diff --git a/.codecov.yml b/.codecov.yml
new file mode 100644
index 0000000000000..f10c1873295db
--- /dev/null
+++ b/.codecov.yml
@@ -0,0 +1,42 @@
+#see https://github.com/codecov/support/wiki/Codecov-Yaml
+codecov:
+ notify:
+ require_ci_to_pass: yes
+
+coverage:
+ precision: 0 # 2 = xx.xx%, 0 = xx%
+ round: nearest # how coverage is rounded: down/up/nearest
+ range: 40...100 # custom range of coverage colors from red -> yellow -> green
+ status:
+ # https://codecov.readme.io/v1.0/docs/commit-status
+ project:
+ default:
+ against: auto
+ target: 99% # specify the target coverage for each commit status
+ threshold: 20% # allow this little decrease on project
+ # https://github.com/codecov/support/wiki/Filtering-Branches
+ # branches: master
+ if_ci_failed: error
+ # https://github.com/codecov/support/wiki/Patch-Status
+ patch:
+ default:
+ against: auto
+ target: 40% # specify the target "X%" coverage to hit
+ # threshold: 50% # allow this much decrease on patch
+ changes: false
+
+parsers:
+ gcov:
+ branch_detection:
+ conditional: true
+ loop: true
+ macro: false
+ method: false
+ javascript:
+ enable_partials: false
+
+comment:
+ layout: header, diff
+ require_changes: false
+ behavior: default # update if exists else create new
+ # branches: *
diff --git a/.travis.yml b/.travis.yml
index d80b291f14299..fb1f8c95410b7 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,17 +1,46 @@
+# vim ft=yaml
+
+# After changing this file, check it on:
+# http://yaml-online-parser.appspot.com/
+
+# See doc/travis_notes.txt for some guidelines
+
+# this file is *not* meant to cover or endorse the use of travis, but rather to
+# help confirm pull requests to this project.
+
+dist: xenial # Ubuntu 16.04
+
+env:
+ global:
+ - DISPLAY=""
+
language: python
-python:
- - "3.7"
-# command to install dependencies
+
+matrix:
+ include:
+ - python: 3.6
+ env: TOXENV=py36
+ - python: 3.7
+ env: TOXENV=py37
+
+# See http://docs.travis-ci.com/user/caching/#pip-cache
cache: pip
+
install:
- - pip install -e .
- pip install -r requirements.txt
- - pip install -r tests/requirements.txt
- - pip install -U numpy
+ - pip install -r ./tests/requirements.txt
+ - pip --version ; pip list
-# keep build from timing out
-dist: xenial
-
-# command to run tests
script:
- - py.test -v # or py.test for Python versions 3.5 and below
\ No newline at end of file
+ # integration
+ - tox --sitepackages
+ - python setup.py install --dry-run
+
+after_success:
+ - coverage report
+ # disable auto coverage bc it isn't accurate since it misses gpu code.
+ # to get coverage, run local and push results
+ # - codecov
+
+notifications:
+ email: false
diff --git a/MANIFEST.in b/MANIFEST.in
index 53c1b22055d2e..e39ffbad5520d 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,9 +1,36 @@
-graft docs
+# Manifest syntax https://docs.python.org/2/distutils/sourcedist.html
+graft wheelhouse
-include COPYING
-include AUTHORS
+recursive-include birl *.py
+recursive-exclude __pycache__ *.py[cod] *.orig
-recursive-include src/einsteinpy/tests *.py *.html
+# Include the README
+include *.md
-prune docs/source/examples/.ipynb_checkpoints
-global-exclude *.py[cod] __pycache__ *.so *.dylib
+# Include the license file
+include LICENSE
+
+exclude *.sh
+exclude *.toml
+recursive-include examples *.py
+recursive-include pytorch_lightning *.py
+
+# exclude tests from package
+recursive-exclude tests *
+exclude tests
+
+# Exclude the documentation files
+recursive-exclude docs *
+exclude docs
+
+# Include the Requirements
+include requirements.txt
+
+# Exclude build configs
+exclude *.yml
+
+prune .git
+prune .github
+prune notebook*
+prune temp*
+prune test*
\ No newline at end of file
diff --git a/README.md b/README.md
index 7542eeef3a6f2..b2d286ece826c 100644
--- a/README.md
+++ b/README.md
@@ -1,25 +1,26 @@
-
-
-
-
-
- PyTorch Lightning
-
-
- The PyTorch Keras for ML researchers. More control. Less boilerplate.
-
-
-
-
+
+
+
+# PyTorch Lightning
+
+**The PyTorch Keras for ML researchers. More control. Less boilerplate.**
+
+
+[](https://badge.fury.io/py/pytorch-lightning)
+[](https://pepy.tech/project/pytorch-lightning)
+[](https://travis-ci.org/williamFalcon/pytorch-lightning)
+
+[](https://codecov.io/gh/Borda/pytorch-lightning)
+[](https://www.codefactor.io/repository/github/borda/pytorch-lightning)
+[](https://pytorch-lightning.readthedocs.io/en/latest)
+[](https://github.com/williamFalcon/pytorch-lightning/blob/master/LICENSE)
+
+
+
+Simple installation from PyPI
```bash
pip install pytorch-lightning
```
@@ -127,7 +128,7 @@ trainer = Trainer(experiment=exp, max_nb_epochs=1, train_percent_check=0.1)
trainer.fit(model)
# view tensorflow logs
-print(f'View tensorboard logs by running\ntensorboard --logdir {os.getcwd()}')
+print('View tensorboard logs by running\ntensorboard --logdir %s' % os.getcwd())
print('and going to http://localhost:6006 on your browser')
```
@@ -137,11 +138,7 @@ print('and going to http://localhost:6006 on your browser')
Everything in gray!
You define the blue parts using the LightningModule interface:
-
-
-
-
+
```{.python}
# what to do in the training loop
@@ -223,19 +220,11 @@ def validation_end(self, outputs):
## Tensorboard
Lightning is fully integrated with tensorboard.
-
-
-
-
+
Lightning also adds a text column with all the hyperparameters for this experiment.
-
-
-
-
+
Simply note the path you set for the Experiment
``` {.python}
diff --git a/appveyor.yml b/appveyor.yml
new file mode 100644
index 0000000000000..ad03a4786b057
--- /dev/null
+++ b/appveyor.yml
@@ -0,0 +1,66 @@
+# https://www.appveyor.com/docs/appveyor-yml/
+environment:
+
+ # SDK v7.0 MSVC Express 2008's SetEnv.cmd script will fail if the
+ # /E:ON and /V:ON options are not enabled in the batch script interpreter
+ # See: http://stackoverflow.com/a/13751649/163740
+ CMD_IN_ENV: "cmd /E:ON /V:ON /C obvci_appveyor_python_build_env.cmd"
+
+ matrix:
+ # Pre-installed Python versions, which Appveyor may upgrade to
+ # a later point release.
+ # See: http://www.appveyor.com/docs/installed-software#python
+
+
+ # - PYTHON: "C:\\Python35-x64"
+ # PYTHON_VERSION: "3.5.x"
+ # PYTHON_ARCH: "64"
+ # TOXENV: "py35"
+
+ - PYTHON: "C:\\Python36-x64"
+ PYTHON_VERSION: "3.6.x"
+ PYTHON_ARCH: "64"
+ TOXENV: "py36"
+ PIP_PYVER: "36"
+
+ - PYTHON: "C:\\Python37-x64"
+ PYTHON_VERSION: "3.7.x"
+ PYTHON_ARCH: "64"
+ TOXENV: "py37"
+ PIP_PYVER: "37"
+
+build: off
+
+# https://www.appveyor.com/docs/build-cache/
+cache:
+ - C:\ProgramData\chocolatey\bin -> appveyor.yml
+ - C:\ProgramData\chocolatey\lib -> appveyor.yml
+ - '%LOCALAPPDATA%\pip\Cache -> appveyor.yml'
+
+# scripts that run after cloning repository
+install:
+ # If there is a newer build queued for the same PR, cancel this one.
+ # The AppVeyor 'rollout builds' option is supposed to serve the same
+ # purpose but it is problematic because it tends to cancel builds pushed
+ # directly to master instead of just PR builds (or the converse).
