def test_from_csv(tmpdir):
csv_path = csv_data(tmpdir)
dm = TextClassificationData.from_files(backbone=TEST_BACKBONE,
train_file=csv_path,
input="sentence",
target="label",
batch_size=1)
batch = next(iter(dm.train_dataloader()))
assert batch["labels"].item() in [0, 1]
assert "input_ids" in batch
def test_from_csv(tmpdir):
if os.name == "nt":
# TODO: huggingface stuff timing out on windows
return True
csv_path = csv_data(tmpdir)
dm = TextClassificationData.from_files(backbone=TEST_BACKBONE,
train_file=csv_path,
input="sentence",
target="label",
batch_size=1)
batch = next(iter(dm.train_dataloader()))
assert batch["labels"].item() in [0, 1]
assert "input_ids" in batch
def test_classification(tmpdir):
csv_path = csv_data(tmpdir)
data = TextClassificationData.from_files(
backbone=TEST_BACKBONE,
train_file=csv_path,
input="sentence",
target="label",
num_workers=0,
batch_size=2,
)
model = TextClassifier(2, TEST_BACKBONE)
trainer = Trainer(default_root_dir=tmpdir, fast_dev_run=True)
trainer.fit(model, datamodule=data)
def test_classification(tmpdir):
if os.name == "nt":
# TODO: huggingface stuff timing out on windows
return True
csv_path = csv_data(tmpdir)
data = TextClassificationData.from_files(
backbone=TEST_BACKBONE,
train_file=csv_path,
input="sentence",
target="label",
num_workers=0,
batch_size=2,
)
model = TextClassifier(2, TEST_BACKBONE)
trainer = Trainer(default_root_dir=tmpdir, fast_dev_run=True)
trainer.fit(model, datamodule=data)
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from flash.text import TextClassificationData, TextClassifier
# 1. Download the data
download_data("https://pl-flash-data.s3.amazonaws.com/imdb.zip", 'data/')
# 2. Load the data
datamodule = TextClassificationData.from_files(
train_file="data/imdb/train.csv",
valid_file="data/imdb/valid.csv",
test_file="data/imdb/test.csv",
input="review",
target="sentiment",
batch_size=512
)
# 3. Build the model
model = TextClassifier(num_classes=datamodule.num_classes)
# 4. Create the trainer. Run once on data
trainer = flash.Trainer(max_epochs=1)
# 5. Fine-tune the model
trainer.finetune(model, datamodule=datamodule, strategy='freeze')
# 6. Test model
trainer.test()
