def test_initializers_1(): wide = Wide(100, 1) deepdense = DeepDense(hidden_layers=[32,16], dropout=[0.5, 0.5], deep_column_idx=deep_column_idx, embed_input=embed_input, continuous_cols=colnames[-5:]) deeptext = DeepText( vocab_size=vocab_size, embed_dim=32, padding_idx=0) deepimage=DeepImage(pretrained=True) model = WideDeep(wide=wide, deepdense=deepdense, deeptext=deeptext, deepimage=deepimage, output_dim=1) cmodel = c(model) org_weights = [] for n,p in cmodel.named_parameters(): if n in test_layers_1: org_weights.append(p) model.compile(method='binary', verbose=0, initializers=initializers_1) init_weights = [] for n,p in model.named_parameters(): if n in test_layers_1: init_weights.append(p) res = all([torch.all((1-(a==b).int()).bool()) for a,b in zip(org_weights, init_weights)]) assert res
def test_initializers_1(initializers, test_layers):
wide = Wide(np.unique(X_wide).shape[0], 1)
deeptabular = TabMlp(
mlp_hidden_dims=[32, 16],
mlp_dropout=[0.5, 0.5],
column_idx=column_idx,
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
deeptext = DeepText(vocab_size=vocab_size, embed_dim=32, padding_idx=0)
deepimage = DeepImage(pretrained=True)
model = WideDeep(
wide=wide,
deeptabular=deeptabular,
deeptext=deeptext,
deepimage=deepimage,
pred_dim=1,
)
cmodel = c(model)
org_weights = []
for n, p in cmodel.named_parameters():
if n in test_layers:
org_weights.append(p)
trainer = Trainer(model,
objective="binary",
verbose=0,
initializers=initializers)
init_weights = []
for n, p in trainer.model.named_parameters():
if n in test_layers:
init_weights.append(p)
res = all([
torch.all((1 - (a == b).int()).bool())
for a, b in zip(org_weights, init_weights)
])
assert res
# deepdense = TabResnet(
# blocks_dims=[64, 32],
# dropout=0.2,
# column_idx=tab_preprocessor.column_idx,
# embed_input=tab_preprocessor.embeddings_input,
# continuous_cols=continuous_cols,
# )
deeptext = DeepText(
vocab_size=len(text_processor.vocab.itos),
hidden_dim=64,
n_layers=3,
rnn_dropout=0.5,
padding_idx=1,
embed_matrix=text_processor.embedding_matrix,
)
deepimage = DeepImage(pretrained=True, head_hidden_dims=None)
model = WideDeep(wide=wide,
deeptabular=deepdense,
deeptext=deeptext,
deepimage=deepimage)
wide_opt = torch.optim.Adam(model.wide.parameters(), lr=0.01)
deep_opt = torch.optim.Adam(model.deeptabular.parameters())
text_opt = RAdam(model.deeptext.parameters())
img_opt = RAdam(model.deepimage.parameters())
wide_sch = torch.optim.lr_scheduler.StepLR(wide_opt, step_size=5)
deep_sch = torch.optim.lr_scheduler.StepLR(deep_opt, step_size=3)
text_sch = torch.optim.lr_scheduler.StepLR(text_opt, step_size=5)
img_sch = torch.optim.lr_scheduler.StepLR(img_opt, step_size=3)
deepdense = DeepDense(
hidden_layers=[64, 32],
dropout=[0.2, 0.2],
deep_column_idx=prepare_deep.deep_column_idx,
embed_input=prepare_deep.embeddings_input,
continuous_cols=continuous_cols,
)
deeptext = DeepText(
vocab_size=len(text_processor.vocab.itos),
hidden_dim=64,
n_layers=3,
rnn_dropout=0.5,
padding_idx=1,
embedding_matrix=text_processor.embedding_matrix,
)
deepimage = DeepImage(pretrained=True, head_layers=None)
model = WideDeep(wide=wide,
deepdense=deepdense,
deeptext=deeptext,
deepimage=deepimage)
wide_opt = torch.optim.Adam(model.wide.parameters(), lr=0.01)
deep_opt = torch.optim.Adam(model.deepdense.parameters())
text_opt = RAdam(model.deeptext.parameters())
img_opt = RAdam(model.deepimage.parameters())
wide_sch = torch.optim.lr_scheduler.StepLR(wide_opt, step_size=5)
deep_sch = torch.optim.lr_scheduler.StepLR(deep_opt, step_size=3)
text_sch = torch.optim.lr_scheduler.StepLR(text_opt, step_size=5)
img_sch = torch.optim.lr_scheduler.StepLR(img_opt, step_size=3)
y_train,
y_val,