+ - SET PATH=%PYTHON%;%PYTHON%\\Scripts;%path%
+ - pip install -U --user pip
+ - pip install "https://download.pytorch.org/whl/cu90/torch-1.1.0-cp%PIP_PYVER%-cp%PIP_PYVER%m-win_amd%PYTHON_ARCH%.whl"
+ pip install "https://download.pytorch.org/whl/cu90/torchvision-0.3.0-cp%PIP_PYVER%-cp%PIP_PYVER%m-win_amd%PYTHON_ARCH%.whl"
+ - pip install -r requirements.txt
+ - pip install -r ./tests/requirements.txt
+
+# scripts to run before tests (working directory and environment changes are persisted from the previous steps such as "before_build")
+before_test:
+ - python --version
+ - pip --version
+ - pip list
+ - dir
+
+# to run your custom scripts instead of automatic tests
+test_script:
+ - tox --sitepackages --parallel auto
+
+on_success:
+ - coverage report
+ # - codecov
diff --git a/coverage.svg b/coverage.svg
deleted file mode 100644
index 6bfc8faf24d3c..0000000000000
--- a/coverage.svg
+++ /dev/null
@@ -1,21 +0,0 @@
-
-
-
-
-
-
-
-
-
- coverage
- coverage
- 99%
- 99%
-
-
diff --git a/docs/Trainer/Distributed training.md b/docs/Trainer/Distributed training.md
index aedbd20ed1f42..cafc719df0a95 100644
--- a/docs/Trainer/Distributed training.md
+++ b/docs/Trainer/Distributed training.md
@@ -94,7 +94,7 @@ cluster.add_command('export NCCL_SOCKET_IFNAME=^docker0,lo')
cluster.add_command('export NCCL_DEBUG=INFO')
# setting a master port here is a good idea.
-cluster.add_command(f'export MASTER_PORT={PORT}')
+cluster.add_command('export MASTER_PORT=%r' % PORT)
# good to load the latest NCCL version
cluster.load_modules(['NCCL/2.4.7-1-cuda.10.0'])
diff --git a/docs/source/_static/lightning_logo_medium.png b/docs/source/_static/lightning_logo_medium.png
new file mode 100644
index 0000000000000..a28606b541632
Binary files /dev/null and b/docs/source/_static/lightning_logo_medium.png differ
diff --git a/docs/source/_static/lightning_logo_small.png b/docs/source/_static/lightning_logo_small.png
new file mode 100644
index 0000000000000..17d0aa92bce2b
Binary files /dev/null and b/docs/source/_static/lightning_logo_small.png differ
diff --git a/examples/__init__.py b/examples/__init__.py
index 6743d7f97919c..0d456dacb6443 100644
--- a/examples/__init__.py
+++ b/examples/__init__.py
@@ -1 +1,5 @@
-from .new_project_templates.lightning_module_template import LightningTemplateModel
\ No newline at end of file
+from .new_project_templates.lightning_module_template import LightningTemplateModel
+
+__all__ = [
+ 'LightningTemplateModel'
+]
diff --git a/examples/new_project_templates/lightning_module_template.py b/examples/new_project_templates/lightning_module_template.py
index 483a4e3a048df..d6bdd13068e40 100644
--- a/examples/new_project_templates/lightning_module_template.py
+++ b/examples/new_project_templates/lightning_module_template.py
@@ -47,11 +47,13 @@ def __build_model(self):
Layout model
:return:
"""
- self.c_d1 = nn.Linear(in_features=self.hparams.in_features, out_features=self.hparams.hidden_dim)
+ self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+ out_features=self.hparams.hidden_dim)
self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
- self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim, out_features=self.hparams.out_features)
+ self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+ out_features=self.hparams.out_features)
# ---------------------
# TRAINING
@@ -171,8 +173,10 @@ def configure_optimizers(self):
def __dataloader(self, train):
# init data generators
- transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
- dataset = MNIST(root=self.hparams.data_root, train=train, transform=transform, download=True)
+ transform = transforms.Compose([transforms.ToTensor(),
+ transforms.Normalize((0.5,), (1.0,))])
+ dataset = MNIST(root=self.hparams.data_root, train=train,
+ transform=transform, download=True)
# when using multi-node we need to add the datasampler
train_sampler = None
@@ -182,7 +186,7 @@ def __dataloader(self, train):
if self.on_gpu:
train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
batch_size = batch_size // self.trainer.world_size # scale batch size
- except Exception as e:
+ except Exception:
pass
should_shuffle = train_sampler is None
@@ -211,7 +215,7 @@ def test_dataloader(self):
return self.__dataloader(train=False)
@staticmethod
- def add_model_specific_args(parent_parser, root_dir): # pragma: no cover
+ def add_model_specific_args(parent_parser, root_dir): # pragma: no cover
"""
Parameters you define here will be available to your model through self.hparams
:param parent_parser:
@@ -224,20 +228,25 @@ def add_model_specific_args(parent_parser, root_dir): # pragma: no cover
# parser.set_defaults(gradient_clip=5.0)
# network params
- parser.add_argument('--in_features', default=28*28, type=int)
+ parser.add_argument('--in_features', default=28 * 28, type=int)
parser.add_argument('--out_features', default=10, type=int)
- parser.add_argument('--hidden_dim', default=50000, type=int) # use 500 for CPU, 50000 for GPU to see speed difference
+ # use 500 for CPU, 50000 for GPU to see speed difference
+ parser.add_argument('--hidden_dim', default=50000, type=int)
parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
# data
parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
# training params (opt)
- parser.opt_list('--learning_rate', default=0.001*8, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
+ parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+ options=[0.0001, 0.0005, 0.001, 0.005],
tunable=False)
- parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
-
- # if using 2 nodes with 4 gpus each the batch size here (256) will be 256 / (2*8) = 16 per gpu
- parser.opt_list('--batch_size', default=256*8, type=int, options=[32, 64, 128, 256], tunable=False,
- help='batch size will be divided over all the gpus being used across all nodes')
+ parser.opt_list('--optimizer_name', default='adam', type=str,
+ options=['adam'], tunable=False)
+
+ # if using 2 nodes with 4 gpus each the batch size here
+ # (256) will be 256 / (2*8) = 16 per gpu
+ parser.opt_list('--batch_size', default=256 * 8, type=int,
+ options=[32, 64, 128, 256], tunable=False,
+ help='batch size will be divided over all gpus being used across all nodes')
return parser
diff --git a/examples/new_project_templates/multi_node_cluster_template.py b/examples/new_project_templates/multi_node_cluster_template.py
index 5f6914d107ae0..c4af6d416b20a 100644
--- a/examples/new_project_templates/multi_node_cluster_template.py
+++ b/examples/new_project_templates/multi_node_cluster_template.py
@@ -10,12 +10,12 @@
from pytorch_lightning.models.trainer import Trainer
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
SEED = 2334
torch.manual_seed(SEED)
np.random.seed(SEED)
-from .lightning_module_template import LightningTemplateModel
-
def main_local(hparams):
main(hparams, None, None)
@@ -112,8 +112,10 @@ def optimize_on_cluster(hyperparams):
cluster.add_command('source activate lightning')
# run only on 32GB voltas
- cluster.add_slurm_cmd(cmd='constraint', value='volta32gb', comment='use 32gb gpus')
- cluster.add_slurm_cmd(cmd='partition', value=hyperparams.gpu_partition, comment='use 32gb gpus')
+ cluster.add_slurm_cmd(cmd='constraint', value='volta32gb',
+ comment='use 32gb gpus')
+ cluster.add_slurm_cmd(cmd='partition', value=hyperparams.gpu_partition,
+ comment='use 32gb gpus')
# run hopt
# creates and submits jobs to slurm
@@ -140,15 +142,23 @@ def optimize_on_cluster(hyperparams):
parent_parser.add_argument('--gpu_partition', type=str, help='consult your cluster manual')
# TODO: make 1 param
- parent_parser.add_argument('--per_experiment_nb_gpus', type=int, help='how many gpus to use in a node')
- parent_parser.add_argument('--gpus', type=str, default='-1', help='how many gpus to use in the node')
-
- parent_parser.add_argument('--nb_gpu_nodes', type=int, default=1, help='how many nodes to use in a cluster')
- parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir, help='where to save logs')
- parent_parser.add_argument('--slurm_log_path', type=str, default=slurm_out_dir, help='where to save slurm meta')
- parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model')
- parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name')
- parent_parser.add_argument('--nb_hopt_trials', type=int, default=1, help='how many grid search trials to run')
+ parent_parser.add_argument('--per_experiment_nb_gpus', type=int,
+ help='how many gpus to use in a node')
+ parent_parser.add_argument('--gpus', type=str, default='-1',
+ help='how many gpus to use in the node')
+
+ parent_parser.add_argument('--nb_gpu_nodes', type=int, default=1,
+ help='how many nodes to use in a cluster')
+ parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+ help='where to save logs')
+ parent_parser.add_argument('--slurm_log_path', type=str, default=slurm_out_dir,
+ help='where to save slurm meta')
+ parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+ help='where to save model')
+ parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+ help='test tube exp name')
+ parent_parser.add_argument('--nb_hopt_trials', type=int, default=1,
+ help='how many grid search trials to run')
# allow model to overwrite or extend args
parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
diff --git a/examples/new_project_templates/single_cpu_template.py b/examples/new_project_templates/single_cpu_template.py
index 29c255981627a..c0f4826f99634 100644
--- a/examples/new_project_templates/single_cpu_template.py
+++ b/examples/new_project_templates/single_cpu_template.py
@@ -9,12 +9,12 @@
from pytorch_lightning.models.trainer import Trainer
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
SEED = 2334
torch.manual_seed(SEED)
np.random.seed(SEED)
-from .lightning_module_template import LightningTemplateModel
-
def main(hparams):
"""
@@ -90,9 +90,12 @@ def main(hparams):
parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
# gpu args
- parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir, help='where to save logs')
- parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model')
- parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name')
+ parent_parser.add_argument('--test_tube_save_path', type=str,
+ default=test_tube_dir, help='where to save logs')
+ parent_parser.add_argument('--model_save_path', type=str,
+ default=checkpoint_dir, help='where to save model')
+ parent_parser.add_argument('--experiment_name', type=str,
+ default='pt_lightning_exp_a', help='test tube exp name')
# allow model to overwrite or extend args
parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
@@ -102,5 +105,5 @@ def main(hparams):
# RUN TRAINING
# ---------------------
# run on HPC cluster
- print(f'RUNNING ON CPU')
+ print('RUNNING ON CPU')
main(hyperparams)
diff --git a/examples/new_project_templates/single_gpu_node_16bit_template.py b/examples/new_project_templates/single_gpu_node_16bit_template.py
index 14db484e56409..babf18e73a2a4 100644
--- a/examples/new_project_templates/single_gpu_node_16bit_template.py
+++ b/examples/new_project_templates/single_gpu_node_16bit_template.py
@@ -9,12 +9,12 @@
from pytorch_lightning.models.trainer import Trainer
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
SEED = 2334
torch.manual_seed(SEED)
np.random.seed(SEED)
-from .lightning_module_template import LightningTemplateModel
-
def main(hparams):
"""
@@ -92,10 +92,15 @@ def main(hparams):
parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
# gpu args
- parent_parser.add_argument('--gpus', type=str, default='-1', help='how many gpus to use in the node. -1 uses all the gpus on the node')
- parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir, help='where to save logs')
- parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model')
- parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name')
+ parent_parser.add_argument('--gpus', type=str, default='-1',
+ help='how many gpus to use in the node.'
