MIP: step 7: move train, eval script to tools.

Author: ruotianluo

README.md

@@ -39,13 +39,13 @@ We now support both flickr30k and COCO. See details in [data/README.md](data/REA
 ### Start training
 
 ```bash
-$ python train.py --id fc --caption_model newfc --input_json data/cocotalk.json --input_fc_dir data/cocotalk_fc --input_att_dir data/cocotalk_att --input_label_h5 data/cocotalk_label.h5 --batch_size 10 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 0 --checkpoint_path log_fc --save_checkpoint_every 6000 --val_images_use 5000 --max_epochs 30
+$ python tools/train.py --id fc --caption_model newfc --input_json data/cocotalk.json --input_fc_dir data/cocotalk_fc --input_att_dir data/cocotalk_att --input_label_h5 data/cocotalk_label.h5 --batch_size 10 --learning_rate 5e-4 --learning_rate_decay_start 0 --scheduled_sampling_start 0 --checkpoint_path log_fc --save_checkpoint_every 6000 --val_images_use 5000 --max_epochs 30
 ```
 
 or 
 
 ```bash
-$ python train.py --cfg configs/fc.yml --id fc
+$ python tools/train.py --cfg configs/fc.yml --id fc
 ```
 
 The train script will dump checkpoints into the folder specified by `--checkpoint_path` (default = `log_$id/`). By default only save the best-performing checkpoint on validation and the latest checkpoint to save disk space. You can also set `--save_history_ckpt` to 1 to save every checkpoint.
@@ -78,12 +78,12 @@ $ bash scripts/copy_model.sh fc fc_rl
 
 Then
 ```bash
-$ python train.py --id fc_rl --caption_model newfc --input_json data/cocotalk.json --input_fc_dir data/cocotalk_fc --input_att_dir data/cocotalk_att --input_label_h5 data/cocotalk_label.h5 --batch_size 10 --learning_rate 5e-5 --start_from log_fc_rl --checkpoint_path log_fc_rl --save_checkpoint_every 6000 --language_eval 1 --val_images_use 5000 --self_critical_after 30 --cached_tokens coco-train-idxs --max_epoch 50 --train_sample_n 5
+$ python tools/train.py --id fc_rl --caption_model newfc --input_json data/cocotalk.json --input_fc_dir data/cocotalk_fc --input_att_dir data/cocotalk_att --input_label_h5 data/cocotalk_label.h5 --batch_size 10 --learning_rate 5e-5 --start_from log_fc_rl --checkpoint_path log_fc_rl --save_checkpoint_every 6000 --language_eval 1 --val_images_use 5000 --self_critical_after 30 --cached_tokens coco-train-idxs --max_epoch 50 --train_sample_n 5
 ```
 
 or 
 ```bash
-$ python train.py --cfg configs/fc_rl.yml --id fc_rl
+$ python tools/train.py --cfg configs/fc_rl.yml --id fc_rl
 ```
 
 
@@ -100,7 +100,7 @@ Now place all your images of interest into a folder, e.g. `blah`, and run
 the eval script:
 
 ```bash
-$ python eval.py --model model.pth --infos_path infos.pkl --image_folder blah --num_images 10
+$ python tools/eval.py --model model.pth --infos_path infos.pkl --image_folder blah --num_images 10
 ```
 
 This tells the `eval` script to run up to 10 images from the given folder. If you have a big GPU you can speed up the evaluation by increasing `batch_size`. Use `--num_images -1` to process all images. The eval script will create an `vis.json` file inside the `vis` folder, which can then be visualized with the provided HTML interface:
@@ -115,7 +115,7 @@ Now visit `localhost:8000` in your browser and you should see your predicted cap
 ### Evaluate on Karpathy's test split
 
 ```bash
-$ python eval.py --dump_images 0 --num_images 5000 --model model.pth --infos_path infos.pkl --language_eval 1 
+$ python tools/eval.py --dump_images 0 --num_images 5000 --model model.pth --infos_path infos.pkl --language_eval 1 
 ```
 
 The defualt split to evaluate is test. The default inference method is greedy decoding (`--sample_method greedy`), to sample from the posterior, set `--sample_method sample`.
@@ -125,7 +125,7 @@ The defualt split to evaluate is test. The default inference method is greedy de
 ### Evaluate on COCO test set
 
 ```bash
-$ python eval.py --input_json cocotest.json --input_fc_dir data/cocotest_bu_fc --input_att_dir data/cocotest_bu_att --input_label_h5 none --num_images -1 --model model.pth --infos_path infos.pkl --language_eval 0
+$ python tools/eval.py --input_json cocotest.json --input_fc_dir data/cocotest_bu_fc --input_att_dir data/cocotest_bu_att --input_label_h5 none --num_images -1 --model model.pth --infos_path infos.pkl --language_eval 0
 ```
 
 You can download the preprocessed file `cocotest.json`, `cocotest_bu_att` and `cocotest_bu_fc` from [link](https://drive.google.com/open?id=1eCdz62FAVCGogOuNhy87Nmlo5_I0sH2J).