This page contains various exercises of image classification task with famous MNIST dataset.
from fastai.vision import *
from fastai.callbacks import *
Data preparation¶
mnist = untar_data(URLs.MNIST_TINY)
!tree -d $mnist
/home/condor/.fastai/data/mnist_tiny ├── models ├── test ├── train │ ├── 3 │ └── 7 └── valid ├── 3 └── 7 8 directories
Use data augmentation, but not flipping:
tfms = get_transforms(do_flip=False)
data = (ImageList.from_folder(mnist) #,convert_mode='L')
.split_by_rand_pct(0.2)
.label_from_folder()
# .add_test_folder(mnist/'testing')
.transform(tfms)
.databunch(bs=128)
.normalize(imagenet_stats))
data
ImageDataBunch; Train: LabelList (1143 items) x: ImageList Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28) y: CategoryList 7,7,7,7,7 Path: /home/condor/.fastai/data/mnist_tiny; Valid: LabelList (285 items) x: ImageList Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28) y: CategoryList 3,3,7,3,7 Path: /home/condor/.fastai/data/mnist_tiny; Test: None
data.show_batch(4,figsize=(5,5))
Model 1¶
learner = cnn_learner(data, models.resnet18, metrics=[accuracy], callbacks=[SaveModelCallback(learner, every='epoch', monitor='accuracy')])
learner
Learner(data=ImageDataBunch;
Train: LabelList (1143 items)
x: ImageList
Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)
y: CategoryList
7,7,7,7,7
Path: /home/condor/.fastai/data/mnist_tiny;
Valid: LabelList (285 items)
x: ImageList
Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)
y: CategoryList
3,3,7,3,7
Path: /home/condor/.fastai/data/mnist_tiny;
Test: None, model=Sequential(
(0): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(1): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.25, inplace=False)
(4): Linear(in_features=1024, out_features=512, bias=True)
(5): ReLU(inplace=True)
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.5, inplace=False)
(8): Linear(in_features=512, out_features=3, bias=True)
)
), opt_func=functools.partial(<class 'torch.optim.adam.Adam'>, betas=(0.9, 0.99)), loss_func=FlattenedLoss of CrossEntropyLoss(), metrics=[<function accuracy at 0x7fea5b721158>], true_wd=True, bn_wd=True, wd=0.01, train_bn=True, path=PosixPath('/home/condor/.fastai/data/mnist_tiny'), model_dir='models', callback_fns=[functools.partial(<class 'fastai.basic_train.Recorder'>, add_time=True, silent=False)], callbacks=[SaveModelCallback
learn: Learner(data=ImageDataBunch;
Train: LabelList (1143 items)
x: ImageList
Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)
y: CategoryList
7,7,7,7,7
Path: /home/condor/.fastai/data/mnist_tiny;
Valid: LabelList (285 items)
x: ImageList
Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)
y: CategoryList
3,3,7,3,7
Path: /home/condor/.fastai/data/mnist_tiny;
Test: None, model=Sequential(
(0): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(1): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.25, inplace=False)
(4): Linear(in_features=1024, out_features=512, bias=True)
(5): ReLU(inplace=True)
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.5, inplace=False)
(8): Linear(in_features=512, out_features=3, bias=True)
)
), opt_func=functools.partial(<class 'torch.optim.adam.Adam'>, betas=(0.9, 0.99)), loss_func=FlattenedLoss of CrossEntropyLoss(), metrics=[<function accuracy at 0x7fea5b721158>], true_wd=True, bn_wd=True, wd=0.01, train_bn=True, path=PosixPath('/home/condor/.fastai/data/mnist_tiny'), model_dir='models', callback_fns=[functools.partial(<class 'fastai.basic_train.Recorder'>, add_time=True, silent=False)], callbacks=[<class 'fastai.train.ShowGraph'>], layer_groups=[Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(5): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(6): ReLU(inplace=True)
(7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
(12): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(15): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(16): ReLU(inplace=True)
(17): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(18): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(20): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(22): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(23): ReLU(inplace=True)
