ss (#1)

* Fix visualize activations (matterport#1211)

Fix visualize activations (Squashed 4 commits by @keineahnung2345)

# Get activations of a few sample layers
activations = model.run_graph([image], [
    ("input_image",        model.keras_model.get_layer("input_image").output)
])
leads to the error:
InvalidArgumentError: input_image:0 is both fed and fetched.

Revise the code according to https://stackoverflow.com/questions/39307108/placeholder-20-is-both-fed-and-fetched

* Fix typo in config.py

* Fix typo in rpn_class_loss_graph

Fix matterport#870

* Reversed order (1) and (2) in installation

Reference to matterport#1255

* remove unused code (matterport#1227)

Remove unused code

README.md

@@ -179,11 +179,11 @@ If you use Docker, the code has been verified to work on
 
 
 ## Installation
-1. Install dependencies
+1. Clone this repository
+2. Install dependencies
    ```bash
    pip3 install -r requirements.txt
    ```
-2. Clone this repository
 3. Run setup from the repository root directory
     ```bash
     python3 setup.py install

mrcnn/config.py

@@ -129,7 +129,7 @@ class Config(object):
     # Minimum scaling ratio. Checked after MIN_IMAGE_DIM and can force further
     # up scaling. For example, if set to 2 then images are scaled up to double
     # the width and height, or more, even if MIN_IMAGE_DIM doesn't require it.
-    # Howver, in 'square' mode, it can be overruled by IMAGE_MAX_DIM.
+    # However, in 'square' mode, it can be overruled by IMAGE_MAX_DIM.
     IMAGE_MIN_SCALE = 0
     # Number of color channels per image. RGB = 3, grayscale = 1, RGB-D = 4
     # Changing this requires other changes in the code. See the WIKI for more

mrcnn/model.py

@@ -526,7 +526,6 @@ def detection_targets_graph(proposals, gt_class_ids, gt_boxes, gt_masks, config)
     crowd_ix = tf.where(gt_class_ids < 0)[:, 0]
     non_crowd_ix = tf.where(gt_class_ids > 0)[:, 0]
     crowd_boxes = tf.gather(gt_boxes, crowd_ix)
-    crowd_masks = tf.gather(gt_masks, crowd_ix, axis=2)
     gt_class_ids = tf.gather(gt_class_ids, non_crowd_ix)
     gt_boxes = tf.gather(gt_boxes, non_crowd_ix)
     gt_masks = tf.gather(gt_masks, non_crowd_ix, axis=2)
@@ -1025,7 +1024,7 @@ def rpn_class_loss_graph(rpn_match, rpn_class_logits):
 
     rpn_match: [batch, anchors, 1]. Anchor match type. 1=positive,
                -1=negative, 0=neutral anchor.
-    rpn_class_logits: [batch, anchors, 2]. RPN classifier logits for FG/BG.
+    rpn_class_logits: [batch, anchors, 2]. RPN classifier logits for BG/FG.
     """
     # Squeeze last dim to simplify
     rpn_match = tf.squeeze(rpn_match, -1)

mrcnn/visualize.py

@@ -140,7 +140,6 @@ def display_instances(image, boxes, masks, class_ids, class_names,
             class_id = class_ids[i]
             score = scores[i] if scores is not None else None
             label = class_names[class_id]
-            x = random.randint(x1, (x1 + x2) // 2)
             caption = "{} {:.3f}".format(label, score) if score else label
         else:
             caption = captions[i]
@@ -436,7 +435,6 @@ def draw_boxes(image, boxes=None, refined_boxes=None,
             # If there are refined boxes, display captions on them
             if refined_boxes is not None:
                 y1, x1, y2, x2 = ry1, rx1, ry2, rx2
-            x = random.randint(x1, (x1 + x2) // 2)
             ax.text(x1, y1, caption, size=11, verticalalignment='top',
                     color='w', backgroundcolor="none",
                     bbox={'facecolor': color, 'alpha': 0.5,

samples/balloon/inspect_balloon_model.ipynb

@@ -1134,7 +1134,7 @@
    "source": [
     "# Get activations of a few sample layers\n",
     "activations = model.run_graph([image], [\n",
-    "    (\"input_image\",        model.keras_model.get_layer(\"input_image\").output),\n",
+    "    (\"input_image\",        tf.identity(model.keras_model.get_layer(\"input_image\").output)),\n",
     "    (\"res2c_out\",          model.keras_model.get_layer(\"res2c_out\").output),\n",
     "    (\"res3c_out\",          model.keras_model.get_layer(\"res3c_out\").output),\n",
     "    (\"res4w_out\",          model.keras_model.get_layer(\"res4w_out\").output),  # for resnet100\n",

samples/coco/inspect_model.ipynb

@@ -1249,7 +1249,7 @@
    "source": [
     "# Get activations of a few sample layers\n",
     "activations = model.run_graph([image], [\n",
-    "    (\"input_image\",        model.keras_model.get_layer(\"input_image\").output),\n",
+    "    (\"input_image\",        tf.identity(model.keras_model.get_layer(\"input_image\").output)),\n",
     "    (\"res4w_out\",          model.keras_model.get_layer(\"res4w_out\").output),  # for resnet100\n",
     "    (\"rpn_bbox\",           model.keras_model.get_layer(\"rpn_bbox\").output),\n",
     "    (\"roi\",                model.keras_model.get_layer(\"ROI\").output),\n",

samples/nucleus/inspect_nucleus_model.ipynb

@@ -1229,7 +1229,7 @@
    "source": [
     "# Get activations of a few sample layers\n",
     "activations = model.run_graph([image], [\n",
-    "    (\"input_image\",        model.keras_model.get_layer(\"input_image\").output),\n",
+    "    (\"input_image\",        tf.identity(model.keras_model.get_layer(\"input_image\").output)),\n",
     "    (\"res2c_out\",          model.keras_model.get_layer(\"res2c_out\").output),\n",
     "    (\"res3c_out\",          model.keras_model.get_layer(\"res3c_out\").output),\n",
     "    (\"rpn_bbox\",           model.keras_model.get_layer(\"rpn_bbox\").output),\n",