+ 'value -1 uses all the gpus on the node')
+ parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+ help='where to save logs')
+ parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+ help='where to save model')
+ parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+ help='test tube exp name')
# allow model to overwrite or extend args
parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
@@ -105,5 +110,5 @@ def main(hparams):
# RUN TRAINING
# ---------------------
# run on HPC cluster
- print(f'RUNNING INTERACTIVE MODE ON GPUS. gpu ids: {hyperparams.gpus}')
+ print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
main(hyperparams)
diff --git a/examples/new_project_templates/single_gpu_node_ddp_template.py b/examples/new_project_templates/single_gpu_node_ddp_template.py
index 56e301b20478a..68a332aeb8b5a 100644
--- a/examples/new_project_templates/single_gpu_node_ddp_template.py
+++ b/examples/new_project_templates/single_gpu_node_ddp_template.py
@@ -9,12 +9,12 @@
from pytorch_lightning.models.trainer import Trainer
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
SEED = 2334
torch.manual_seed(SEED)
np.random.seed(SEED)
-from .lightning_module_template import LightningTemplateModel
-
def main(hparams):
"""
@@ -92,10 +92,15 @@ def main(hparams):
parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
# gpu args
- parent_parser.add_argument('--gpus', type=str, default='-1', help='how many gpus to use in the node. -1 uses all the gpus on the node')
- parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir, help='where to save logs')
- parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model')
- parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name')
+ parent_parser.add_argument('--gpus', type=str, default='-1',
+ help='how many gpus to use in the node.'
+ ' value -1 uses all the gpus on the node')
+ parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+ help='where to save logs')
+ parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+ help='where to save model')
+ parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+ help='test tube exp name')
# allow model to overwrite or extend args
parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
@@ -105,5 +110,5 @@ def main(hparams):
# RUN TRAINING
# ---------------------
# run on HPC cluster
- print(f'RUNNING INTERACTIVE MODE ON GPUS. gpu ids: {hyperparams.gpus}')
+ print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
main(hyperparams)
diff --git a/examples/new_project_templates/single_gpu_node_dp_template.py b/examples/new_project_templates/single_gpu_node_dp_template.py
index 9d6992533b680..d752713ee1df4 100644
--- a/examples/new_project_templates/single_gpu_node_dp_template.py
+++ b/examples/new_project_templates/single_gpu_node_dp_template.py
@@ -9,12 +9,12 @@
from pytorch_lightning.models.trainer import Trainer
from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
+
SEED = 2334
torch.manual_seed(SEED)
np.random.seed(SEED)
-from .lightning_module_template import LightningTemplateModel
-
def main(hparams):
"""
@@ -91,10 +91,15 @@ def main(hparams):
parent_parser = HyperOptArgumentParser(strategy='grid_search', add_help=False)
# gpu args
- parent_parser.add_argument('--gpus', type=str, default='-1', help='how many gpus to use in the node. -1 uses all the gpus on the node')
- parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir, help='where to save logs')
- parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir, help='where to save model')
- parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a', help='test tube exp name')
+ parent_parser.add_argument('--gpus', type=str, default='-1',
+ help='how many gpus to use in the node.'
+ ' value -1 uses all the gpus on the node')
+ parent_parser.add_argument('--test_tube_save_path', type=str, default=test_tube_dir,
+ help='where to save logs')
+ parent_parser.add_argument('--model_save_path', type=str, default=checkpoint_dir,
+ help='where to save model')
+ parent_parser.add_argument('--experiment_name', type=str, default='pt_lightning_exp_a',
+ help='test tube exp name')
# allow model to overwrite or extend args
parser = LightningTemplateModel.add_model_specific_args(parent_parser, root_dir)
@@ -104,5 +109,5 @@ def main(hparams):
# RUN TRAINING
# ---------------------
# run on HPC cluster
- print(f'RUNNING INTERACTIVE MODE ON GPUS. gpu ids: {hyperparams.gpus}')
+ print('RUNNING INTERACTIVE MODE ON GPUS. gpu ids: %i' % hyperparams.gpus)
main(hyperparams)
diff --git a/examples/new_project_templates/trainer_cpu_template.py b/examples/new_project_templates/trainer_cpu_template.py
index de6ba7c424571..84a29a9bf3627 100644
--- a/examples/new_project_templates/trainer_cpu_template.py
+++ b/examples/new_project_templates/trainer_cpu_template.py
@@ -6,7 +6,7 @@
from pytorch_lightning.utilities.arg_parse import add_default_args
from pytorch_lightning.callbacks.pt_callbacks import EarlyStopping, ModelCheckpoint
-from .lightning_module_template import LightningTemplateModel
+from examples.new_project_templates.lightning_module_template import LightningTemplateModel
def main(hparams):
@@ -67,7 +67,7 @@ def main(hparams):
add_default_args(parent_parser, root_dir)
# allow model to overwrite or extend args
- parser = ExampleModel.add_model_specific_args(parent_parser)
+ parser = LightningTemplateModel.add_model_specific_args(parent_parser)
hyperparams = parser.parse_args()
# train model
diff --git a/pytorch_lightning/__init__.py b/pytorch_lightning/__init__.py
index 4b5961ac2daf4..73067d63858f9 100644
--- a/pytorch_lightning/__init__.py
+++ b/pytorch_lightning/__init__.py
@@ -1,3 +1,19 @@
from .models.trainer import Trainer
from .root_module.root_module import LightningModule
-from .root_module.decorators import data_loader
\ No newline at end of file
+from .root_module.decorators import data_loader
+
+__version__ = '0.3.6.9'
+__author__ = "William Falcon",
+__author_email__ = "waf2107@columbia.edu"
+__license__ = 'Apache-2'
+__homepage__ = 'https://github.com/williamFalcon/pytorch-lightning',
+__copyright__ = 'Copyright (c) 2018-2019, %s.' % __author__
+__doc__ = """
+The Keras for ML researchers using PyTorch
+"""
+
+__all__ = [
+ 'Trainer',
+ 'LightningModule',
+ 'data_loader',
+]
diff --git a/pytorch_lightning/callbacks/__init__.py b/pytorch_lightning/callbacks/__init__.py
index f180c2542490f..035deb0681d7d 100644
--- a/pytorch_lightning/callbacks/__init__.py
+++ b/pytorch_lightning/callbacks/__init__.py
@@ -1 +1,6 @@
-from .pt_callbacks import EarlyStopping, ModelCheckpoint
\ No newline at end of file
+from .pt_callbacks import EarlyStopping, ModelCheckpoint
+
+__all__ = [
+ 'EarlyStopping',
+ 'ModelCheckpoint',
+]
diff --git a/pytorch_lightning/callbacks/pt_callbacks.py b/pytorch_lightning/callbacks/pt_callbacks.py
index 89c8f6b2e5f8f..f07c6a28e33c3 100644
--- a/pytorch_lightning/callbacks/pt_callbacks.py
+++ b/pytorch_lightning/callbacks/pt_callbacks.py
@@ -122,9 +122,9 @@ def on_epoch_end(self, epoch, logs=None):
current = logs.get(self.monitor)
stop_training = False
if current is None:
- print('Early stopping conditioned on metric `%s` ''which is not available. Available metrics are: %s' %
- (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning
- )
+ print('Early stopping conditioned on metric `%s` '
+ 'which is not available. Available metrics are: %s' %
+ (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning)
exit(-1)
if self.monitor_op(current - self.min_delta, self.best):
@@ -188,8 +188,7 @@ def __init__(self, filepath, monitor='val_loss', verbose=0,
if mode not in ['auto', 'min', 'max']:
print('ModelCheckpoint mode %s is unknown, '
- 'fallback to auto mode.' % (mode),
- RuntimeWarning)
+ 'fallback to auto mode.' % (mode), RuntimeWarning)
mode = 'auto'
if mode == 'min':
@@ -233,8 +232,8 @@ def on_epoch_end(self, epoch, logs=None):
if self.save_best_only:
current = logs.get(self.monitor)
if current is None:
- print('Can save best model only with %s available, '
- 'skipping.' % (self.monitor), RuntimeWarning)
+ print('Can save best model only with %s available,'
+ ' skipping.' % (self.monitor), RuntimeWarning)
else:
if self.monitor_op(current, self.best):
if self.verbose > 0:
diff --git a/pytorch_lightning/models/__init__.py b/pytorch_lightning/models/__init__.py
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/pytorch_lightning/models/trainer.py b/pytorch_lightning/models/trainer.py
index 2655809c4a7de..574c8061c55d9 100644
--- a/pytorch_lightning/models/trainer.py
+++ b/pytorch_lightning/models/trainer.py
@@ -1,12 +1,10 @@
"""
The trainer handles all the logic for running a val loop, training loop, distributing, etc...
