SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fixing model

Browse Source
This commit is contained in:
thomwolf
2018-11-03 03:11:13 +01:00
parent 38f740a1d5
commit 8aa22af0c5
3 changed files with 278 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
extract_features_pytorch.py
View File

@@ -268,29 +268,31 @@ def main():
input_mask = input_mask.float().to(device)
all_encoder_layers, _ = model(input_ids, token_type_ids=None, attention_mask=input_mask)
all_encoder_layers = all_encoder_layers
for enc_layers, example_index in zip(all_encoder_layers, example_indices):
for b, example_index in enumerate(example_indices):
feature = features[example_index.item()]
unique_id = int(feature.unique_id)
# feature = unique_id_to_feature[unique_id]
output_json = collections.OrderedDict()
output_json["linex_index"] = unique_id
all_features = []
all_out_features = []
for (i, token) in enumerate(feature.tokens):
all_layers = []
for (j, layer_index) in enumerate(layer_indexes):
layer_output = enc_layers[int(layer_index)].detach().cpu().numpy()
layer_output = all_encoder_layers[int(layer_index)].detach().cpu().numpy()
layer_output = layer_output[b]
layers = collections.OrderedDict()
layers["index"] = layer_index
layers["values"] = [
round(float(x), 6) for x in layer_output[i:(i + 1)].flat
round(x.item(), 6) for x in layer_output[i]
]
all_layers.append(layers)
features = collections.OrderedDict()
features["token"] = token
features["layers"] = all_layers
all_features.append(features)
output_json["features"] = all_features
out_features = collections.OrderedDict()
out_features["token"] = token
out_features["layers"] = all_layers
all_out_features.append(out_features)
output_json["features"] = all_out_features
writer.write(json.dumps(output_json) + "\n")