Mask_rcnn: AssertionError in run_graph

[orestis-z]

I am running testing MASK_RCNN on my local computer and on a remote machine.
In inspect_model everything runs fine locally but on the remote machine I get an assertion error at ### 1.b RPN Predictions:

# Run RPN sub-graph
pillar = model.keras_model.get_layer("ROI").output  # node to start searching from
rpn = model.run_graph([image], [
    ("rpn_class", model.keras_model.get_layer("rpn_class").output),
    ("pre_nms_anchors", model.ancestor(pillar, "ROI/pre_nms_anchors:0")),
    ("refined_anchors", model.ancestor(pillar, "ROI/refined_anchors:0")),
    ("refined_anchors_clipped", model.ancestor(pillar, "ROI/refined_anchors_clipped:0")),
    ("post_nms_anchor_ix", model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")),
    ("proposals", model.keras_model.get_layer("ROI").output),
])

=>

AssertionError            Traceback (most recent call last)
<ipython-input-14-799ca4676404> in <module>()
      7     ("refined_anchors_clipped", model.ancestor(pillar, "ROI/refined_anchors_clipped:0")),
      8     ("post_nms_anchor_ix", model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")),
----> 9     ("proposals", model.keras_model.get_layer("ROI").output),
     10 ])

/home/orestisz/repositories/Mask_RCNN/model.py in run_graph(self, images, outputs)
   2296         for o in outputs.values():
   2297             print(o)
-> 2298             assert o is not None
   2299 
   2300         # Build a Keras function to run parts of the computation graph

AssertionError:

when printing the outputs:

for o in outputs.values():
            print(o)
            assert o is not None

I get the following output locally:

Tensor("rpn_class/concat:0", shape=(?, ?, 2), dtype=float32, device=/device:CPU:0)
Tensor("ROI/pre_nms_anchors:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
Tensor("ROI/refined_anchors:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
Tensor("ROI/refined_anchors_clipped:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
Tensor("ROI/rpn_non_max_suppression:0", shape=(?,), dtype=int32, device=/device:CPU:0)
Tensor("ROI/packed_2:0", shape=(1, ?, 4), dtype=float32, device=/device:CPU:0)

and the following remotely:

Tensor("rpn_class/concat:0", shape=(?, ?, 2), dtype=float32, device=/device:CPU:0)
Tensor("ROI/pre_nms_anchors:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
Tensor("ROI/refined_anchors:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
Tensor("ROI/refined_anchors_clipped:0", shape=(1, 10000, 4), dtype=float32, device=/device:CPU:0)
None

So looks like ("post_nms_anchor_ix", model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")) is causing the issue.

Any suggestions? Thanks in advance

[vijaykbg]

I am getting the same error when I run 1.b RPN Predictions

Any suggestions?

[waleedka]

Can you provide more details about your setup?

• Which versions of TensorFlow and Keras are you using?
• Which OS?
• Did you make any changes to the model, even if simple ones?

[waleedka]

Actually, I think I found the problem. TensorFlow 1.4 introduces a new version of the non-max-suppression operation with a new name. I just pushed a fix to handle the the 1.4 new name.

[orestis-z]

@waleedka thanks a lot for the fix!
But I think you wanted to type this:

nms_node = (model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")
            or model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV2:0"))

instead of:

nms_node = (ancestor(model, pillar, "ROI/rpn_non_max_suppression:0")
            or ancestor(model, pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV2:0"))

?

[waleedka]

You're right. Thank you. Pushed another fix.

[Superlee506]

@zamponotiropita Hi, do you meet this issue #285 , when I feed the run_graph with 2 images, it still outputs 1 batch_size. Any suggestion will be appreciated.

[benediktbrandt]

Just want to add that with tensorflow 1.9 it is now NonMaxSuppressionV3:0, so the code should be:

nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV2:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV3:0")

[1044886782]

Just want to add that with tensorflow 1.9 it is now NonMaxSuppressionV3:0, so the code should be:

nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV2:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV3:0")

Yeah，this helps me a lot,especially there is no answer among the Baidu or Google.I guess this bug due to the "version" will always confuse the newbie like me

[Jayleelwj]

Just want to add that with tensorflow 1.9 it is now NonMaxSuppressionV3:0, so the code should be:

nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV2:0")
if nms_node is None:
    nms_node = model.ancestor(pillar, "ROI/rpn_non_max_suppression/NonMaxSuppressionV3:0")

Much appreciated for your answer. It works for me