add instructions for downloading coco

coco_dataset/download_coco.txt

@@ -0,0 +1,12 @@
+mkdir data
+cd data
+wget http://images.cocodataset.org/zips/train2017.zip
+wget http://images.cocodataset.org/zips/val2017.zip
+wget http://images.cocodataset.org/zips/test2017.zip
+wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip
+wget http://images.cocodataset.org/annotations/image_info_test2017.zip
+unzip train2017.zip
+unzip val2017.zip
+unzip test2017.zip
+unzip annotations_trainval2017.zip
+unzip image_info_test2017.zip

usage_example.txt

@@ -1,3 +1,5 @@
 python3 run_image_captioning_flax.py --dataset_name ./coco_dataset/coco_dataset.py --dataset_config_name=2017 --data_dir ./coco_dataset/dummy_data/ --caption_column caption --image_column image_path --max_target_length 8 --num_beams 2 --output_dir debug --do_train --per_device_train_batch_size 2 --do_eval --per_device_eval_batch_size 4 --do_predict --max_train_samples 16 --max_eval_samples 16 --max_predict_samples 16 --preprocessing_num_workers 2 --num_train_epochs 3 --learning_rate 3e-5 --do_predict_after_evaluation --predict_with_generate --logging_steps 2 --block_size 8 --encoder_model_name_or_path ./encoder-decoder/encoder/ --decoder_model_name_or_path ./encoder-decoder/decoder/
 
+python3 run_image_captioning_flax.py --dataset_name ./coco_dataset/coco_dataset.py --dataset_config_name=2017 --data_dir ./coco_dataset/data/ --caption_column caption --image_column image_path --max_target_length 8 --num_beams 2 --output_dir debug --do_train --per_device_train_batch_size 2 --do_eval --per_device_eval_batch_size 4 --do_predict --max_train_samples 16 --max_eval_samples 16 --max_predict_samples 16 --preprocessing_num_workers 2 --num_train_epochs 3 --learning_rate 3e-5 --do_predict_after_evaluation --predict_with_generate --logging_steps 2 --block_size 8 --encoder_model_name_or_path ./encoder-decoder/encoder/ --decoder_model_name_or_path ./encoder-decoder/decoder/
+
 python3 run_image_captioning_flax.py --dataset_name ./image_caption_dataset/image_caption_dataset.py --dataset_config_name=coco_2017 --data_dir ./image_caption_dataset/coco_dataset/ --caption_column en --image_column image_path --max_target_length 8 --num_beams 2 --output_dir debug --do_train --per_device_train_batch_size 2 --do_eval --per_device_eval_batch_size 4 --do_predict --max_train_samples 16 --max_eval_samples 16 --max_predict_samples 16 --preprocessing_num_workers 2 --num_train_epochs 3 --learning_rate 3e-5 --do_predict_after_evaluation --predict_with_generate --logging_steps 2 --block_size 8 --encoder_model_name_or_path ./encoder-decoder/encoder/ --decoder_model_name_or_path ./encoder-decoder/decoder