Custom Object Detection with TensorFlow
Home Page: https://medium.freecodecamp.org/tracking-the-millenium-falcon-with-tensorflow-c8c86419225e
License: MIT License
Hi Nick,
after recapping successfully your tutorial "as is" I tried out to create my own object detection model. I replaced your pictures with mine, used my own annotation xml files (boxes only), trained it (was very short run time - only one global step ...), created the graph file and then tested it with the following result. There seems to go something wrong with the "aspect" parameter set to "normal" ... but I do not know what that means ;-)
jre@ibm-jre-mbp ==_-+- python object_detection/object_detection_runner.py
dyld: warning, LC_RPATH $ORIGIN/../../_solib_darwin_x86_64/_U_S_Stensorflow_Spython_C_Upywrap_Utensorflow_Uinternal.so___Utensorflow in /Users/jre/Library/Python/2.7/lib/python/site-packages/tensorflow/python/_pywrap_tensorflow_internal.so being ignored in restricted program because it is a relative path
Loading model...
detecting...
2017-12-01 11:55:11.616214: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Traceback (most recent call last):
File "object_detection/object_detection_runner.py", line 90, in <module>
detect_objects(image_path)
File "object_detection/object_detection_runner.py", line 63, in detect_objects
plt.imshow(image_np, aspect = 'normal')
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/matplotlib/pyplot.py", line 3080, in imshow
**kwargs)
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/matplotlib/__init__.py", line 1710, in inner
return func(ax, *args, **kwargs)
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/matplotlib/axes/_axes.py", line 5189, in imshow
self.set_aspect(aspect)
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/matplotlib/axes/_base.py", line 1273, in set_aspect
self._aspect = float(aspect) # raise ValueError if necessary
ValueError: could not convert string to float: normal
[ /Users/jre/Downloads/Watson/JRE-Object-Detection-master ]
jre@ibm-jre-mbp ==_-+-
What is going wrong? Find the installed versions of numpy and matplotlib below:
jre@ibm-jre-mbp ==_-+- pip list --format=legacy
altgraph (0.10.2)
appnope (0.1.0)
asn1crypto (0.23.0)
backports-abc (0.5)
backports.functools-lru-cache (1.4)
backports.shutil-get-terminal-size (1.0.0)
backports.weakref (1.0.post1)
bdist-mpkg (0.5.0)
bleach (2.1.1)
bonjour-py (0.3)
certifi (2017.11.5)
cffi (1.11.2)
chardet (3.0.4)
configparser (3.5.0)
cryptography (2.1.3)
cycler (0.10.0)
decorator (4.1.2)
entrypoints (0.2.3)
enum34 (1.1.6)
funcsigs (1.0.2)
functools32 (3.2.3.post2)
futures (3.1.1)
html5lib (1.0b10)
idna (2.6)
ipaddress (1.0.18)
ipykernel (4.6.1)
ipython (5.5.0)
ipython-genutils (0.2.0)
ipywidgets (7.0.5)
Jinja2 (2.10)
jsonschema (2.6.0)
jupyter (1.0.0)
jupyter-client (5.1.0)
jupyter-console (5.2.0)
jupyter-core (4.4.0)
lxml (4.1.1)
macholib (1.5.1)
Markdown (2.6.9)
MarkupSafe (1.0)
matplotlib (2.1.0)
mistune (0.8.1)
mock (2.0.0)
modulegraph (0.10.4)
nbconvert (5.3.1)
nbformat (4.4.0)
notebook (5.2.1)
numpy (1.13.3)
olefile (0.44)
pandocfilters (1.4.2)
pathlib2 (2.3.0)
pbr (3.1.1)
pexpect (4.3.0)
pickleshare (0.7.4)
Pillow (4.3.0)
pip (9.0.1)
prompt-toolkit (1.0.15)
protobuf (3.5.0.post1)
ptyprocess (0.5.2)
py2app (0.7.3)
pycparser (2.18)