(24): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(25): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): ReLU(inplace=True)
(10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(11): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(12): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(13): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): ReLU(inplace=True)
(15): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(16): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(17): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(18): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(20): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): ReLU(inplace=True)
(22): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(23): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): AdaptiveAvgPool2d(output_size=1)
(1): AdaptiveMaxPool2d(output_size=1)
(2): Flatten()
(3): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(4): Dropout(p=0.25, inplace=False)
(5): Linear(in_features=1024, out_features=512, bias=True)
(6): ReLU(inplace=True)
(7): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(8): Dropout(p=0.5, inplace=False)
(9): Linear(in_features=512, out_features=3, bias=True)
)], add_time=True, silent=False)
monitor: accuracy
mode: auto
every: epoch
name: bestmodel], layer_groups=[Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(5): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(6): ReLU(inplace=True)
(7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
(12): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(15): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(16): ReLU(inplace=True)
(17): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(18): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(20): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(22): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(23): ReLU(inplace=True)
(24): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(25): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): ReLU(inplace=True)
(10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(11): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(12): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(13): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): ReLU(inplace=True)
(15): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(16): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(17): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(18): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(20): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): ReLU(inplace=True)
(22): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(23): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): AdaptiveAvgPool2d(output_size=1)
(1): AdaptiveMaxPool2d(output_size=1)
(2): Flatten()
(3): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(4): Dropout(p=0.25, inplace=False)
(5): Linear(in_features=1024, out_features=512, bias=True)
(6): ReLU(inplace=True)
(7): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(8): Dropout(p=0.5, inplace=False)
(9): Linear(in_features=512, out_features=3, bias=True)
)], add_time=True, silent=False)
learner.lr_find()
46.15% [6/13 02:19<02:42]
| epoch | train_loss | valid_loss | accuracy | time |
|---|---|---|---|---|
| 0 | 1.966129 | #na# | 00:21 | |
| 1 | 1.892043 | #na# | 00:23 | |
| 2 | 1.866067 | #na# | 00:23 | |
| 3 | 1.857823 | #na# | 00:23 | |
| 4 | 1.802631 | #na# | 00:23 | |
| 5 | 1.724750 | #na# | 00:23 |
100.00% [8/8 00:22<00:00 1.5384]
LR Finder is complete, type {learner_name}.recorder.plot() to see the graph.
--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-16-f01cf5c6afa7> in <module> ----> 1 learner.lr_find() ~/fastai/fastai/train.py in lr_find(learn, start_lr, end_lr, num_it, stop_div, wd) 39 cb = LRFinder(learn, start_lr, end_lr, num_it, stop_div) 40 epochs = int(np.ceil(num_it/len(learn.data.train_dl))) ---> 41 learn.fit(epochs, start_lr, callbacks=[cb], wd=wd) 42 43 def to_fp16(learn:Learner, loss_scale:float=None, max_noskip:int=1000, dynamic:bool=True, clip:float=None, ~/fastai/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks) 198 else: self.opt.lr,self.opt.wd = lr,wd 199 callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks) --> 200 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks) 201 202 def create_opt(self, lr:Floats, wd:Floats=0.)