add customer dataset and associated config file

README.md

@@ -109,7 +109,7 @@ frankfurt_000001_079206_leftImg8bit.png,frankfurt_000001_079206_gtFine_labelIds.
 ...
 ```
 Each line is a pair of training sample and ground truth image path, which are separated by a single comma `,`.   
-Then you need to change the field of `im_root` and `train/val_im_anns` in the configuration files. If you found what shows in `cityscapes_cv2.py` is not clear, you can also see `coco.py`.
+Then you need to change the field of `im_root` and `train/val_im_anns` in the config file. I prepared a demo config file for you named [`bisenet_customer.py`](./configs/bisenet_customer.py). You can start from this conig file.
 
 
 ## train

configs/bisenet_customer.py

@@ -0,0 +1,23 @@
+
+cfg = dict(
+    model_type='bisenetv1',
+    n_cats=20,
+    num_aux_heads=2,
+    lr_start=1e-2,
+    weight_decay=5e-4,
+    warmup_iters=1000,
+    max_iter=80000,
+    dataset='CustomerDataset',
+    im_root='./datasets/cityscapes',
+    train_im_anns='./datasets/cityscapes/train.txt',
+    val_im_anns='./datasets/cityscapes/val.txt',
+    scales=[0.75, 2.],
+    cropsize=[512, 512],
+    eval_crop=[512, 512],
+    eval_scales=[0.5, 0.75, 1.0, 1.25, 1.5, 1.75],
+    ims_per_gpu=8,
+    eval_ims_per_gpu=2,
+    use_fp16=True,
+    use_sync_bn=False,
+    respth='./res',
+)