as opt_file:
json.dump(vars(opt), opt_file)
torch.manual_seed(opt.manual_seed)
model, parameters = generate_model(opt)
#print(model)
pytorch_total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
print("Total number of trainable parameters: ", pytorch_total_params)
# Define Class weights
if opt.weighted:
print("Weighted Loss is created")
if opt.n_finetune_classes == 2:
weight = torch.tensor([1.0, 3.0])
else:
weight = torch.ones(opt.n_finetune_classes)
else:
weight = None
criterion = nn.CrossEntropyLoss()
if not opt.no_cuda:
criterion = nn.DataParallel(criterion.cuda())
if opt.no_mean_norm and not opt.std_norm:
norm_method = Normalize([0, 0, 0], [1, 1, 1])
elif not opt.std_norm:
norm_method = Normalize(opt.mean, [1, 1, 1])
else:
norm_method = Normalize(opt.mean, opt.std)
train_loader = torch.utils.data.DataLoader(
training_data,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.n_threads,
pin_memory=True)
train_logger = Logger(
os.path.join(opt.result_path, 'train.log'),
['epoch', 'loss', 'acc', 'precision','recall','lr'])
train_batch_logger = Logger(
os.path.join(opt.result_path, 'train_batch.log'),
['epoch', 'batch', 'iter', 'loss', 'acc', 'precision', 'recall', 'lr'])
if opt.nesterov:
dampening = 0
else:
dampening = opt.dampening
optimizer = optim.SGD(
parameters,
lr=opt.learning_rate,
momentum=opt.momentum,
dampening=dampening,
weight_decay=opt.weight_decay,
nesterov=opt.nesterov)
# scheduler = lr_scheduler.ReduceLROnPlateau(
# optimizer, 'min', patience=opt.lr_patience)
if not opt.no_val:
spatial_transform = Compose([
Scale(opt.sample_size),
CenterCrop(opt.sample_size),
ToTensor(opt.norm_value), norm_method
])
print('run')
for i in range(opt.begin_epoch, opt.n_epochs + 1):
if not opt.no_train:
adjust_learning_rate(optimizer, i, opt.lr_steps)
train_epoch(i, train_loader, model, criterion, optimizer, opt,
train_logger, train_batch_logger)
I have also made changes in my train file:
model = nn.DataParallel(model(),device_ids=[0,1]).cuda()
outputs = model(inputs)
It does not seem to work properly and is giving error. Please advice, I am new to pytorch.
Thanks
As mentioned in this link, you have to do model.cuda() before passing it to nn.DataParallel.
net = nn.DataParallel(model.cuda(), device_ids=[0,1])
https://github.com/pytorch/pytorch/issues/17065
I come here because I have an issue with my Jupiter's Python3 notebook.
I need to create a function that uses the multiprocessing library.
Before to implement it, I make some tests.
I found a looooot of different examples but the issue is everytime the same : my code is executed but nothing happens in the notebook's interface :
The code i try to run on jupyter is this one :
import os
from multiprocessing import Process, current_process
def doubler(number):
"""
A doubling function that can be used by a process
"""
result = number * 2
proc_name = current_process().name
print('{0} doubled to {1} by: {2}'.format(
number, result, proc_name))
return result
if __name__ == '__main__':
numbers = [5, 10, 15, 20, 25]
procs = []
proc = Process(target=doubler, args=(5,))
for index, number in enumerate(numbers):
proc = Process(target=doubler, args=(number,))
proc2 = Process(target=doubler, args=(number,))
procs.append(proc)
procs.append(proc2)
proc.start()
proc2.start()
proc = Process(target=doubler, name='Test', args=(2,))
proc.start()
procs.append(proc)
for proc in procs:
proc.join()
It's OK when I just run my code without Jupyter but with the command "python my_progrem.py" and I can see the logs :
Is there, for my example, and in Jupyter, a way to catch the results of my two tasks (proc1 and proc2 which both call thefunction "doubler") in a variable/object that I could use after ?
If "yes", how can I do it?
#Konate's answer really helped me. Here is a simplified version using multiprocessing.pool:
import multiprocessing
def double(a):
return a * 2
def driver_func():
PROCESSES = 4
with multiprocessing.Pool(PROCESSES) as pool:
params = [(1, ), (2, ), (3, ), (4, )]
results = [pool.apply_async(double, p) for p in params]
for r in results:
print('\t', r.get())
driver_func()
I succeed by using multiprocessing.pool.
I was inspired by this approach :
def test():
PROCESSES = 4
print('Creating pool with %d processes\n' % PROCESSES)
with multiprocessing.Pool(PROCESSES) as pool:
TASKS = [(mul, (i, 7)) for i in range(10)] + \
[(plus, (i, 8)) for i in range(10)]
results = [pool.apply_async(calculate, t) for t in TASKS]
imap_it = pool.imap(calculatestar, TASKS)
imap_unordered_it = pool.imap_unordered(calculatestar, TASKS)
print('Ordered results using pool.apply_async():')
for r in results:
print('\t', r.get())
print()
print('Ordered results using pool.imap():')
for x in imap_it:
print('\t', x)
...etc
For more, the code is at : https://docs.python.org/3.4/library/multiprocessing.html?
Another way of running multiprocessing jobs in a Jupyter notebook is to use one of the approaches supported by the nbmultitask package.
This works for me on MAC (cannot make it work on windows):
import multiprocessing as mp
mp_start_count = 0
if __name__ == '__main__':
if mp_start_count == 0:
mp.set_start_method('fork')
mp_start_count += 1