Pygments (2.2.0)
pyobjc-core (2.5.1)
pyobjc-framework-Accounts (2.5.1)
pyobjc-framework-AddressBook (2.5.1)
pyobjc-framework-AppleScriptKit (2.5.1)
pyobjc-framework-AppleScriptObjC (2.5.1)
pyobjc-framework-Automator (2.5.1)
pyobjc-framework-CFNetwork (2.5.1)
pyobjc-framework-Cocoa (2.5.1)
pyobjc-framework-Collaboration (2.5.1)
pyobjc-framework-CoreData (2.5.1)
pyobjc-framework-CoreLocation (2.5.1)
pyobjc-framework-CoreText (2.5.1)
pyobjc-framework-DictionaryServices (2.5.1)
pyobjc-framework-EventKit (2.5.1)
pyobjc-framework-ExceptionHandling (2.5.1)
pyobjc-framework-FSEvents (2.5.1)
pyobjc-framework-InputMethodKit (2.5.1)
pyobjc-framework-InstallerPlugins (2.5.1)
pyobjc-framework-InstantMessage (2.5.1)
pyobjc-framework-LatentSemanticMapping (2.5.1)
pyobjc-framework-LaunchServices (2.5.1)
pyobjc-framework-Message (2.5.1)
pyobjc-framework-OpenDirectory (2.5.1)
pyobjc-framework-PreferencePanes (2.5.1)
pyobjc-framework-PubSub (2.5.1)
pyobjc-framework-QTKit (2.5.1)
pyobjc-framework-Quartz (2.5.1)
pyobjc-framework-ScreenSaver (2.5.1)
pyobjc-framework-ScriptingBridge (2.5.1)
pyobjc-framework-SearchKit (2.5.1)
pyobjc-framework-ServiceManagement (2.5.1)
pyobjc-framework-Social (2.5.1)
pyobjc-framework-SyncServices (2.5.1)
pyobjc-framework-SystemConfiguration (2.5.1)
pyobjc-framework-WebKit (2.5.1)
pyOpenSSL (17.4.0)
pyparsing (2.2.0)
pysolr (3.6.0)
python-dateutil (2.6.1)
pytz (2017.3)
pyzmq (16.0.3)
qtconsole (4.3.1)
requests (2.18.4)
scandir (1.6)
scipy (0.13.0b1)
setuptools (38.2.1)
simplegeneric (0.8.1)
singledispatch (3.4.0.3)
six (1.11.0)
subprocess32 (3.2.7)
tensorflow (1.4.0)
tensorflow-tensorboard (0.4.0rc3)
terminado (0.8)
testpath (0.3.1)
tornado (4.5.2)
traitlets (4.3.2)
urllib3 (1.22)
vboxapi (1.0)
watson-developer-cloud (1.0.0)
wcwidth (0.1.7)
webencodings (0.5.1)
Werkzeug (0.12.2)
wheel (0.30.0)
widgetsnbextension (3.0.8)
xattr (0.6.4)
zope.interface (4.1.1)
[ /Users/jre/Downloads/Watson/JRE-Object-Detection-master ]
jre@ibm-jre-mbp ==_-+-
tensorflow-gpu 1.3.0
tensorflow-tensorboard 0.1.8
Keras 2.0.6
Keras-Applications 1.0.6
I downloaded model_zoo link and successfully running 2 models ( ssd_mobilenet_v1_coco, ssd_inception_v2_coco) without any problems.But when i try faster_rcnn_inception_resnet_v2_atrous_coco, and rfcn_resnet101_coco models, models start working properly, but it consumes almost 62.8G/62.8G memory, so I couldn't run it. Have you ever got this issues?
I have 2394*3062 png image files for training, so i resizing the image as 600 * 767(config file).
i also using 'os.environ['CUDA_VISIBLE_DEVICES'] = '1'' and it works well.
Total memory: 10.91GiB
Free memory: 10.75GiB
2018-10-23 10:55:29.290302: I tensorflow/core/common_runtime/gpu/gpu_device.cc:976] DMA: 0
2018-10-23 10:55:29.290311: I tensorflow/core/common_runtime/gpu/gpu_device.cc:986] 0: Y
2018-10-23 10:55:29.290323: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:06:00.0)
2018-10-23 10:55:31.938505: I tensorflow/core/common_runtime/simple_placer.cc:697] Ignoring device specification /device:GPU:0 for node 'prefetch_queue_Dequeue' because the input edge from 'prefetch_queue' is a reference connection and already has a device field set to /device:CPU:0
INFO:tensorflow:Restoring parameters from model.ckpt
INFO:tensorflow:Starting Session.