"""
-import subprocess
-import traceback
-import warnings
+
import os
-import pdb
import re
+import warnings
import numpy as np
import tqdm
@@ -17,13 +15,14 @@
from ..root_module.memory import get_gpu_memory_map
from ..root_module.model_saving import TrainerIO
-from ..pt_overrides.override_data_parallel import LightningDistributedDataParallel, LightningDataParallel
+from ..pt_overrides.override_data_parallel import (
+ LightningDistributedDataParallel, LightningDataParallel)
from ..utilities.debugging import MisconfigurationException
try:
from apex import amp
APEX_AVAILABLE = True
-except Exception:
+except ImportError:
APEX_AVAILABLE = False
@@ -66,17 +65,20 @@ def __init__(self,
check_val_every_n_epoch=1,
fast_dev_run=False,
accumulate_grad_batches=1,
- max_nb_epochs=1000, min_nb_epochs=1,
- train_percent_check=1.0, val_percent_check=1.0, test_percent_check=1.0,
+ max_nb_epochs=1000,
+ min_nb_epochs=1,
+ train_percent_check=1.0,
+ val_percent_check=1.0,
+ test_percent_check=1.0,
val_check_interval=0.95,
- log_save_interval=100, add_log_row_interval=10,
+ log_save_interval=100,
+ add_log_row_interval=10,
distributed_backend='dp',
use_amp=False,
print_nan_grads=False,
print_weights_summary=True,
amp_level='O2',
nb_sanity_val_steps=5):
-
"""
:param experiment: Test-tube experiment
@@ -102,16 +104,15 @@ def __init__(self,
:param val_check_interval:
:param log_save_interval:
:param add_log_row_interval:
- :param distributed_backend: 'np' to use DistributedParallel, 'ddp' to use DistributedDataParallel
+ :param distributed_backend:
+ 'np' to use DistributedParallel, 'dp' to use DistributedDataParallel
:param use_amp:
:param print_nan_grads:
:param print_weights_summary:
:param amp_level:
:param nb_sanity_val_steps:
"""
-
# Transfer params
-
self.nb_gpu_nodes = nb_gpu_nodes
self.gradient_clip = gradient_clip
self.check_val_every_n_epoch = check_val_every_n_epoch
@@ -173,13 +174,14 @@ def __init__(self,
# set the correct cuda visible devices (using pci order)
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
- os.environ["CUDA_VISIBLE_DEVICES"] = ','.join([str(x) for x in self.data_parallel_device_ids])
- print(f'VISIBLE GPUS: {os.environ["CUDA_VISIBLE_DEVICES"]}')
+ os.environ["CUDA_VISIBLE_DEVICES"] = ','.join([str(x) for x in
+ self.data_parallel_device_ids])
+ print('VISIBLE GPUS: %r' % os.environ["CUDA_VISIBLE_DEVICES"])
# make DP and DDP mutually exclusive
# single GPU will also use DP with devices=[0]
- have_gpus = self.data_parallel_device_ids is not None and len(self.data_parallel_device_ids) > 0
- if have_gpus:
+ requested_gpus = self.data_parallel_device_ids is not None
+ if requested_gpus and len(self.data_parallel_device_ids) > 0:
self.use_dp = distributed_backend == 'dp'
self.use_ddp = distributed_backend == 'ddp'
@@ -201,7 +203,7 @@ def __init__(self,
try:
self.nb_slurm_tasks = int(os.environ['SLURM_NTASKS'])
self.is_slurm_managing_tasks = self.nb_slurm_tasks == self.nb_requested_gpus
- except Exception as e:
+ except Exception:
# likely not on slurm, so set the slurm managed flag to false
self.is_slurm_managing_tasks = False
@@ -226,7 +228,8 @@ def __init__(self,
self.val_dataloader = None
# how much of the data to use
- self.__determine_data_use_amount(train_percent_check, val_percent_check, test_percent_check, overfit_pct)
+ self.__determine_data_use_amount(train_percent_check, val_percent_check,
+ test_percent_check, overfit_pct)
print('gpu available: {}, used: {}'.format(torch.cuda.is_available(), self.on_gpu))
# 16 bit mixed precision training using apex
@@ -235,20 +238,21 @@ def __init__(self,
print('using 16bit precision')
if use_amp and not APEX_AVAILABLE: # pragma: no cover
- msg = '''
+ msg = """
You set use_amp=True but do not have apex installed.
- Install apex first using this guide and rerun with use_amp=True:
+ Install apex first using this guide and rerun with use_amp=True:
https://github.com/NVIDIA/apex#linux
-
+
this run will NOT use 16 bit precision
- '''
+ """
raise ModuleNotFoundError(msg)
@property
def data_parallel(self):
return self.use_dp or self.use_ddp
- def __determine_data_use_amount(self, train_percent_check, val_percent_check, test_percent_check, overfit_pct):
+ def __determine_data_use_amount(self, train_percent_check, val_percent_check,
+ test_percent_check, overfit_pct):
"""
Use less data for debugging purposes
"""
@@ -275,7 +279,7 @@ def __tng_tqdm_dic(self):
'tng_loss': '{0:.3f}'.format(self.avg_loss),
'v_nb': '{}'.format(self.experiment.version),
'epoch': '{}'.format(self.current_epoch),
- 'batch_nb':'{}'.format(self.batch_nb),
+ 'batch_nb': '{}'.format(self.batch_nb),
}
tqdm_dic.update(self.tqdm_metrics)
@@ -389,18 +393,19 @@ def get_dataloaders(self, model):
self.val_dataloader = model.val_dataloader
if self.use_ddp and not isinstance(self.tng_dataloader.sampler, DistributedSampler):
- msg = '''
- when using multiple gpus and multiple nodes you must pass a DistributedSampler to DataLoader(sampler).
-
- ie: this:
- dataset = myDataset()
- dataloader = Dataloader(dataset)
-
- becomes:
- dataset = myDataset()
- dist_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
- dataloader = Dataloader(dataset, sampler=dist_sampler)
- '''
+ msg = """
+when using multiple gpus and multiple nodes you must pass
+ a DistributedSampler to DataLoader(sampler).
+
+ie: this:
+dataset = myDataset()
+dataloader = Dataloader(dataset)
+
+becomes:
+dataset = myDataset()
+dist_sampler = torch.utils.data.distributed.DistributedSampler(dataset)
+dataloader = Dataloader(dataset, sampler=dist_sampler)
+"""
raise MisconfigurationException(msg)
# -----------------------------
@@ -410,19 +415,20 @@ def fit(self, model):
# when using multi-node or DDP within a node start each module in a separate process
if self.use_ddp:
- # must copy only the meta of the exp so it survives pickle/unpickle when going to new process
+ # must copy only the meta of the exp so it survives pickle/unpickle
+ # when going to new process
self.experiment = self.experiment.get_meta_copy()
if self.is_slurm_managing_tasks:
task = int(os.environ['SLURM_LOCALID'])
self.ddp_train(task, model)
else:
- msg = f"""
- You requested {self.nb_requested_gpus} GPUs but launched {self.nb_slurm_tasks} slurm tasks.
- We will launch {self.nb_requested_gpus} processes for you.
- We recommend you let slurm manage the processes by setting: --ntasks-per-node={self.nb_requested_gpus}
- If you're not using SLURM, ignore this message!
- """
+ msg = """
+You requested %(nb_gpus)s GPUs but launched %(nb_tasks)s slurm tasks.
+We will launch %(nb_gpus)s processes for you.
+We recommend you let slurm manage the processes by setting: --ntasks-per-node=%(nb_gpus)s
+If you're not using SLURM, ignore this message!
