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

add sdpa to ViT [follow up of #29325] (#30555)

Browse Source 
remove blank line (+1 squashed commit)
Squashed commits:
[24ccd2061] [run-slow]vit_msn,vision_encoder_decoder (+24 squashed commits)
Squashed commits:
[08bd27e7a] [run-slow]vit_msn,vision_encoder_decoder
[ec96a8db3] [run-slow]vit_msn
[ead817eca] fix vit msn multi gpu
[d12cdc8fd] [run-slow]audio_spectrogram_transformer,deit,vision_encoder_decoder,vision_text_dual_encoder,vit,vit_hybrid,vit_mae,vit_msn,videomae,yolos
[3fdbfa88f] doc
[a3ff33e4a] finish implementation
[e20b7b7fb] Update test_modeling_common.py
[e290c5810] Update test_modeling_flax_common.py
[d3af86f46] comment
[ff7dd32d8] more comments
[59b137889] suggestion
[7e2ba6d67] attn_implementation as attribute of the class
[fe66ab71f] minor
[38642b568] Apply suggestions from code review

Accept comments

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[22cde7d52] Update tests/test_modeling_common.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[48e137cc6] Update tests/test_modeling_common.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[99f4c679f] Update tests/test_modeling_common.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[96cf20a6d] Update src/transformers/models/vit_msn/modeling_vit_msn.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[c59377d23] Update src/transformers/models/vit_mae/modeling_vit_mae.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[b70a47259] Update tests/models/vision_text_dual_encoder/test_modeling_vision_text_dual_encoder.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
[00c84d216] [run-slow]audio_spectrogram_transformer,deit,vision_encoder_decoder,vision_text_dual_encoder,vit,vit_hybrid,vit_mae,vit_msn,videomae,yolos
[61f00ebb0] all tests are passing locally
[e9e0b82b7] vision encoder/decoder
[4d5076b56] test-vision (+20 squashed commits)
Squashed commits:
[d1add8db9] yolo
[9fde65716] fix flax
[986566c28] minor
[ca2f21d1f] vit
[3333efd7a] easy models change
[ebfc21402] [run-slow]audio_spectrogram_transformer,deit,vision_encoder_decoder,vision_text_dual_encoder,vit,vit_hybrid,vit_mae,vit_msn,videomae,yolos
[b8b8603ed] [run-slow]vision_encoder_decoder,vision_text_dual_encoder,yolos
[48ecc7e26] all tests are passing locally
[bff7fc366] minor
[62f88306f] fix yolo and text_encoder tests
[121507555] [run-slow]audio_spectrogram_transformer,deit,vit,vit_hybrid,vit_mae,vit_msn,videomae
[1064cae0a] [run-slow]vision_encoder_decoder,vision_text_dual_encoder,yolos
[b7f52ff3a] [run-slow]audio_spectrogram_transformer,deit,vit,vit_hybrid,vit_mae,vit_msn,videomae
[cffaa10dd] fix-copies
[ef6c511c4] test vit hybrid
[7d4ba8644] vit hybrid
[66f919033] [run-slow]audio_spectrogram_transformer,deit,vit,vit_hybrid,vit_mae,vit_msn,videomae
[1fcc0a031] fixes
[cfde6eb21] fixup
[e77df1ed3] all except yolo end encoder decoder (+17 squashed commits)
Squashed commits:
[602913e22] vit + vit_mae are working
[547f6c4cc] RUN_SLOW=1 pytest tests/models/audio_spectrogram_transformer/ tests/models/deit/ tests/models/videomae/  passes
[61a97dfa9] it s the complete opposite...
[aefab37d4] fix more tests
[71802a1b9] fix all torch tests
[40b12eb58] encoder - decoder tests
[941552b69] slow decorator where appropriate
[14d055d80] has_attentions to yolo and msn
[3381fa19f] add correct name
[e261316a7] repo consistency
[31c6d0c08] fixup
[9d214276c] minor fix
[11ed2e1b7] chore
[eca6644c4] add sdpa to vit-based models
[cffbf390b] make fix-copies result
[6468319b0] fix style
[d324cd02a] add sdpa for vit

Co-authored-by: Liubov Yaronskaya <luba.yaronskaya@gmail.com>
This commit is contained in:
hyenal
2024-05-16 10:56:11 +01:00
committed by GitHub
parent 9fd606dbdb
commit 1c21f48a50
34 changed files with 709 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/models/vit/test_modeling_flax_vit.py
View File

@@ -49,6 +49,7 @@ class FlaxViTModelTester(unittest.TestCase):
attention_probs_dropout_prob=0.1,
type_sequence_label_size=10,
initializer_range=0.02,
attn_implementation="eager",
):
self.parent = parent
self.batch_size = batch_size
@@ -66,6 +67,7 @@ class FlaxViTModelTester(unittest.TestCase):
self.attention_probs_dropout_prob = attention_probs_dropout_prob
self.type_sequence_label_size = type_sequence_label_size
self.initializer_range = initializer_range
self.attn_implementation = attn_implementation
# in ViT, the seq length equals the number of patches + 1 (we add 1 for the [CLS] token)
num_patches = (image_size // patch_size) ** 2
@@ -87,6 +89,7 @@ class FlaxViTModelTester(unittest.TestCase):
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
is_decoder=False,
initializer_range=self.initializer_range,
attn_implementation=self.attn_implementation,
)
return config, pixel_values

3
tests/models/vit/test_modeling_tf_vit.py
View File

@@ -63,6 +63,7 @@ class TFViTModelTester:
initializer_range=0.02,
num_labels=3,
scope=None,
attn_implementation="eager",
):
self.parent = parent
self.batch_size = batch_size
@@ -81,6 +82,7 @@ class TFViTModelTester:
self.type_sequence_label_size = type_sequence_label_size
self.initializer_range = initializer_range
self.scope = scope
self.attn_implementation = attn_implementation
# in ViT, the seq length equals the number of patches + 1 (we add 1 for the [CLS] token)
num_patches = (image_size // patch_size) ** 2
@@ -111,6 +113,7 @@ class TFViTModelTester:
attention_probs_dropout_prob=self.attention_probs_dropout_prob,
is_decoder=False,
initializer_range=self.initializer_range,
attn_implementation=self.attn_implementation,
)
def create_and_check_model(self, config, pixel_values, labels):

7
tests/models/vit/test_modeling_vit.py
View File

@@ -68,6 +68,8 @@ class ViTModelTester:
initializer_range=0.02,
scope=None,
encoder_stride=2,
mask_ratio=0.5,
attn_implementation="eager",
):
self.parent = parent
self.batch_size = batch_size
@@ -87,10 +89,14 @@ class ViTModelTester:
self.initializer_range = initializer_range
self.scope = scope
self.encoder_stride = encoder_stride
self.attn_implementation = attn_implementation
# in ViT, the seq length equals the number of patches + 1 (we add 1 for the [CLS] token)
num_patches = (image_size // patch_size) ** 2
self.seq_length = num_patches + 1
self.mask_ratio = mask_ratio
self.num_masks = int(mask_ratio * self.seq_length)
self.mask_length = num_patches
def prepare_config_and_inputs(self):
pixel_values = floats_tensor([self.batch_size, self.num_channels, self.image_size, self.image_size])
@@ -118,6 +124,7 @@ class ViTModelTester:
is_decoder=False,
initializer_range=self.initializer_range,
encoder_stride=self.encoder_stride,
attn_implementation=self.attn_implementation,
)
def create_and_check_model(self, config, pixel_values, labels):