INFO:tensorflow:Saving checkpoint to path train/model.ckpt
INFO:tensorflow:Starting Queues.
INFO:tensorflow:global_step/sec: 0
INFO:tensorflow:Recording summary at step 0.
INFO:tensorflow:global step 1: loss = 1.5886 (24.888 sec/step)
INFO:tensorflow:global step 2: loss = 1.4227 (0.812 sec/step)
INFO:tensorflow:global step 3: loss = 1.2016 (0.875 sec/step)
model {
faster_rcnn {
num_classes: 1
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 767
}
}
feature_extractor {
type: 'faster_rcnn_inception_resnet_v2'
first_stage_features_stride: 8
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 2.0]
height_stride: 8
width_stride: 8
}
}
first_stage_atrous_rate: 2
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.7
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 17
maxpool_kernel_size: 1
maxpool_stride: 1
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0003
schedule {
step: 0
learning_rate: .0003
}
schedule {
step: 900000
learning_rate: .00003
}
schedule {
step: 1200000
learning_rate: .000003
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint: "model.ckpt"
from_detection_checkpoint: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset. This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "train.record"
}
label_map_path: "annotations/label_map.pbtxt"
}
eval_config: {
num_examples: 170
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "val.record"
}
label_map_path: "annotations/label_map.pbtxt"
shuffle: false
num_readers: 1
}
There is no longer a create_tf_record.py in tools. There is a pet create tf record, but that one requires trimap's and may not even be geared towards ssd.
For the model to train on 500 images 200000-epochs !
What is the configuration(RAM,NVIDIA Graphics) Required to finish it in 2 days.
Please can any one suggest !
How do I train and test?
Trying to reproduce your demo, I run your training example with your images and "faster_rcnn_resnet101.config" . Although the loss drops gradually the prediction scores drop fast to zero after few hundred of steps. Changing the learning rate didn't solved it.
Do you have any suggestion?
Traceback (most recent call last):
File "object_detection/object_detection_runner.py", line 95, in
detect_objects(image_path)
File "object_detection/object_detection_runner.py", line 64, in detect_objects
plt.imshow(image_np, aspect = 'normal')
File "/usr/local/lib/python2.7/dist-packages/matplotlib/pyplot.py", line 3080, in imshow
**kwargs)
File "/usr/local/lib/python2.7/dist-packages/matplotlib/init.py", line 1710, in inner
return func(ax, *args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/matplotlib/axes/_axes.py", line 5189, in imshow
self.set_aspect(aspect)
File "/usr/local/lib/python2.7/dist-packages/matplotlib/axes/_base.py", line 1273, in set_aspect
self._aspect = float(aspect) # raise ValueError if necessary
ValueError: could not convert string to float: normal
.local/lib/python2.7/site-packages/requests/init.py:80: RequestsDependencyWarning: urllib3 (1.22) or chardet (2.3.0) doesn't match a supported version!
RequestsDependencyWarning)
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Summary name Learning Rate is illegal; using Learning_Rate instead.
Traceback (most recent call last):
File "object_detection/train.py", line 198, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/media/admin1/8C4CB1B64CB19C00/Tej/ML/Custom-Object-Detection-master/object_detection/trainer.py", line 218, in train
var_map, train_config.fine_tune_checkpoint))
File "/media/admin1/8C4CB1B64CB19C00/Tej/ML/Custom-Object-Detection-master/object_detection/utils/variables_helper.py", line 122, in get_variables_available_in_checkpoint
ckpt_reader = tf.train.NewCheckpointReader(checkpoint_path)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 110, in NewCheckpointReader
return CheckpointReader(compat.as_bytes(filepattern), status)
File "/usr/lib/python2.7/contextlib.py", line 24, in exit
self.gen.next()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model.ckpt
Where I'm getting wrong?