+""" % {'nb_gpus': self.nb_requested_gpus, 'nb_tasks': self.nb_slurm_tasks}
warnings.warn(msg)
mp.spawn(self.ddp_train, nprocs=len(self.data_parallel_device_ids), args=(model, ))
@@ -435,7 +441,8 @@ def fit(self, model):
else:
# run through amp wrapper
if self.use_amp:
- raise MisconfigurationException('amp + cpu is not supported. Please use a GPU option')
+ raise MisconfigurationException('amp + cpu is not supported.'
+ ' Please use a GPU option')
# CHOOSE OPTIMIZER
# allow for lr schedulers as well
@@ -462,9 +469,11 @@ def __dp_train(self, model):
# check for this bug (amp + dp + !01 doesn't work)
# https://github.com/NVIDIA/apex/issues/227
if self.use_dp and self.use_amp:
- m = f'amp level {self.amp_level} with DataParallel is not supported. ' \
- f'See this note from NVIDIA for more info: https://github.com/NVIDIA/apex/issues/227. ' \
- f'We recommend you switch to ddp if you want to use amp'
+ m = """
+Amp level %r with DataParallel is not supported.
+See this note from NVIDIA for more info: https://github.com/NVIDIA/apex/issues/227.
+We recommend you switch to ddp if you want to use amp
+""" % self.amp_level
raise MisconfigurationException(m)
model = LightningDataParallel(model, device_ids=self.data_parallel_device_ids)
@@ -484,7 +493,7 @@ def ddp_train(self, gpu_nb, model):
try:
node_id = os.environ['SLURM_NODEID']
self.node_rank = int(node_id)
- except Exception as e:
+ except Exception:
self.node_rank = 0
# recover original exp before went into process
@@ -527,7 +536,8 @@ def ddp_train(self, gpu_nb, model):
)
self.optimizers = optimizers
- model = LightningDistributedDataParallel(model, device_ids=[gpu_nb], find_unused_parameters=True)
+ model = LightningDistributedDataParallel(model, device_ids=[gpu_nb],
+ find_unused_parameters=True)
# continue training routine
self.__run_pretrain_routine(model)
@@ -543,14 +553,14 @@ def __init_tcp_connection(self):
# sets the appropriate port
try:
port = os.environ['MASTER_PORT']
- except Exception as e:
+ except Exception:
port = 12910
- os.environ['MASTER_PORT'] = f'{port}'
+ os.environ['MASTER_PORT'] = str(port)
# figure out the root node addr
try:
root_node = os.environ['SLURM_NODELIST'].split(' ')[0]
- except Exception as e:
+ except Exception:
root_node = '127.0.0.2'
root_node = self.resolve_root_node_address(root_node)
@@ -642,7 +652,8 @@ def __train(self):
# init progbar when requested
if self.progress_bar:
- self.prog_bar = tqdm.tqdm(range(self.total_batches), position=self.process_position)
+ self.prog_bar = tqdm.tqdm(range(self.total_batches),
+ position=self.process_position)
for batch_nb, data_batch in enumerate(self.tng_dataloader):
self.batch_nb = batch_nb
@@ -651,7 +662,8 @@ def __train(self):
model = self.__get_model()
model.global_step = self.global_step
- # stop when the flag is changed or we've gone past the amount requested in the batches
+ # stop when the flag is changed or we've gone past the amount
+ # requested in the batches
self.total_batch_nb += 1
met_batch_limit = batch_nb > self.nb_tng_batches
if met_batch_limit:
@@ -698,7 +710,8 @@ def __train(self):
model.on_tng_metrics(metrics)
# log metrics
- scalar_metrics = self.__metrics_to_scalars(metrics, blacklist=self.__log_vals_blacklist())
+ scalar_metrics = self.__metrics_to_scalars(
+ metrics, blacklist=self.__log_vals_blacklist())
if self.proc_rank == 0:
self.experiment.log(scalar_metrics, global_step=self.global_step)
self.experiment.save()
@@ -720,7 +733,8 @@ def __train(self):
# early stopping
met_min_epochs = epoch_nb > self.min_nb_epochs
if self.enable_early_stop and met_min_epochs:
- should_stop = self.early_stop_callback.on_epoch_end(epoch=epoch_nb, logs=self.__tng_tqdm_dic)
+ should_stop = self.early_stop_callback.on_epoch_end(epoch=epoch_nb,
+ logs=self.__tng_tqdm_dic)
# stop training
stop = should_stop and met_min_epochs
@@ -773,14 +787,14 @@ def __run_tng_batch(self, data_batch, batch_nb):
try:
model_specific_tqdm_metrics_dic = output['prog']
- except Exception as e:
+ except Exception:
model_specific_tqdm_metrics_dic = {}
# if output dict doesn't have the keyword loss
# then assume the output=loss if scalar
try:
loss = output['loss']
- except Exception as e:
+ except Exception:
if type(output) is torch.Tensor:
loss = output
@@ -828,7 +842,8 @@ def __run_tng_batch(self, data_batch, batch_nb):
# clear gradients
optimizer.zero_grad()
- # queuing loss across batches blows it up proportionally... divide out the number accumulated
+ # queuing loss across batches blows it up proportionally...
+ # divide out the number accumulated
self.batch_loss_value = self.batch_loss_value / self.accumulate_grad_batches
# track loss
@@ -885,4 +900,5 @@ def __run_validation(self):
# model checkpointing
if self.proc_rank == 0 and self.checkpoint_callback is not None:
print('save callback...')
- self.checkpoint_callback.on_epoch_end(epoch=self.current_epoch, logs=self.__tng_tqdm_dic)
+ self.checkpoint_callback.on_epoch_end(epoch=self.current_epoch,
+ logs=self.__tng_tqdm_dic)
diff --git a/pytorch_lightning/pt_overrides/override_data_parallel.py b/pytorch_lightning/pt_overrides/override_data_parallel.py
index f06f8030ad500..ab88d286bb73b 100644
--- a/pytorch_lightning/pt_overrides/override_data_parallel.py
+++ b/pytorch_lightning/pt_overrides/override_data_parallel.py
@@ -63,7 +63,6 @@ def forward(self, *inputs, **kwargs):
outputs = self.parallel_apply(replicas, inputs, kwargs)
return self.gather(outputs, self.output_device)
-
def parallel_apply(self, replicas, inputs, kwargs):
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
diff --git a/pytorch_lightning/root_module/grads.py b/pytorch_lightning/root_module/grads.py
index d50fa450961a2..7bdc8572b97fb 100644
--- a/pytorch_lightning/root_module/grads.py
+++ b/pytorch_lightning/root_module/grads.py
@@ -4,6 +4,7 @@
from torch import nn
+
class GradInformation(nn.Module):
def grad_norm(self, norm_type):
@@ -16,12 +17,13 @@ def grad_norm(self, norm_type):
total_norm += param_norm ** norm_type
norm = param_norm ** (1 / norm_type)
- results['grad_{}_norm_{}'.format(norm_type, i)] = round(norm.data.cpu().numpy().flatten()[0], 3)
- except Exception as e:
+ grad = round(norm.data.cpu().numpy().flatten()[0], 3)
+ results['grad_{}_norm_{}'.format(norm_type, i)] = grad
+ except Exception:
# this param had no grad
pass
total_norm = total_norm ** (1. / norm_type)
- results['grad_{}_norm_total'.format(norm_type)] = round(total_norm.data.cpu().numpy().flatten()[0], 3)
+ grad = round(total_norm.data.cpu().numpy().flatten()[0], 3)
+ results['grad_{}_norm_total'.format(norm_type)] = grad
return results
-
diff --git a/pytorch_lightning/root_module/hooks.py b/pytorch_lightning/root_module/hooks.py
index 849826a83eabb..00ece234824e5 100644
--- a/pytorch_lightning/root_module/hooks.py
+++ b/pytorch_lightning/root_module/hooks.py
@@ -43,4 +43,3 @@ def on_after_backward(self):
:return:
"""
pass
-
diff --git a/pytorch_lightning/root_module/memory.py b/pytorch_lightning/root_module/memory.py
index 128fb16f18b43..3a636b040a270 100644
--- a/pytorch_lightning/root_module/memory.py
+++ b/pytorch_lightning/root_module/memory.py
@@ -94,7 +94,7 @@ def get_parameter_sizes(self):
mods = list(self.model.modules())
sizes = []