->None: ~/fastai/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics) 106 cb_handler=cb_handler, pbar=pbar) 107 else: val_loss=None --> 108 if cb_handler.on_epoch_end(val_loss): break 109 except Exception as e: 110 exception = e ~/fastai/fastai/callback.py in on_epoch_end(self, val_loss) 315 "Epoch is done, process `val_loss`." 316 self.state_dict['last_metrics'] = [val_loss] if val_loss is not None else [None] --> 317 self('epoch_end', call_mets = val_loss is not None) 318 self.state_dict['epoch'] += 1 319 return self.state_dict['stop_training'] ~/fastai/fastai/callback.py in __call__(self, cb_name, call_mets, **kwargs) 249 if call_mets: 250 for met in self.metrics: self._call_and_update(met, cb_name, **kwargs) --> 251 for cb in self.callbacks: self._call_and_update(cb, cb_name, **kwargs) 252 253 def set_dl(self, dl:DataLoader): ~/fastai/fastai/callback.py in _call_and_update(self, cb, cb_name, **kwargs) 239 def _call_and_update(self, cb, cb_name, **kwargs)->None: 240 "Call `cb_name` on `cb` and update the inner state." --> 241 new = ifnone(getattr(cb, f'on_{cb_name}')(**self.state_dict, **kwargs), dict()) 242 for k,v in new.items(): 243 if k not in self.state_dict: ~/fastai/fastai/callbacks/tracker.py in on_epoch_end(self, epoch, **kwargs) 92 def on_epoch_end(self, epoch:int, **kwargs:Any)->None: 93 "Compare the value monitored to its best score and maybe save the model." ---> 94 if self.every=="epoch": self.learn.save(f'{self.name}_{epoch}') 95 else: #every="improvement" 96 current = self.get_monitor_value() AttributeError: 'NoneType' object has no attribute 'save'
learner.recorder.plot()
learner.fit_one_cycle(2, max_lr=2e-2)
--------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-12-aa29cbe08277> in <module> ----> 1 learner.fit_one_cycle(2, max_lr=2e-2) ~/fastai/fastai/train.py in fit_one_cycle(learn, cyc_len, max_lr, moms, div_factor, pct_start, final_div, wd, callbacks, tot_epochs, start_epoch) 21 callbacks.append(OneCycleScheduler(learn, max_lr, moms=moms, div_factor=div_factor, pct_start=pct_start, 22 final_div=final_div, tot_epochs=tot_epochs, start_epoch=start_epoch)) ---> 23 learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks) 24 25 def fit_fc(learn:Learner, tot_epochs:int=1, lr:float=defaults.lr, moms:Tuple[float,float]=(0.95,0.85), start_pct:float=0.72, ~/fastai/fastai/basic_train.py in fit(self, epochs, lr, wd, callbacks) 198 else: self.opt.lr,self.opt.wd = lr,wd 199 callbacks = [cb(self) for cb in self.callback_fns + listify(defaults.extra_callback_fns)] + listify(callbacks) --> 200 fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks) 201 202 def create_opt(self, lr:Floats, wd:Floats=0.)->None: ~/fastai/fastai/basic_train.py in fit(epochs, learn, callbacks, metrics) 89 cb_handler = CallbackHandler(callbacks, metrics) 90 pbar = master_bar(range(epochs)) ---> 91 cb_handler.on_train_begin(epochs, pbar=pbar, metrics=metrics) 92 93 exception=False ~/fastai/fastai/callback.py in on_train_begin(self, epochs, pbar, metrics) 263 self.state_dict.update(dict(n_epochs=epochs, pbar=pbar, metrics=metrics)) 264 names = [(met.name if hasattr(met, 'name') else camel2snake(met.__class__.__name__)) for met in self.metrics] --> 265 self('train_begin', metrics_names=names) 266 if self.state_dict['epoch'] != 0: 267 self.state_dict['pbar'].first_bar.total -= self.state_dict['epoch'] ~/fastai/fastai/callback.py in __call__(self, cb_name, call_mets, **kwargs) 249 if call_mets: 250 for met in self.metrics: self._call_and_update(met, cb_name, **kwargs) --> 251 for cb in self.callbacks: self._call_and_update(cb, cb_name, **kwargs) 252 253 def set_dl(self, dl:DataLoader): ~/fastai/fastai/callback.py in _call_and_update(self, cb, cb_name, **kwargs) 239 def _call_and_update(self, cb, cb_name, **kwargs)->None: 240 "Call `cb_name` on `cb` and update the inner state." --> 241 new = ifnone(getattr(cb, f'on_{cb_name}')(**self.state_dict, **kwargs), dict()) 242 for k,v in new.items(): 243 if k not in self.state_dict: TypeError: on_train_begin() missing 1 required positional argument: 'self'