Could anyone help me.....
Hi Nick, I am not sure if I am doing wrong. Running "python object_detection/create_tf_record.py" gives a warning but train.record and val.record are created:
dyld: warning, LC_RPATH $ORIGIN/../../_solib_darwin_x86_64/_U_S_Stensorflow_Spython_C_Upywrap_Utensorflow_Uinternal.so___Utensorflow in /Users/jre/Library/Python/2.7/lib/python/site-packages/tensorflow/python/pywrap_tensorflow_internal.so being ignored in restricted program because it is a relative path
/Users/jre/Downloads/Watson/Custom-Object-Detection-master/object_detection/utils/dataset_util.py:75: FutureWarning: The behavior of this method will change in future versions. Use specific 'len(elem)' or 'elem is not None' test instead.
if not xml:
[ /Users/jre/Downloads/Watson/Custom-Object-Detection-master ]
jre@ibm-jre-mbp ==-+-
Is this ok?
Hi nick,
I'm new to tensorflow so this may be a dumb question, but every output images that the program makes is resized to 558 of height and i think maybe that's why the program doesn't recognise features in my test images.
Maybe you can help?
The project I am targeting is a ship.
When I try to train with your project.
Instead, the accuracy rate has dropped.
It may be because there is a similar project So affecting the weight.
Is there any way to train the original coco project
Instead of creating a new one?
Hi you have given a very good explanation. But I have some Issue in training.
I have followed your instruction but When I run train.py with the dataset given by you my system freezes at step 0 and then I have to restart my system.
When I checked ram usage using htop command, I saw It consumes whole RAM.
I am using linux 14.04 with 8 gb, 4 CPU cores.
Can we run this code on CPU or it is only compatible to GPU?
python object_detection/train.py --logtostderr --train_dir=train/ --pipeline_config_path=ssd_inception_v2_coco.config
WARNING:tensorflow:From /home/prashant/Custom-Object-Detection/object_detection/trainer.py:176: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.create_global_step
Traceback (most recent call last):
File "object_detection/train.py", line 198, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/home/prashant/Custom-Object-Detection/object_detection/trainer.py", line 192, in train
clones = model_deploy.create_clones(deploy_config, model_fn, [input_queue])
File "/home/prashant/Custom-Object-Detection/slim/deployment/model_deploy.py", line 193, in create_clones
outputs = model_fn(*args, **kwargs)
File "/home/prashant/Custom-Object-Detection/object_detection/trainer.py", line 133, in _create_losses
losses_dict = detection_model.loss(prediction_dict)
File "/home/prashant/Custom-Object-Detection/object_detection/meta_architectures/ssd_meta_arch.py", line 431, in loss
location_losses, cls_losses, prediction_dict, match_list)
File "/home/prashant/Custom-Object-Detection/object_detection/meta_architectures/ssd_meta_arch.py", line 565, in _apply_hard_mining
match_list=match_list)
File "/home/prashant/Custom-Object-Detection/object_detection/core/losses.py", line 445, in call
location_losses = tf.unstack(location_losses)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 1054, in unstack
(axis, -value_shape.ndims, value_shape.ndims))
This happened with at least 3 images so far and this was not the problem when these images were in the training set before.
The error code is like this:
Traceback (most recent call last):
File "object_detection/object_detection_runner.py", line 90, in
detect_objects(image_path)
File "object_detection/object_detection_runner.py", line 43, in detect_objects
image_np = load_image_into_numpy_array(image)
File "object_detection/object_detection_runner.py", line 39, in load_image_into_numpy_array
(im_height, im_width, 3)).astype(np.uint8)
ValueError: cannot reshape array of size 587214 into shape (606,969,3)
It seems weird to me that these 3 images were resulting an error when doing predictions and they were completely fine when they were in the training set. Do you have any fix or suggestions for this?