- for i in range(1,len(mods)):
+ for i in range(1, len(mods)):
m = mods[i]
p = list(m.parameters())
modsz = []
@@ -127,7 +127,7 @@ def make_summary(self):
if self.model.example_input_array is not None:
cols.extend(['In_sizes', 'Out_sizes'])
- df = pd.DataFrame(np.zeros( (len(self.layer_names), len(cols))))
+ df = pd.DataFrame(np.zeros((len(self.layer_names), len(cols))))
df.columns = cols
df['Name'] = self.layer_names
@@ -152,16 +152,16 @@ def summarize(self):
self.make_summary()
-def print_mem_stack(): # pragma: no cover
+def print_mem_stack(): # pragma: no cover
for obj in gc.get_objects():
try:
if torch.is_tensor(obj) or (hasattr(obj, 'data') and torch.is_tensor(obj.data)):
print(type(obj), obj.size())
- except Exception as e:
+ except Exception:
pass
-def count_mem_items(): # pragma: no cover
+def count_mem_items(): # pragma: no cover
nb_params = 0
nb_tensors = 0
for obj in gc.get_objects():
@@ -172,7 +172,7 @@ def count_mem_items(): # pragma: no cover
nb_params += 1
else:
nb_tensors += 1
- except Exception as e:
+ except Exception:
pass
return nb_params, nb_tensors
@@ -196,6 +196,6 @@ def get_gpu_memory_map():
gpu_memory = [int(x) for x in result.strip().split('\n')]
gpu_memory_map = {}
for k, v in zip(range(len(gpu_memory)), gpu_memory):
- k = f'gpu_{k}'
+ k = 'gpu_%i' % k
gpu_memory_map[k] = v
return gpu_memory_map
diff --git a/pytorch_lightning/root_module/model_saving.py b/pytorch_lightning/root_module/model_saving.py
index 0bde0943f45a8..0765142cd537f 100644
--- a/pytorch_lightning/root_module/model_saving.py
+++ b/pytorch_lightning/root_module/model_saving.py
@@ -3,7 +3,8 @@
import torch
-from ..pt_overrides.override_data_parallel import LightningDistributedDataParallel, LightningDataParallel
+from ..pt_overrides.override_data_parallel import (
+ LightningDistributedDataParallel, LightningDataParallel)
class ModelIO(object):
@@ -45,7 +46,8 @@ def on_hpc_load(self, checkpoint):
class TrainerIO(object):
def __get_model(self):
- is_dp_module = type(self.model) is LightningDistributedDataParallel or type(self.model) is LightningDataParallel
+ is_dp_module = isinstance(self.model, (LightningDistributedDataParallel,
+ LightningDataParallel))
model = self.model.module if is_dp_module else self.model
return model
diff --git a/pytorch_lightning/root_module/root_module.py b/pytorch_lightning/root_module/root_module.py
index 1421a72d5b357..96dbfdcd442a0 100644
--- a/pytorch_lightning/root_module/root_module.py
+++ b/pytorch_lightning/root_module/root_module.py
@@ -129,6 +129,3 @@ def freeze(self):
def unfreeze(self):
for param in self.parameters():
param.requires_grad = True
-
-
-
diff --git a/pytorch_lightning/testing/lm_test_module.py b/pytorch_lightning/testing/lm_test_module.py
index 9861810e8a7f8..61ecf874f337d 100644
--- a/pytorch_lightning/testing/lm_test_module.py
+++ b/pytorch_lightning/testing/lm_test_module.py
@@ -48,11 +48,13 @@ def __build_model(self):
Layout model
:return:
"""
- self.c_d1 = nn.Linear(in_features=self.hparams.in_features, out_features=self.hparams.hidden_dim)
+ self.c_d1 = nn.Linear(in_features=self.hparams.in_features,
+ out_features=self.hparams.hidden_dim)
self.c_d1_bn = nn.BatchNorm1d(self.hparams.hidden_dim)
self.c_d1_drop = nn.Dropout(self.hparams.drop_prob)
- self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim, out_features=self.hparams.out_features)
+ self.c_d2 = nn.Linear(in_features=self.hparams.hidden_dim,
+ out_features=self.hparams.out_features)
# ---------------------
# TRAINING
@@ -191,8 +193,10 @@ def configure_optimizers(self):
def __dataloader(self, train):
# init data generators
- transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (1.0,))])
- dataset = MNIST(root=self.hparams.data_root, train=train, transform=transform, download=True)
+ transform = transforms.Compose([transforms.ToTensor(),
+ transforms.Normalize((0.5,), (1.0,))])
+ dataset = MNIST(root=self.hparams.data_root, train=train,
+ transform=transform, download=True)
# when using multi-node we need to add the datasampler
train_sampler = None
@@ -202,7 +206,7 @@ def __dataloader(self, train):
if self.on_gpu and not self.force_remove_distributed_sampler:
train_sampler = DistributedSampler(dataset, rank=self.trainer.proc_rank)
batch_size = batch_size // self.trainer.world_size # scale batch size
- except Exception as e:
+ except Exception:
pass
should_shuffle = train_sampler is None
@@ -242,19 +246,24 @@ def add_model_specific_args(parent_parser, root_dir):
# network params
parser.opt_list('--drop_prob', default=0.2, options=[0.2, 0.5], type=float, tunable=False)
- parser.add_argument('--in_features', default=28*28, type=int)
+ parser.add_argument('--in_features', default=28 * 28, type=int)
parser.add_argument('--out_features', default=10, type=int)
- parser.add_argument('--hidden_dim', default=50000, type=int) # use 500 for CPU, 50000 for GPU to see speed difference
+ # use 500 for CPU, 50000 for GPU to see speed difference
+ parser.add_argument('--hidden_dim', default=50000, type=int)
# data
parser.add_argument('--data_root', default=os.path.join(root_dir, 'mnist'), type=str)
# training params (opt)
- parser.opt_list('--learning_rate', default=0.001*8, type=float, options=[0.0001, 0.0005, 0.001, 0.005],
+ parser.opt_list('--learning_rate', default=0.001 * 8, type=float,
+ options=[0.0001, 0.0005, 0.001, 0.005],
tunable=False)
- parser.opt_list('--optimizer_name', default='adam', type=str, options=['adam'], tunable=False)
-
- # if using 2 nodes with 4 gpus each the batch size here (256) will be 256 / (2*8) = 16 per gpu
- parser.opt_list('--batch_size', default=256*8, type=int, options=[32, 64, 128, 256], tunable=False,
- help='batch size will be divided over all the gpus being used across all nodes')
+ parser.opt_list('--optimizer_name', default='adam', type=str,
+ options=['adam'], tunable=False)
+
+ # if using 2 nodes with 4 gpus each the batch size here
+ # (256) will be 256 / (2*8) = 16 per gpu
+ parser.opt_list('--batch_size', default=256 * 8, type=int,
+ options=[32, 64, 128, 256], tunable=False,
+ help='batch size will be divided over all gpus being used across all nodes')
return parser
diff --git a/pytorch_lightning/utilities/arg_parse.py b/pytorch_lightning/utilities/arg_parse.py
index f274e751c3b6d..39d4ec81f9486 100644
--- a/pytorch_lightning/utilities/arg_parse.py
+++ b/pytorch_lightning/utilities/arg_parse.py
@@ -3,32 +3,46 @@
Might need to update with the new flags
"""
+import os
+
+
def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None):
# tng, test, val check intervals
- parser.add_argument('--eval_test_set', dest='eval_test_set', action='store_true', help='true = run test set also')
- parser.add_argument('--check_val_every_n_epoch', default=1, type=int, help='check val every n epochs')
+ parser.add_argument('--eval_test_set', dest='eval_test_set', action='store_true',
+ help='true = run test set also')
+ parser.add_argument('--check_val_every_n_epoch', default=1, type=int,
+ help='check val every n epochs')
parser.opt_list('--accumulate_grad_batches', default=1, type=int, tunable=False,
- help='accumulates gradients k times before applying update. Simulates huge batch size')
+ help='accumulates gradients k times before applying update.'
