[MaskRCNN] improve visualization palette

.github/ISSUE_TEMPLATE/unexpected-problems---bugs.md

@@ -18,14 +18,16 @@ feel free to delete everything in this template.
 
 (3) **If not using examples, tell us what you did:**
 
-Note that we may not be able to investigate it if there is no reproducible code.
-It's always better to paste what you did instead of describing them.
+  It's always better to copy-paste what you did than to describe them.
+
+  Please try to provide enough information to let other __reproduce__ your issues. 
+  Without reproducing the issue, we may not be able to investigate it.
 
 ### 2. What you observed:
 
 (1) **Include the ENTIRE logs here:**
 
-It's always better to paste what you observed instead of describing them.
+It's always better to copy-paste what you observed instead of describing them.
 
 It's always better to paste **as much as possible**, although sometimes a partial log is OK.
 
@@ -42,11 +44,11 @@ If you expect higher speed, please read
 http://tensorpack.readthedocs.io/tutorial/performance-tuning.html 
 before posting.
 
-If you expect higher accuracy, only in one of the two conditions can we help with it:
+If you expect certain accuracy, only in one of the two conditions can we help with it:
 (1) You're unable to match the accuracy documented in tensorpack examples.
 (2) It appears to be a tensorpack bug.
 
-Otherwise, how to get high accuracy is a machine learning question and is
+Otherwise, how to train a model to certain accuracy is a machine learning question and is
 not our responsibility to figure out.
 
 ### 4. Your environment:

.github/ISSUE_TEMPLATE/using-understanding-tensorpack.md

@@ -4,7 +4,7 @@ about: More general questions about Tensorpack.
 
 ---
 
-+ If you did something with tensorpack and it failed, please use the "Unexpected Problems /
++ If you did something with tensorpack and it failed, PLEASE STOP HERE and use the "Unexpected Problems /
   Bugs" category.
 
 + Your question is probably answered in [tutorials](http://tensorpack.readthedocs.io/tutorial/index.html#user-tutorials). Read it first.
@@ -23,6 +23,7 @@ Some typical questions that we DO NOT answer:
   We have no plans to do so. We don't consider feature
   requests for examples or implement a paper for you.
   If you don't know how to do something yourself, you may ask a usage question.
+
 + "The examples do not perform as expected after I change the models/dataset/parameters/etc.":
 
   Tensorpack maintainers make sure the examples perform well without modifications.

examples/FasterRCNN/README.md

@@ -63,7 +63,7 @@ Some reasonable configurations are listed in the table below.
 
 To predict on an image (needs DISPLAY to show the outputs):
 ```
-./train.py --predict input.jpg --load /path/to/Trained-Model-Checkpoint --config SAME-AS-TRAINING
+./train.py --predict input1.jpg input2.jpg --load /path/to/Trained-Model-Checkpoint --config SAME-AS-TRAINING
 ```
 
 To evaluate the performance of a model on COCO:

examples/FasterRCNN/config.py

@@ -201,7 +201,7 @@ _C.TEST.FRCNN_NMS_THRESH = 0.5
 # Smaller threshold value gives significantly better mAP. But we use 0.05 for consistency with Detectron.
 # mAP with 1e-4 threshold can be found at https://github.com/tensorpack/tensorpack/commit/26321ae58120af2568bdbf2269f32aa708d425a8#diff-61085c48abee915b584027e1085e1043  # noqa
 _C.TEST.RESULT_SCORE_THRESH = 0.05
-_C.TEST.RESULT_SCORE_THRESH_VIS = 0.3   # only visualize confident results
+_C.TEST.RESULT_SCORE_THRESH_VIS = 0.5   # only visualize confident results
 _C.TEST.RESULTS_PER_IM = 100
 
 _C.freeze()  # avoid typo / wrong config keys

examples/FasterRCNN/train.py

@@ -393,7 +393,7 @@ def do_predict(pred_func, input_file):
     final = draw_final_outputs(img, results)
     viz = np.concatenate((img, final), axis=1)
     cv2.imwrite("output.png", viz)
-    logger.info("Inference output written to output.png")
+    logger.info("Inference output for {} written to output.png".format(input_file))
     tpviz.interactive_imshow(viz)
 
 
@@ -405,7 +405,7 @@ if __name__ == '__main__':
     parser.add_argument('--evaluate', help="Run evaluation. "
                                            "This argument is the path to the output json evaluation file")
     parser.add_argument('--predict', help="Run prediction on a given image. "
-                                          "This argument is the path to the input image file")
+                                          "This argument is the path to the input image file", nargs='+')
     parser.add_argument('--config', help="A list of KEY=VALUE to overwrite those defined in config.py",
                         nargs='+')
 
@@ -440,7 +440,9 @@ if __name__ == '__main__':
                 input_names=MODEL.get_inference_tensor_names()[0],
                 output_names=MODEL.get_inference_tensor_names()[1])
             if args.predict:
-                do_predict(OfflinePredictor(predcfg), args.predict)
+                predictor = OfflinePredictor(predcfg)
+                for image_file in args.predict:
+                    do_predict(predictor, image_file)
             elif args.evaluate:
                 assert args.evaluate.endswith('.json'), args.evaluate
                 do_evaluate(predcfg, args.evaluate)

examples/FasterRCNN/viz.py

@@ -9,6 +9,7 @@ from tensorpack.utils.palette import PALETTE_RGB
 
 from config import config as cfg
 from utils.np_box_ops import iou as np_iou
+from utils.np_box_ops import area as np_area
 
 
 def draw_annotation(img, boxes, klass, is_crowd=None):
@@ -70,14 +71,19 @@ def draw_final_outputs(img, results):
     if len(results) == 0:
         return img
 