Thank you,
Selin
I was following your article on Medium and everything went well up until where I had to run python object_detection/create_tf_record.py I have updated my trainval.txt and label_map.pbtxt. I also have my xml files in the folder where they are supposed to be also with the corresponding images in the images folder. However, whenever I try to run the create_tf_record.py file, it keeps giving me an error saying cannot find annotations. I am not sure what I am doing wrong. Please let me know if this can be fixed
Getting error while compiling the protobuf libraries
INFO:tensorflow:global step 2: loss = 1.7981 (25.561 sec/step)
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, Incompatible shapes: [1,63,4] vs. [1,64,4]
[[Node: gradients/Loss/BoxClassifierLoss/Loss/sub_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](gradients/Loss/BoxClassifierLoss/Loss/sub_grad/Shape, gradients/Loss/BoxClassifierLoss/Loss/sub_1_grad/Shape)]]
thank you for your share. i want to know how to detenct the vedio's ship
2018-03-04 13:19:20.290777: W tensorflow/core/framework/op_kernel.cc:1192] Resource exhausted: OOM when allocating tensor with shape[1,1024,51,38]
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.ResourceExhaustedError'>, OOM when allocating tensor with shape[1,1024,51,38]
[[Node: FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=1.001e-05, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/Conv2D, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/gamma/read/_683, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/beta/read/_685, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_mean/read/_687, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_variance/read/_689)]]
[[Node: Reshape_24/_1255 = _HostRecvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4073_Reshape_24", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Caused by op u'FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm', defined at:
File "object_detection/train.py", line 198, in
tf.app.run()
File "/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run/Documents/Custom-Object-Detection-master/object_detection/trainer.py", line 192, in train
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "
clones = model_deploy.create_clones(deploy_config, model_fn, [input_queue])
File "/Documents/Custom-Object-Detection-master/slim/deployment/model_deploy.py", line 193, in create_clones/Documents/Custom-Object-Detection-master/object_detection/trainer.py", line 131, in _create_losses
outputs = model_fn(*args, **kwargs)
File "
prediction_dict = detection_model.predict(images)
File "/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 513, in predict/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 652, in _extract_rpn_feature_maps
image_shape) = self._extract_rpn_feature_maps(preprocessed_inputs)
File "
preprocessed_inputs, scope=self.first_stage_feature_extractor_scope)
File "/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 131, in extract_proposal_features/Documents/Custom-Object-Detection-master/object_detection/models/faster_rcnn_resnet_v1_feature_extractor.py", line 126, in _extract_proposal_features
return self._extract_proposal_features(preprocessed_inputs, scope)
File "
scope=var_scope)
File "/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 298, in resnet_v1_101/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 216, in resnet_v1
reuse=reuse, scope=scope)
File "
net = resnet_utils.stack_blocks_dense(net, blocks, output_stride)
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/Documents/Custom-Object-Detection-master/slim/nets/resnet_utils.py", line 185, in stack_blocks_dense
return func(*args, **current_args)
File "
net = block.unit_fn(net, rate=rate, **dict(unit, stride=1))
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 118, in bottleneck
return func(*args, **current_args)
File "
activation_fn=None, scope='conv3')
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1042, in convolution
return func(*args, **current_args)
File "
outputs = normalizer_fn(outputs, **normalizer_params)
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 643, in batch_norm
return func(*args, **current_args)
File "
outputs = layer.apply(inputs, training=is_training)
File "/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 671, in apply/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 575, in call
return self.call(inputs, *args, **kwargs)
File "
outputs = self.call(inputs, *args, **kwargs)
File "/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 395, in call/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 302, in _fused_batch_norm
return self._fused_batch_norm(inputs, training=training)
File "
training, _fused_batch_norm_training, _fused_batch_norm_inference)
File "/lib/python2.7/site-packages/tensorflow/python/layers/utils.py", line 208, in smart_cond/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 299, in _fused_batch_norm_inference
return fn2()
File "
data_format=self._data_format)
File "/lib/python2.7/site-packages/tensorflow/python/ops/nn_impl.py", line 831, in fused_batch_norm/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2034, in _fused_batch_norm
name=name)
File "
is_training=is_training, name=name)
File "/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "
op_def=op_def)
File "~/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,1024,51,38]
[[Node: FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=1.001e-05, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/Conv2D, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/gamma/read/_683, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/beta/read/_685, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_mean/read/_687, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_variance/read/_689)]]
[[Node: Reshape_24/_1255 = _HostRecvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4073_Reshape_24", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Traceback (most recent call last):
File "object_detection/train.py", line 198, in
tf.app.run()
File "/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run/Documents/Custom-Object-Detection-master/object_detection/trainer.py", line 296, in train
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "
saver=saver)
