The rt-mrcnn from noxouille

Difference between the original mask-rcnn and mt-mrcnn model.

Hello.
What is the big difference between the original mask-rcnn and mt-mrcnn? Are the two model structures different? How did you speed up? Is it possible to explain? Is only run_webcam.py code different?

InvalidArgumentError: Incompatible shapes: [1,46,80,256] vs. [1,45,80,256] when running run_webcam.py

running python run_webcam.py throws the following error.

InvalidArgumentError (see above for traceback): Incompatible shapes: [1,46,80,256] vs. [1,45,80,256]
	 [[node fpn_p4add/add (defined at /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/layers/merge.py:210) ]]

full output including traceback is

/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Using TensorFlow backend.

Configurations:
BACKBONE                       resnet101
BACKBONE_STRIDES               [4, 8, 16, 32, 64]
BATCH_SIZE                     1
BBOX_STD_DEV                   [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE         None
DETECTION_MAX_INSTANCES        100
DETECTION_MIN_CONFIDENCE       0.7
DETECTION_NMS_THRESHOLD        0.3
FPN_CLASSIF_FC_LAYERS_SIZE     1024
GPU_COUNT                      1
GRADIENT_CLIP_NORM             5.0
IMAGES_PER_GPU                 1
IMAGE_CHANNEL_COUNT            3
IMAGE_MAX_DIM                  1024
IMAGE_META_SIZE                93
IMAGE_MIN_DIM                  800
IMAGE_MIN_SCALE                0
IMAGE_RESIZE_MODE              none
IMAGE_SHAPE                    [1024 1024    3]
LEARNING_MOMENTUM              0.9
LEARNING_RATE                  0.001
LOSS_WEIGHTS                   {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0}
MASK_POOL_SIZE                 14
MASK_SHAPE                     [28, 28]
MAX_GT_INSTANCES               100
MEAN_PIXEL                     [123.7 116.8 103.9]
MINI_MASK_SHAPE                (56, 56)
NAME                           coco
NUM_CLASSES                    81
POOL_SIZE                      7
POST_NMS_ROIS_INFERENCE        1000
POST_NMS_ROIS_TRAINING         2000
PRE_NMS_LIMIT                  6000
ROI_POSITIVE_RATIO             0.33
RPN_ANCHOR_RATIOS              [0.5, 1, 2]
RPN_ANCHOR_SCALES              (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE              1
RPN_BBOX_STD_DEV               [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD              0.7
RPN_TRAIN_ANCHORS_PER_IMAGE    256
STEPS_PER_EPOCH                1000
TOP_DOWN_PYRAMID_SIZE          256
TRAIN_BN                       False
TRAIN_ROIS_PER_IMAGE           200
USE_MINI_MASK                  True
USE_RPN_ROIS                   True
VALIDATION_STEPS               50
WEIGHT_DECAY                   0.0001


WARNING:tensorflow:From /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:1208: calling reduce_max_v1 (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead
WARNING:tensorflow:From /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:1242: calling reduce_sum_v1 (from tensorflow.python.ops.math_ops) with keep_dims is deprecated and will be removed in a future version.
Instructions for updating:
keep_dims is deprecated, use keepdims instead
WARNING:tensorflow:From /Users/<username>/Downloads/rt-mrcnn/mrcnn/model.py:772: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
2021-02-07 12:40:57.721828: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Traceback (most recent call last):
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call
    return fn(*args)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [1,46,80,256] vs. [1,45,80,256]
	 [[{{node fpn_p4add/add}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "run_webcam.py", line 100, in <module>
    results = model.detect([frame])
  File "/Users/<username>/Downloads/rt-mrcnn/mrcnn/model.py", line 2524, in detect
    self.keras_model.predict([molded_images, image_metas, anchors], verbose=0)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/engine/training.py", line 1765, in predict
    verbose=verbose, steps=steps)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/engine/training.py", line 1299, in _predict_loop
    batch_outs = f(ins_batch)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2352, in __call__
    **self.session_kwargs)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1152, in _run
    feed_dict_tensor, options, run_metadata)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run
    run_metadata)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [1,46,80,256] vs. [1,45,80,256]
	 [[node fpn_p4add/add (defined at /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/layers/merge.py:210) ]]

Caused by op 'fpn_p4add/add', defined at:
  File "run_webcam.py", line 38, in <module>
    model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)
  File "/Users/<username>/Downloads/rt-mrcnn/mrcnn/model.py", line 1837, in __init__
    self.keras_model = self.build(mode=mode, config=config)
  File "/Users/<username>/Downloads/rt-mrcnn/mrcnn/model.py", line 1907, in build
    KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c4p4')(C4)])
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/engine/topology.py", line 603, in __call__
    output = self.call(inputs, **kwargs)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/layers/merge.py", line 146, in call
    return self._merge_function(inputs)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/layers/merge.py", line 210, in _merge_function
    output += inputs[i]
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 812, in binary_op_wrapper
    return func(x, y, name=name)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 365, in add
    "Add", x=x, y=y, name=name)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
    op_def=op_def)
  File "/Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1801, in __init__
    self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Incompatible shapes: [1,46,80,256] vs. [1,45,80,256]
	 [[node fpn_p4add/add (defined at /Users/<username>/miniconda3/envs/rt-mrcnn/lib/python3.6/site-packages/keras/layers/merge.py:210) ]]

Implementation

How can I add the variations in the original repo already installed?

run_webcam.py | Use CPU instead of GPU

Hi, My model is trained on GPU but to run on webcam I am planning to use CPU.
How may a modify this code to enable CPU instead of GPU?

Only running at 0.5-1 FPS on a 1080TI

Have you had problems with the algorithm running incredibly slow? Do you know if there are any ways to make the computations easier other than decreasing the image size? Thanks in advance!

it's only 5 fps on GTX 1080 TI

I think it is slow, far from realtime.

it is only 5 fps on gtx 1080 ti

noxouille / rt-mrcnn Goto Github PK

rt-mrcnn's People

Contributors

Stargazers

Watchers

Forkers

rt-mrcnn's Issues

Difference between the original mask-rcnn and mt-mrcnn model.

InvalidArgumentError: Incompatible shapes: [1,46,80,256] vs. [1,45,80,256] when running run_webcam.py

Implementation

run_webcam.py | Use CPU instead of GPU

Only running at 0.5-1 FPS on a 1080TI

it's only 5 fps on GTX 1080 TI

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent