riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Segformer TF: fix output size in documentation (#18572)

Browse Source 
* Segformer TF: fix output size in doc

* Segformer pytorch: fix output size in doc

Co-authored-by: Maxime Gardoni <maxime.gardoni@ecorobotix.com>
This commit is contained in:
Maxime G 2022-08-11 10:59:37 +02:00 committed by GitHub
parent 051311ff66
commit 76568d24b6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/models/segformer/modeling_segformer.py
View File

@ -784,7 +784,7 @@ class SegformerForSemanticSegmentation(SegformerPreTrainedModel):
>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits # shape (batch_size, num_labels, height, width)
>>> logits = outputs.logits # shape (batch_size, num_labels, height/4, width/4)
>>> list(logits.shape)
[1, 150, 128, 128]
```"""

2
src/transformers/models/segformer/modeling_tf_segformer.py
View File

@ -847,7 +847,7 @@ class TFSegformerForSemanticSegmentation(TFSegformerPreTrainedModel):
>>> inputs = feature_extractor(images=image, return_tensors="tf")
>>> outputs = model(**inputs, training=False)
>>> # logits are of shape (batch_size, num_labels, height, width)
>>> # logits are of shape (batch_size, num_labels, height/4, width/4)
>>> logits = outputs.logits
>>> list(logits.shape)
[1, 150, 128, 128]