File "/lib/python2.7/site-packages/tensorflow/contrib/slim/python/slim/learning.py", line 775, in train/lib/python2.7/contextlib.py", line 35, in exit
sv.stop(threads, close_summary_writer=True)
File "
self.gen.throw(type, value, traceback)
File "/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 964, in managed_session/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 792, in stop
self.stop(close_summary_writer=close_summary_writer)
File "
stop_grace_period_secs=self._stop_grace_secs)
File "/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 296, in stop_on_exception
six.reraise(*self._exc_info_to_raise)
File "
yield
File "/lib/python2.7/site-packages/tensorflow/python/training/coordinator.py", line 494, in run/lib/python2.7/site-packages/tensorflow/python/training/supervisor.py", line 994, in run_loop
self.run_loop()
File "
self._sv.global_step])
File "/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
run_metadata_ptr)
File "
feed_dict_tensor, options, run_metadata)
File "/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
options, run_metadata)
File "
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1,1024,51,38]
[[Node: FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=1.001e-05, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/Conv2D, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/gamma/read/_683, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/beta/read/_685, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_mean/read/_687, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_variance/read/_689)]]
[[Node: Reshape_24/_1255 = _HostRecvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4073_Reshape_24", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Caused by op u'FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm', defined at:
File "object_detection/train.py", line 198, in
tf.app.run()
File "/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run/Documents/Custom-Object-Detection-master/object_detection/trainer.py", line 192, in train
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "
clones = model_deploy.create_clones(deploy_config, model_fn, [input_queue])
File "/Documents/Custom-Object-Detection-master/slim/deployment/model_deploy.py", line 193, in create_clones/Documents/Custom-Object-Detection-master/object_detection/trainer.py", line 131, in _create_losses
outputs = model_fn(*args, **kwargs)
File "
prediction_dict = detection_model.predict(images)
File "/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 513, in predict/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 652, in _extract_rpn_feature_maps
image_shape) = self._extract_rpn_feature_maps(preprocessed_inputs)
File "
preprocessed_inputs, scope=self.first_stage_feature_extractor_scope)
File "/Documents/Custom-Object-Detection-master/object_detection/meta_architectures/faster_rcnn_meta_arch.py", line 131, in extract_proposal_features/Documents/Custom-Object-Detection-master/object_detection/models/faster_rcnn_resnet_v1_feature_extractor.py", line 126, in _extract_proposal_features
return self._extract_proposal_features(preprocessed_inputs, scope)
File "
scope=var_scope)
File "/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 298, in resnet_v1_101/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 216, in resnet_v1
reuse=reuse, scope=scope)
File "
net = resnet_utils.stack_blocks_dense(net, blocks, output_stride)
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/Documents/Custom-Object-Detection-master/slim/nets/resnet_utils.py", line 185, in stack_blocks_dense
return func(*args, **current_args)
File "
net = block.unit_fn(net, rate=rate, **dict(unit, stride=1))
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/Documents/Custom-Object-Detection-master/slim/nets/resnet_v1.py", line 118, in bottleneck
return func(*args, **current_args)
File "
activation_fn=None, scope='conv3')
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1042, in convolution
return func(*args, **current_args)
File "
outputs = normalizer_fn(outputs, **normalizer_params)
File "/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 643, in batch_norm
return func(*args, **current_args)
File "
outputs = layer.apply(inputs, training=is_training)
File "/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 671, in apply/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 575, in call
return self.call(inputs, *args, **kwargs)
File "
outputs = self.call(inputs, *args, **kwargs)
File "/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 395, in call/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 302, in _fused_batch_norm
return self._fused_batch_norm(inputs, training=training)
File "
training, _fused_batch_norm_training, _fused_batch_norm_inference)
File "/lib/python2.7/site-packages/tensorflow/python/layers/utils.py", line 208, in smart_cond/lib/python2.7/site-packages/tensorflow/python/layers/normalization.py", line 299, in _fused_batch_norm_inference
return fn2()
File "
data_format=self._data_format)
File "/lib/python2.7/site-packages/tensorflow/python/ops/nn_impl.py", line 831, in fused_batch_norm/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2034, in _fused_batch_norm
name=name)
File "
is_training=is_training, name=name)
File "/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "
op_def=op_def)
File "~/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,1024,51,38]
[[Node: FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/FusedBatchNorm = FusedBatchNorm[T=DT_FLOAT, data_format="NHWC", epsilon=1.001e-05, is_training=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/Conv2D, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/gamma/read/_683, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/beta/read/_685, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_mean/read/_687, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_variance/read/_689)]]
[[Node: Reshape_24/_1255 = _HostRecvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4073_Reshape_24", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
I get the following error, when I run "python -m wml.start_training_run"
from object_detection.protos import string_int_label_map_pb2
training-UGIxBkrmR: ImportError: cannot import name 'string_int_label_map_pb2'
Any help? @bourdakos1
May you provide a complete example please?
