Skip to content

fix tutorial_mnist_simple.py #1130

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 25, 2021
Merged

fix tutorial_mnist_simple.py #1130

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 12 additions & 16 deletions examples/basic_tutorials/tutorial_mnist_simple.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@

# The same set of code can switch the backend with one line
import os
# os.environ['TL_BACKEND'] = 'tensorflow'
os.environ['TL_BACKEND'] = 'tensorflow'
# os.environ['TL_BACKEND'] = 'mindspore'
os.environ['TL_BACKEND'] = 'paddle'
# os.environ['TL_BACKEND'] = 'paddle'
import numpy as np
import tensorlayer as tl
from tensorlayer.layers import Module
Expand All @@ -15,12 +15,11 @@

X_train, y_train, X_val, y_val, X_test, y_test = tl.files.load_mnist_dataset(shape=(-1, 28, 28, 1))

transform = Compose([Normalize(mean=[127.5], std=[127.5], data_format='HWC')])

transform = Compose([Normalize(mean=[127.5/255.], std=[127.5/255.], data_format='HWC')])

class mnistdataset(Dataset):

def __init__(self, data, label, transform):
def __init__(self, data = X_train, label = y_train ,transform = transform):
self.data = data
self.label = label
self.transform = transform
Expand Down Expand Up @@ -61,24 +60,21 @@ def forward(self, x, foo=None):
out = tl.ops.relu(out)
return out


MLP = CustomModel()

n_epoch = 50
batch_size = 128
print_freq = 2

train_dataset = mnistdataset(data=X_train, label=y_train, transform=transform)
train_dataset = tl.dataflow.FromGenerator(
train_dataset, output_types=[tl.float32, tl.int64], column_names=['data', 'label']
)
train_loader = tl.dataflow.Dataloader(train_dataset, batch_size=batch_size, shuffle=True)

train_weights = MLP.trainable_weights
optimizer = tl.optimizers.Momentum(0.05, 0.9)
optimizer = tl.optimizers.Momentum(0.001, 0.9)
metric = tl.metric.Accuracy()
model = tl.models.Model(
network=MLP, loss_fn=tl.cost.softmax_cross_entropy_with_logits, optimizer=optimizer, metrics=metric
)
train_dataset = mnistdataset(data = X_train, label = y_train ,transform = transform)
train_dataset = tl.dataflow.FromGenerator(train_dataset, output_types=[tl.float32, tl.int64], column_names=['data', 'label'])
train_loader = tl.dataflow.Dataloader(train_dataset, batch_size=batch_size, shuffle=True)

model = tl.models.Model(network=MLP, loss_fn=tl.cost.softmax_cross_entropy_with_logits, optimizer=optimizer, metrics=metric)
model.train(n_epoch=n_epoch, train_dataset=train_loader, print_freq=print_freq, print_train_batch=False)
model.save_weights('./model.npz', format='npz_dict')
model.load_weights('./model.npz', format='npz_dict')
model.load_weights('./model.npz', format='npz_dict')