def test_initializers_with_pattern(): 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) model = WideDeep(wide=wide, deepdense=deepdense, deeptext=deeptext, pred_dim=1) cmodel = c(model) org_word_embed = [] for n, p in cmodel.named_parameters(): if "word_embed" in n: org_word_embed.append(p) model.compile(method="binary", verbose=0, initializers=initializers_2) init_word_embed = [] for n, p in model.named_parameters(): if "word_embed" in n: init_word_embed.append(p) assert torch.all(org_word_embed[0] == init_word_embed[0].cpu())
def test_no_deephead_and_head_layers(): out = [] model = WideDeep(wide=wide, deepdense=deepdense, head_layers=[8, 4]) # noqa: F841 for n, p in model.named_parameters(): if n == "deephead.head_layer_0.0.weight": out.append(p.size(0) == 8 and p.size(1) == 8) if n == "deephead.head_layer_1.0.weight": out.append(p.size(0) == 4 and p.size(1) == 8) assert all(out)
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