I want to attempt to utilise your project but i feel intimidated by it. I would love a complete example so i can run through it to ensure i have everything set up correctly and see how it works before i start to play.
Ps. It looks like you have a spelling mistake on line 61 in the first sentence of your readme.md. It also looks like you've merged two sentences together. It's very minor.
I am geting this error:
"INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.NotFoundError'>,train.record; No such file or directory"
Please help.
using default config and model, while training:
Traceback (most recent call last):
File "object_detection/train.py", line 198, in
tf.app.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/home/santhosh/Documentsmns/object_detection/trainer.py", line 219, in train
init_saver = tf.train.Saver(available_var_map)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1239, in init
self.build()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1248, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1272, in _build
raise ValueError("No variables to save")
I thought the point of having an images folder and an annotations folder was that that was all the required information for the network to train. But looking at step 6 of
https://towardsdatascience.com/custom-object-detection-using-tensorflow-from-scratch-e61da2e10087
create_tf_record needs a trimaps folder as well. Also apparently create_tf_record is not compatible with jpg's? as it is only hardcoded to accept png's
I'm on Arch, so there could be any number of crazy problems. Followed all install instructions; while running train.py I receive:
Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model.ckpt
There is a tensorflow issue currently open regarding naming conventions, but even using the full path for all of the files I still get the same error. Any ideas?
When running train.py with the parameters given in the tutorial I get also a lot of the relative path warnings as documented in my other issue but train.py completely fails with the following last error messages (I did not post all the warnings before):
...
dyld: warning, LC_RPATH $ORIGIN/../../../../../_solib_darwin_x86_64/_U_S_Stensorflow_Scontrib_Stensor_Uforest_Cpython_Sops_S_Ustats_Uops.so___Utensorflow in /Users/jreich/Library/Python/2.7/lib/python/site-packages/tensorflow/contrib/tensor_forest/python/ops/_stats_ops.so being ignored in restricted program because it is a relative path
INFO:tensorflow:Scale of 0 disables regularizer.
INFO:tensorflow:Scale of 0 disables regularizer.
WARNING:tensorflow:From /Users/jreich/Downloads/Watson/Custom-Object-Detection-master/object_detection/trainer.py:176: create_global_step (from tensorflow.contrib.framework.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.get_or_create_global_step
INFO:tensorflow:Summary name Learning Rate is illegal; using Learning_Rate instead.