+ ' Simulates huge batch size')
parser.add_argument('--max_nb_epochs', default=200, type=int, help='cap epochs')
parser.add_argument('--min_nb_epochs', default=2, type=int, help='min epochs')
- parser.add_argument('--train_percent_check', default=1.0, type=float, help='how much of tng set to check')
- parser.add_argument('--val_percent_check', default=1.0, type=float, help='how much of val set to check')
- parser.add_argument('--test_percent_check', default=1.0, type=float, help='how much of test set to check')
-
- parser.add_argument('--val_check_interval', default=0.95, type=float, help='how much within 1 epoch to check val')
- parser.add_argument('--log_save_interval', default=100, type=int, help='how many batches between log saves')
- parser.add_argument('--add_log_row_interval', default=100, type=int, help='add log every k batches')
+ parser.add_argument('--train_percent_check', default=1.0, type=float,
+ help='how much of tng set to check')
+ parser.add_argument('--val_percent_check', default=1.0, type=float,
+ help='how much of val set to check')
+ parser.add_argument('--test_percent_check', default=1.0, type=float,
+ help='how much of test set to check')
+
+ parser.add_argument('--val_check_interval', default=0.95, type=float,
+ help='how much within 1 epoch to check val')
+ parser.add_argument('--log_save_interval', default=100, type=int,
+ help='how many batches between log saves')
+ parser.add_argument('--add_log_row_interval', default=100, type=int,
+ help='add log every k batches')
# early stopping
parser.add_argument('--disable_early_stop', dest='enable_early_stop', action='store_false')
parser.add_argument('--early_stop_metric', default='val_acc', type=str)
parser.add_argument('--early_stop_mode', default='min', type=str)
- parser.add_argument('--early_stop_patience', default=3, type=int, help='number of epochs until stop')
+ parser.add_argument('--early_stop_patience', default=3, type=int,
+ help='number of epochs until stop')
# gradient handling
parser.add_argument('--gradient_clip', default=-1, type=int)
- parser.add_argument('--track_grad_norm', default=-1, type=int, help='if > 0, will track this grad norm')
+ parser.add_argument('--track_grad_norm', default=-1, type=int,
+ help='if > 0, will track this grad norm')
# model saving
parser.add_argument('--model_save_path', default=root_dir + '/model_weights')
@@ -44,7 +58,8 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
# test_tube settings
parser.add_argument('-en', '--tt_name', default='pt_test')
parser.add_argument('-td', '--tt_description', default='pytorch lightning test')
- parser.add_argument('--tt_save_path', default=root_dir + '/test_tube_logs', help='logging dir')
+ parser.add_argument('--tt_save_path', default=os.path.join(root_dir, 'test_tube_logs'),
+ help='logging dir')
parser.add_argument('--enable_single_run', dest='single_run', action='store_true')
parser.add_argument('--nb_hopt_trials', default=1, type=int)
parser.add_argument('--log_stdout', dest='log_stdout', action='store_true')
@@ -55,25 +70,30 @@ def add_default_args(parser, root_dir, rand_seed=None, possible_model_names=None
parser.add_argument('--default_tensor_type', default='torch.cuda.FloatTensor', type=str)
parser.add_argument('--use_amp', dest='use_amp', action='store_true')
parser.add_argument('--check_grad_nans', dest='check_grad_nans', action='store_true')
- parser.add_argument('--amp_level', default='O2',type=str)
-
+ parser.add_argument('--amp_level', default='O2', type=str)
# run on hpc
parser.add_argument('--on_cluster', dest='on_cluster', action='store_true')
# FAST training
# use these settings to make sure network has no bugs without running a full dataset
- parser.add_argument('--fast_dev_run', dest='fast_dev_run', default=False, action='store_true', help='runs validation after 1 tng step')
- parser.add_argument('--enable_tqdm', dest='enable_tqdm', default=False, action='store_true', help='false removes the prog bar')
- parser.add_argument('--overfit', default=-1, type=float, help='% of dataset to use with this option. float, or -1 for none')
+ parser.add_argument('--fast_dev_run', dest='fast_dev_run', default=False, action='store_true',
+ help='runs validation after 1 tng step')
+ parser.add_argument('--enable_tqdm', dest='enable_tqdm', default=False, action='store_true',
+ help='false removes the prog bar')
+ parser.add_argument('--overfit', default=-1, type=float,
+ help='% of dataset to use with this option. float, or -1 for none')
# debug args
if rand_seed is not None:
parser.add_argument('--random_seed', default=rand_seed, type=int)
- parser.add_argument('--interactive', dest='interactive', action='store_true', help='runs on gpu without cluster')
- parser.add_argument('--debug', dest='debug', action='store_true', help='enables/disables test tube')
- parser.add_argument('--local', dest='local', action='store_true', help='enables local tng')
+ parser.add_argument('--interactive', dest='interactive', action='store_true',
+ help='runs on gpu without cluster')
+ parser.add_argument('--debug', dest='debug', action='store_true',
+ help='enables/disables test tube')
+ parser.add_argument('--local', dest='local', action='store_true',
+ help='enables local tng')
# optimizer
parser.add_argument('--lr_scheduler_milestones', default=None, type=str)
diff --git a/requirements.txt b/requirements.txt
index aba573c0c6085..86c02573bf48e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,4 +3,5 @@ tqdm==4.32.1
twine==1.13.0
numpy==1.16.4
torch>=1.1.0
-torchvision==0.3.0
+torchvision>=0.3.0
+pandas
\ No newline at end of file
diff --git a/setup.py b/setup.py
index e680ef4301207..a8f0d370834cc 100755
--- a/setup.py
+++ b/setup.py
@@ -1,29 +1,55 @@
#!/usr/bin/env python
-from setuptools import setup, find_packages
+from setuptools import setup
+
+import pytorch_lightning
# https://packaging.python.org/guides/single-sourcing-package-version/
# http://blog.ionelmc.ro/2014/05/25/python-packaging/
setup(
name="pytorch-lightning",
- version='0.3.6.9',
- description="The Keras for ML researchers using PyTorch",
- author="William Falcon",
- author_email="waf2107@columbia.edu",
- url="https://github.com/williamFalcon/pytorch-lightning",
- download_url="https://github.com/williamFalcon/pytorch-lightning",
- license="MIT",
+ version=pytorch_lightning.__version__,
+ description=pytorch_lightning.__doc__,
+ author=pytorch_lightning.__author__,
+ author_email=pytorch_lightning.__author_email__,
+ url=pytorch_lightning.__homepage__,
+ license=pytorch_lightning.__license__,
+ packages=['pytorch_lightning'],
+
+ long_description=open("README.md", encoding="utf-8").read(),
+ long_description_content_type='text/markdown',
+
+ include_package_data=True,
+ zip_safe=False,
+
keywords=["deep learning", "pytorch", "AI"],
- python_requires=">=3.5",
+ python_requires=">=3.6",
install_requires=[
"torch>=1.1.0",
"tqdm",
"test-tube>=0.6.7.6",
],
- packages=find_packages(),
- long_description=open("README.md", encoding="utf-8").read(),
- long_description_content_type='text/markdown',
- include_package_data=True,
- zip_safe=False,
+
+ classifiers=[
+ 'Environment :: Console',
+ 'Natural Language :: English',
+ # How mature is this project? Common values are
+ # 3 - Alpha, 4 - Beta, 5 - Production/Stable
+ 'Development Status :: 4 - Beta',
+ # Indicate who your project is intended for
+ 'Intended Audience :: Developers',
+ 'Topic :: Scientific/Engineering :: Artificial Intelligence',
+ 'Topic :: Scientific/Engineering :: Image Recognition',
+ 'Topic :: Scientific/Engineering :: Information Analysis',
+ # Pick your license as you wish
+ 'License :: OSI Approved :: BSD License',
+ 'Operating System :: OS Independent',
+ # Specify the Python versions you support here. In particular, ensure
+ # that you indicate whether you support Python 2, Python 3 or both.
+ 'Programming Language :: Python :: 3',
+ 'Programming Language :: Python :: 3.5',
+ 'Programming Language :: Python :: 3.6',
+ 'Programming Language :: Python :: 3.7',
+ ],
)
diff --git a/tests/README.md b/tests/README.md
index a121ff14145e1..032cf04f1d2de 100644
--- a/tests/README.md
+++ b/tests/README.md
@@ -17,7 +17,7 @@ pip install -e .
pip install -r requirements.txt
# run tests
-py.test
+py.test -v
```
To test models that require GPU make sure to run the above command on a GPU machine.
@@ -50,10 +50,14 @@ cd pytorch-lightning
# generate coverage
pip install coverage
-coverage run tests/test_models.py
+coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
# print coverage stats
-coverage report -m
+coverage report -m
+
+# exporting resulys
+coverage xml
+codecov -t 17327163-8cca-4a5d-86c8-ca5f2ef700bc -v
```
diff --git a/tests/debug.py b/tests/debug.py
index 09e9186b9ccc1..6a5efbecfa2ca 100644
--- a/tests/debug.py
+++ b/tests/debug.py
@@ -61,8 +61,8 @@ def get_model():
root_dir = os.path.dirname(os.path.realpath(__file__))
hparams = Namespace(**{'drop_prob': 0.2,
'batch_size': 32,
- 'in_features': 28*28,
- 'learning_rate': 0.001*8,
+ 'in_features': 28 * 28,
+ 'learning_rate': 0.001 * 8,
'optimizer_name': 'adam',
'data_root': os.path.join(root_dir, 'mnist'),
'out_features': 10,
@@ -107,7 +107,8 @@ def load_model(exp, save_dir):
checkpoints = [x for x in os.listdir(save_dir) if '.ckpt' in x]
weights_dir = os.path.join(save_dir, checkpoints[0])
- trained_model = LightningTemplateModel.load_from_metrics(weights_path=weights_dir, tags_csv=tags_path, on_gpu=True)
+ trained_model = LightningTemplateModel.load_from_metrics(weights_path=weights_dir,
+ tags_csv=tags_path, on_gpu=True)
assert trained_model is not None, 'loading model failed'
@@ -132,7 +133,7 @@ def run_prediction(dataloader, trained_model):
print(val_acc)
- assert val_acc > 0.70, f'this model is expected to get > 0.7 in test set (it got {val_acc})'
+ assert val_acc > 0.70, 'this model is expected to get > 0.7 in test set (it got %f)' % val_acc
def main():
diff --git a/tests/requirements.txt b/tests/requirements.txt
index c16efc2add252..076bfd6500639 100644
--- a/tests/requirements.txt
+++ b/tests/requirements.txt
@@ -1,2 +1,8 @@
-coverage==4.5.3
-pytest==5.0.1
+tox
+coverage
+codecov
+pytest>=3.0.5
+pytest-cov
+flake8
+check-manifest
+test_tube
\ No newline at end of file
diff --git a/tests/test_models.py b/tests/test_models.py
index 73ba2e43c1209..cd03d8b411399 100644
--- a/tests/test_models.py
+++ b/tests/test_models.py
@@ -1,20 +1,22 @@
import os
import shutil
import warnings
+from argparse import Namespace
import pytest
import numpy as np
import torch
+from test_tube import Experiment, SlurmCluster
+
+# sys.path += [os.path.abspath('..'), os.path.abspath('../..')]
from pytorch_lightning import Trainer
-from examples import LightningTemplateModel
from pytorch_lightning.testing.lm_test_module import LightningTestModel
-from argparse import Namespace
-from test_tube import Experiment, SlurmCluster
from pytorch_lightning.callbacks import ModelCheckpoint, EarlyStopping
from pytorch_lightning.utilities.debugging import MisconfigurationException
from pytorch_lightning.root_module import memory
from pytorch_lightning.models.trainer import reduce_distributed_output
from pytorch_lightning.root_module import model_saving
+from examples import LightningTemplateModel
SEED = 2334
torch.manual_seed(SEED)
@@ -30,10 +32,12 @@ def test_amp_gpu_ddp():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_amp_gpu_ddp cannot run.'
