def create_and_check_model(self, config, pixel_values):
model = CLIPVisionModel(config=config)
model.to(torch_device)
model.eval()
result = model(pixel_values)
# expected sequence length = num_patches + 1 (we add 1 for the [CLS] token)
image_size = (self.image_size, self.image_size)
patch_size = (self.patch_size, self.patch_size)
num_patches = (image_size[1] // patch_size[1]) * (image_size[0] // patch_size[0])
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, num_patches + 1, self.hidden_size))
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
def get_vision_text_model(self, vision_config, text_config):
vision_model = CLIPVisionModel(vision_config).eval()
text_model = BertModel(text_config).eval()
return vision_model, text_model
def test_model_from_pretrained(self):
for model_name in CLIP_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = CLIPVisionModel.from_pretrained(model_name)
self.assertIsNotNone(model)