def create_and_check_model(self, config, pixel_values, labels): model = SwinModel(config=config) model.to(torch_device) model.eval() result = model(pixel_values) num_features = int(config.embed_dim * 2**(len(config.depths) - 1)) self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, num_features))
def create_and_check_model(self, config, pixel_values, labels): model = SwinModel(config=config) model.to(torch_device) model.eval() result = model(pixel_values) expected_seq_len = ((config.image_size // config.patch_size) ** 2) // (4 ** (len(config.depths) - 1)) expected_dim = int(config.embed_dim * 2 ** (len(config.depths) - 1)) self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, expected_seq_len, expected_dim))
def create_and_check_model(self, config, pixel_values, labels): model = SwinModel(config=config) model.to(torch_device) model.eval() result = model(pixel_values) # since the model we're testing only consists of a single layer, expected_seq_len = number of patches expected_seq_len = (config.image_size // config.patch_size) ** 2 expected_dim = int(config.embed_dim * 2 ** (len(config.depths) - 1)) self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, expected_seq_len, expected_dim))
def test_model_from_pretrained(self): for model_name in SWIN_PRETRAINED_MODEL_ARCHIVE_LIST[:1]: model = SwinModel.from_pretrained(model_name) self.assertIsNotNone(model)
def get_encoder_decoder_model(self, config, decoder_config): encoder_model = SwinModel(config).eval() decoder_model = BartForCausalLM(decoder_config).eval() return encoder_model, decoder_model