+ 'Rerun on a GPU node to run this test')
return
if not torch.cuda.device_count() > 1:
- warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a node with 2+ GPUs to run this test')
+ warnings.warn('test_amp_gpu_ddp cannot run.'
+ 'Rerun on a node with 2+ GPUs to run this test')
return
os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
@@ -105,7 +109,8 @@ def test_cpu_slurm_save_load():
# wipe-out trainer and model
# retrain with not much data... this simulates picking training back up after slurm
# we want to see if the weights come back correctly
- continue_tng_hparams = get_hparams(continue_training=True, hpc_exp_number=cluster_a.hpc_exp_number)
+ continue_tng_hparams = get_hparams(continue_training=True,
+ hpc_exp_number=cluster_a.hpc_exp_number)
trainer_options = dict(
max_nb_epochs=1,
cluster=SlurmCluster(continue_tng_hparams),
@@ -136,11 +141,9 @@ def assert_pred_same():
def test_loading_meta_tags():
hparams = get_hparams()
- save_dir = init_save_dir()
-
# save tags
exp = get_exp(False)
- exp.tag({'some_str':'a_str', 'an_int': 1, 'a_float': 2.0})
+ exp.tag({'some_str': 'a_str', 'an_int': 1, 'a_float': 2.0})
exp.argparse(hparams)
exp.save()
@@ -221,7 +224,8 @@ def test_model_saving_loading():
# load new model
tags_path = exp.get_data_path(exp.name, exp.version)
tags_path = os.path.join(tags_path, 'meta_tags.csv')
- model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path, tags_csv=tags_path, on_gpu=False)
+ model_2 = LightningTestModel.load_from_metrics(weights_path=new_weights_path,
+ tags_csv=tags_path, on_gpu=False)
model_2.eval()
# make prediction
@@ -246,10 +250,12 @@ def test_amp_gpu_ddp_slurm_managed():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_amp_gpu_ddp cannot run.'
+ ' Rerun on a GPU node to run this test')
return
if not torch.cuda.device_count() > 1:
- warnings.warn('test_amp_gpu_ddp cannot run. Rerun on a node with 2+ GPUs to run this test')
+ warnings.warn('test_amp_gpu_ddp cannot run.'
+ ' Rerun on a node with 2+ GPUs to run this test')
return
# simulate setting slurm flags
@@ -413,7 +419,8 @@ def test_single_gpu_model():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_single_gpu_model cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_single_gpu_model cannot run.'
+ ' Rerun on a GPU node to run this test')
return
model, hparams = get_model()
@@ -434,10 +441,12 @@ def test_multi_gpu_model_dp():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_multi_gpu_model_dp cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_multi_gpu_model_dp cannot run.'
+ ' Rerun on a GPU node to run this test')
return
if not torch.cuda.device_count() > 1:
- warnings.warn('test_multi_gpu_model_dp cannot run. Rerun on a node with 2+ GPUs to run this test')
+ warnings.warn('test_multi_gpu_model_dp cannot run.'
+ ' Rerun on a node with 2+ GPUs to run this test')
return
model, hparams = get_model()
trainer_options = dict(
@@ -460,10 +469,12 @@ def test_amp_gpu_dp():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_amp_gpu_dp cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_amp_gpu_dp cannot run.'
+ ' Rerun on a GPU node to run this test')
return
if not torch.cuda.device_count() > 1:
- warnings.warn('test_amp_gpu_dp cannot run. Rerun on a node with 2+ GPUs to run this test')
+ warnings.warn('test_amp_gpu_dp cannot run.'
+ ' Rerun on a node with 2+ GPUs to run this test')
return
model, hparams = get_model()
trainer_options = dict(
@@ -482,10 +493,12 @@ def test_multi_gpu_model_ddp():
:return:
"""
if not torch.cuda.is_available():
- warnings.warn('test_multi_gpu_model_ddp cannot run. Rerun on a GPU node to run this test')
+ warnings.warn('test_multi_gpu_model_ddp cannot run.'
+ ' Rerun on a GPU node to run this test')
return
if not torch.cuda.device_count() > 1:
- warnings.warn('test_multi_gpu_model_ddp cannot run. Rerun on a node with 2+ GPUs to run this test')
+ warnings.warn('test_multi_gpu_model_ddp cannot run.'
+ ' Rerun on a node with 2+ GPUs to run this test')
return
os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
@@ -502,7 +515,6 @@ def test_multi_gpu_model_ddp():
run_gpu_model_test(trainer_options, model, hparams)
-
def test_ddp_sampler_error():
"""
Make sure DDP + AMP work
@@ -587,8 +599,8 @@ def get_hparams(continue_training=False, hpc_exp_number=0):
args = {
'drop_prob': 0.2,
'batch_size': 32,
- 'in_features': 28*28,
- 'learning_rate': 0.001*8,
+ 'in_features': 28 * 28,
+ 'learning_rate': 0.001 * 8,
'optimizer_name': 'adam',
'data_root': os.path.join(root_dir, 'mnist'),
'out_features': 10,
@@ -673,13 +685,13 @@ def run_prediction(dataloader, trained_model):
print(val_acc)
- assert val_acc > 0.50, f'this model is expected to get > 0.50 in test set (it got {val_acc})'
+ assert val_acc > 0.50, 'this model is expected to get > 0.50 in test set (it got %f)' % val_acc
def assert_ok_acc(trainer):
# this model should get 0.80+ acc
acc = trainer.tng_tqdm_dic['val_acc']
- assert acc > 0.50, f'model failed to get expected 0.50 validation accuracy. Got: {acc}'
+ assert acc > 0.50, 'model failed to get expected 0.50 validation accuracy. Got: %f' % acc
if __name__ == '__main__':
diff --git a/tox.ini b/tox.ini
new file mode 100644
index 0000000000000..a91ac5efce9d5
--- /dev/null
+++ b/tox.ini
@@ -0,0 +1,47 @@
+# this file is *not* meant to cover or endorse the use of tox or pytest or testing in general,
+#
+# It's meant to show the use of:
+#
+# - check-manifest
+# confirm items checked into vcs are in your segdist
+# - python setup.py check
+# confirm required package meta-data in setup.py
+# - readme_renderer (when using a ReStructuredText README)
+# confirms your long_description will render correctly on PyPI.
+#
+# and also to help confirm pull requests to this project.
+
+[tox]
+envlist = py{35,36,37}
+
+[pytest]
+log_cli = 0
+log_cli_level = CRITICAL
+log_cli_format = %(message)s
+log_file = pytest.log
+log_file_level = DEBUG
+log_file_format = %(asctime)s [%(levelname)8s] %(message)s (%(filename)s:%(lineno)s)
+log_file_date_format=%Y-%m-%d %H:%M:%S
+
+[testenv]
+basepython =
+ py35: python3.5
+ py36: python3.6
+ py37: python3.7
+deps =
+ -r requirements.txt
+ -r ./tests/requirements.txt
+commands =
+ check-manifest --ignore tox.ini
+ python setup.py check -m -s
+ coverage run --source pytorch_lightning -m py.test pytorch_lightning tests examples -v --doctest-modules
+ flake8 .
+
+[flake8]
+exclude = .tox,*.egg,build,temp
+select = E,W,F
+doctests = True
+verbose = 2
+# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
+format = pylint
+max-line-length = 100
diff --git a/update.sh b/update.sh
index 4eaf1149d083f..40fcc22d6b79b 100644
--- a/update.sh
+++ b/update.sh
@@ -11,10 +11,7 @@ rm -rf ./dist/*
python3 setup.py sdist
twine upload dist/*
-
-
# to update docs
# cd to root dir
# mkdocs gh-deploy
-
-
-
- 
- 
- 
- 
-
-
-
-
-
-
-