Update README.md

wenz116 · Nov 2, 2018 · 8a52a03 · 8a52a03
1 parent 544e0f0
commit 8a52a03
Showing 1 changed file with 14 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -6,14 +6,20 @@
 * Pytorch 0.2 or higher
 * CUDA 8.0
 
+* Mask R-CNN: Follow the instructions of the [mask-faster-rcnn](https://github.com/lichengunc/mask-faster-rcnn) repo, preparing everything needed for `pyutils/mask-faster-rcnn`.
+
+* REFER API and data: Use the download links of [REFER](https://github.com/lichengunc/refer) and go to the foloder running `make`. Follow `data/README.md` to prepare images and refcoco/refcoco+/refcocog annotations.
+
+* COCO training set should be downloaded in `pyutils/mask-faster-rcnn/data/coco/images/train2014`.
+
 ## Training
 1. Train the baseline segmentation model:
 ```
 ./experiments/scripts/train_baseline.sh <GPUID> <DATASET> <SPLITBY> <OUTPUT_POSTFIX>
 ```
-<DATASET> <SPLITBY>: refcoco unc/refcoco+ unc/refcocog umd/refcocog google
+`<DATASET> <SPLITBY>: refcoco unc/refcoco+ unc/refcocog umd/refcocog google`
 
-Output model will be saved at <DATASET>_<SPLITBY>/output_<OUTPUT_POSTFIX>.
+Output model will be saved at `<DATASET>_<SPLITBY>/output_<OUTPUT_POSTFIX>`.
 
 The Mask-RCNN model is in `pyutils/mask-faster-rcnn/lib/nets/resnet_v1.py` and `pyutils/mask-faster-rcnn/lib/nets/network.py`.
 
@@ -36,4 +42,9 @@ Losses are calculated in [_add_losses()](https://github.com/wenz116/lang2seg/blo
 ```
 ./experiments/scripts/eval_baseline.sh <GPUID> <DATASET> <SPLITBY> <OUTPUT_POSTFIX> <MODEL_ITER>
 ```
-Evaluate the model at <DATASET>_<SPLITBY>/output_<OUTPUT_POSTFIX>, of trained iteration <MODEL_ITER>.
+Evaluate the model at `<DATASET>_<SPLITBY>/output_<OUTPUT_POSTFIX>`, of trained iteration `<MODEL_ITER>`.
+
+2. Evaluate the model with spatial dynamic filters:
+```
+./experiments/scripts/eval_spatial.sh <GPUID> <DATASET> <SPLITBY> <OUTPUT_POSTFIX> <MODEL_ITER>
+```