+    # Display in largest to smallest order to reduce occlusion
+    boxes = np.asarray([r.box for r in results])
+    areas = np_area(boxes)
+    sorted_inds = np.argsort(-areas)
+
     tags = []
     for r in results:
         tags.append(
             "{},{:.2f}".format(cfg.DATA.CLASS_NAMES[r.class_id], r.score))
-    boxes = np.asarray([r.box for r in results])
     ret = viz.draw_boxes(img, boxes, tags)
 
-    for r in results:
+    for result_id in sorted_inds:
+        r = results[result_id]
         if r.mask is not None:
             ret = draw_mask(ret, r.mask)
     return ret

tensorpack/utils/palette.py

@@ -5,7 +5,7 @@ import numpy as np
 
 __all__ = ['PALETTE_RGB']
 
-# copied from https://stackoverflow.com/questions/2328339/how-to-generate-n-different-colors-for-any-natural-number-n
+# Copied from https://stackoverflow.com/questions/2328339/how-to-generate-n-different-colors-for-any-natural-number-n
 PALETTE_HEX = [
     "#000000", "#FFFF00", "#1CE6FF", "#FF34FF", "#FF4A46", "#008941", "#006FA6", "#A30059",
     "#FFDBE5", "#7A4900", "#0000A6", "#63FFAC", "#B79762", "#004D43", "#8FB0FF", "#997D87",
@@ -26,6 +26,92 @@ PALETTE_HEX = [
     "#7ED379", "#012C58"]
 
 
+# Copied from https://github.com/facebookresearch/Detectron/blob/master/detectron/utils/colormap.py
+DETECTRON_PALETTE = np.array(
+    [
+        0.000, 0.447, 0.741,
+        0.850, 0.325, 0.098,
+        0.929, 0.694, 0.125,
+        0.494, 0.184, 0.556,
+        0.466, 0.674, 0.188,
+        0.301, 0.745, 0.933,
+        0.635, 0.078, 0.184,
+        0.300, 0.300, 0.300,
+        0.600, 0.600, 0.600,
+        1.000, 0.000, 0.000,
+        1.000, 0.500, 0.000,
+        0.749, 0.749, 0.000,
+        0.000, 1.000, 0.000,
+        0.000, 0.000, 1.000,
+        0.667, 0.000, 1.000,
+        0.333, 0.333, 0.000,
+        0.333, 0.667, 0.000,
+        0.333, 1.000, 0.000,
+        0.667, 0.333, 0.000,
+        0.667, 0.667, 0.000,
+        0.667, 1.000, 0.000,
+        1.000, 0.333, 0.000,
+        1.000, 0.667, 0.000,
+        1.000, 1.000, 0.000,
+        0.000, 0.333, 0.500,
+        0.000, 0.667, 0.500,
+        0.000, 1.000, 0.500,
+        0.333, 0.000, 0.500,
+        0.333, 0.333, 0.500,
+        0.333, 0.667, 0.500,
+        0.333, 1.000, 0.500,
+        0.667, 0.000, 0.500,
+        0.667, 0.333, 0.500,
+        0.667, 0.667, 0.500,
+        0.667, 1.000, 0.500,
+        1.000, 0.000, 0.500,
+        1.000, 0.333, 0.500,
+        1.000, 0.667, 0.500,
+        1.000, 1.000, 0.500,
+        0.000, 0.333, 1.000,
+        0.000, 0.667, 1.000,
+        0.000, 1.000, 1.000,
+        0.333, 0.000, 1.000,
+        0.333, 0.333, 1.000,
+        0.333, 0.667, 1.000,
+        0.333, 1.000, 1.000,
+        0.667, 0.000, 1.000,
+        0.667, 0.333, 1.000,
+        0.667, 0.667, 1.000,
+        0.667, 1.000, 1.000,
+        1.000, 0.000, 1.000,
+        1.000, 0.333, 1.000,
+        1.000, 0.667, 1.000,
+        0.167, 0.000, 0.000,
+        0.333, 0.000, 0.000,
+        0.500, 0.000, 0.000,
+        0.667, 0.000, 0.000,
+        0.833, 0.000, 0.000,
+        1.000, 0.000, 0.000,
+        0.000, 0.167, 0.000,
+        0.000, 0.333, 0.000,
+        0.000, 0.500, 0.000,
+        0.000, 0.667, 0.000,
+        0.000, 0.833, 0.000,
+        0.000, 1.000, 0.000,
+        0.000, 0.000, 0.167,
+        0.000, 0.000, 0.333,
+        0.000, 0.000, 0.500,
+        0.000, 0.000, 0.667,
+        0.000, 0.000, 0.833,
+        0.000, 0.000, 1.000,
+        0.000, 0.000, 0.000,
+        0.143, 0.143, 0.143,
+        0.286, 0.286, 0.286,
+        0.429, 0.429, 0.429,
+        0.571, 0.571, 0.571,
+        0.714, 0.714, 0.714,
+        0.857, 0.857, 0.857,
+        1.000, 1.000, 1.000
+    ]
+).astype(np.float32).reshape(-1, 3) * 255
+
+
 def _parse_hex_color(s):
     r = int(s[1:3], 16)
     g = int(s[3:5], 16)
@@ -33,6 +119,9 @@ def _parse_hex_color(s):
     return (r, g, b)
 
 
-PALETTE_RGB = np.asarray(
-    list(map(_parse_hex_color, PALETTE_HEX)),
-    dtype='int32')
+# PALETTE_RGB = np.asarray(
+#     list(map(_parse_hex_color, PALETTE_HEX)),
+#     dtype='int32')
+
+# This seems more beautiful
+PALETTE_RGB = DETECTRON_PALETTE