diff --git a/finetune/dataset.py b/finetune/dataset.py index 1904b3f..38d05d4 100644 --- a/finetune/dataset.py +++ b/finetune/dataset.py @@ -329,7 +329,7 @@ def preprocess( for j in range(len(patches[0])): images.append(patches[i][j]) if use_image_id: - image_placeholder = f'{tokenizer.im_id_start}{idx}{tokenizer.im_id_end}' + image_placeholder + image_placeholder = f'{tokenizer.im_id_start}{image_id_cnt}{tokenizer.im_id_end}' + image_placeholder image_id_cnt += 1 image_placeholder += get_grid_placeholder( tokenizer, best_grid, query_nums, new_schema = new_schema) @@ -518,4 +518,4 @@ def reshape_by_patch(image_tensor, patch_size): patches = patches.reshape(image_tensor.size(0), patch_size, patch_size, -1) patches = patches.permute(0, 1, 3, 2).reshape( image_tensor.size(0), patch_size, -1) - return patches \ No newline at end of file + return patches