(self, video_file)
| 355 | |
| 356 | @torch.no_grad() |
| 357 | def get_video_embedding(self, video_file): |
| 358 | pixel_values = load_video(video_file) |
| 359 | TC, H, W = pixel_values.shape |
| 360 | pixel_values = pixel_values.reshape(TC // 3, 3, H, W).transpose(0, 1) # [C, T, H, W] |
| 361 | pixel_values = pixel_values.unsqueeze(0).to(self.device, dtype=self.dtype) |
| 362 | assert len(pixel_values.shape) == 5 |
| 363 | language_model_inputs = self.model.extract_feature(pixel_values) |
| 364 | return language_model_inputs |
| 365 | |
| 366 | @torch.no_grad() |
| 367 | def answer(self, conversations, language_model_inputs, modal_type="image"): |
no test coverage detected