) = train_test_split(X_wide, X_deep, X_text, X_img, target)
# build model components
wide = Wide(np.unique(X_wide).shape[0], 1)
deepdense = DeepDense(
hidden_layers=[32, 16],
dropout=[0.5, 0.5],
deep_column_idx={k: v
for v, k in enumerate(colnames)},
embed_input=embed_input,
continuous_cols=colnames[-5:],
)
deeptext = DeepText(vocab_size=vocab_size, embed_dim=32, padding_idx=0)
deepimage = DeepImage(pretrained=True)
# transforms
mean = [0.406, 0.456, 0.485] # BGR
std = [0.225, 0.224, 0.229] # BGR
transforms1 = [ToTensor, Normalize(mean=mean, std=std)]
transforms2 = [Normalize(mean=mean, std=std)]
##############################################################################
# Test many possible scenarios of data inputs I can think off. Surely users
# will input something unexpected
##############################################################################
@pytest.mark.parametrize(
"X_wide, X_deep, X_text, X_img, X_train, X_val, target, val_split, transforms, nepoch, null",
[
import numpy as np
import torch
import pytest
from pytorch_widedeep.models import DeepImage
X_images = (torch.from_numpy(np.random.rand(10, 3, 224, 224))).float()
###############################################################################
# Simply testing that it runs with the defaults
###############################################################################
model1 = DeepImage()
def test_deep_image():
out = model1(X_images)
assert out.size(0) == 10 and out.size(1) == 512
###############################################################################
# Testing with custome backbone
###############################################################################
model2 = DeepImage(pretrained=False)
def test_deep_image_custom_backbone():
out = model2(X_images)
assert out.size(0) == 10 and out.size(1) == 512
###############################################################################
Wide,
DeepText,
WideDeep,
DeepDense,
DeepImage,
)
embed_input = [(u, i, j)
for u, i, j in zip(["a", "b", "c"][:4], [4] * 3, [8] * 3)]
deep_column_idx = {k: v for v, k in enumerate(["a", "b", "c"])}
wide = Wide(10, 1)
deepdense = DeepDense(hidden_layers=[16, 8],
deep_column_idx=deep_column_idx,
embed_input=embed_input)
deeptext = DeepText(vocab_size=100, embed_dim=8)
deepimage = DeepImage(pretrained=False)
###############################################################################
# test raising 'output dim errors'
###############################################################################
@pytest.mark.parametrize(
"deepcomponent, component_name",
[
(None, "dense"),
(deeptext, "text"),
(deepimage, "image"),
],
)
def test_history_callback(deepcomponent, component_name):
def test_too_cold():
with pytest.raises(ValueError):
mod = DeepImage(freeze_n=10) # noqa: F841
import numpy as np
import torch
import pytest
from pytorch_widedeep.models import DeepImage
X_images = (torch.from_numpy(np.random.rand(10, 3, 224, 224))).float()
###############################################################################
# Simply testing that it runs with the defaults
###############################################################################
model1 = DeepImage()
def test_deep_image_1():
out = model1(X_images)
assert out.size(0) == 10 and out.size(1) == 512
###############################################################################
# Testing with 'custom' backbone
###############################################################################
model2 = DeepImage(pretrained=False)
def test_deep_image_custom_backbone():
out = model2(X_images)
assert out.size(0) == 10 and out.size(1) == 512
###############################################################################