Traceback (most recent call last):
File "object_detection/train.py", line 198, in <module>
tf.app.run()
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/Users/jre/Downloads/Watson/Custom-Object-Detection-master/object_detection/trainer.py", line 218, in train
var_map, train_config.fine_tune_checkpoint))
File "/Users/jre/Downloads/Watson/Custom-Object-Detection-master/object_detection/utils/variables_helper.py", line 122, in get_variables_available_in_checkpoint
ckpt_reader = tf.train.NewCheckpointReader(checkpoint_path)
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 150, in NewCheckpointReader
return CheckpointReader(compat.as_bytes(filepattern), status)
File "/Users/jre/Library/Python/2.7/lib/python/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model.ckpt
[ /Users/jre/Downloads/Watson/Custom-Object-Detection-master ]
jre@ibm-jre-mbp ==_-+-
I interpret the error message that train.py is not able to find the files for the model. I checked the annotation files in "annotations/xmls" and found that there is different folder name given in all of them:
<folder>less_selected</folder>
But the "videoplayback####" JPGs are stored in the "images" folder ... Maybe this also causes trouble with "create_tf_record.py". But probably I am completely on the wrong track ;-)
jre@ibm-jre-mbp ==_-+- cat videoplayback0051.xml
<annotation>
<folder>less_selected</folder>
<filename>videoplayback0051.jpg</filename>
<size>
<width>1000</width>
<height>563</height>
</size>
<segmented>0</segmented>
<object>
<name>Tie Fighter</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>157</xmin>
<ymin>165</ymin>
<xmax>166</xmax>
<ymax>176</ymax>
</bndbox>
</object>
<object>
<name>Tie Fighter</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>136</xmin>
<ymin>151</ymin>
<xmax>145</xmax>
<ymax>160</ymax>
</bndbox>
</object>
</annotation>[ /Users/jre/Downloads/Watson/Custom-Object-Detection-master/annotations/xmls ]
jre@ibm-jre-mbp ==_-+-
I am using for python 2.7.10 which is the default version of my mac os sierra and the pip version is 9.0.1. I hope it is not a big deal to solve :-)
Seems like a disaster to label each frame by hand.
How can I get the org mp4? And could you provide script to produce a new labeled video from org? Thank you!
I only created the tfrecord files using my own dataset and changed num_classes in faster_rcnn_resnet101.config accordingly.
Then when I run the code, it raised the following error:
Caused by op u'save_1/Assign_815', defined at:
File "object_detection/train.py", line 198, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "object_detection/train.py", line 194, in main
worker_job_name, is_chief, FLAGS.train_dir)
File "/Custom-Object-Detection/object_detection/trainer.py", line 281, in train
keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1218, in init
self.build()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1227, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1263, in _build
build_save=build_save, build_restore=build_restore)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 751, in _build_internal
restore_sequentially, reshape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 439, in _AddRestoreOps
assign_ops.append(saveable.restore(tensors, shapes))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 160, in restore
self.op.get_shape().is_fully_defined())
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/state_ops.py", line 276, in assign
validate_shape=validate_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 57, in assign
use_locking=use_locking, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-accessInvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [584] rhs shape= [8]
[[Node: save_1/Assign_815 = Assign[T=DT_FLOAT, _class=["loc:@SecondStageBoxPredictor/BoxEncodingPredictor/biases"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](SecondStageBoxPredictor/BoxEncodingPredictor/biases/Momentum, save_1/RestoreV2_815)]]
It seems the model was restored failed. Besides, my own dataset has 146 classes, so it seems 584 = 146 * 4 is not equal the original 2 classes * 4 = 8.
Can the existing config for mobilenetv1 easily adapted to be used with the new mobilenetv2 /ssdlite?
@bourdakos1
hi,I've trained with my own dataset, and the result is just okay, so I wonder which aspect I can do some changes to finetune the model, such as: the optimizier, learning rate or other parameters, and how to change ?
thanks !
Hi Nick,
I was able to run the exact repo with your help. Thank you very much for your helps.
So, now, I need to apply the same exact steps to my images and xml files. I put my images to images folder. They are all ".jpg" though size is changing from 5-8 KB to 1400 KBs. I put the xmls in the annotations/xmls folder. I updated the trainval.txt, test_images folder, label_map.pbtxt. Everything is as it supposed to be.
However, I keep getting this error when I run the create_tf_record.py ("python object_detection/create_tf_record.py").
''' tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: images\armas1721 : The system cannot find the file specified.
; No such file or directory'''
The file exists, the folder exists. I am not sure why this error is popping up. I google'd around it but no solutions come up in the stackoverflow. I see people are posting the same error code, or similar error codes; have not seen a solution yet.
Does anyone know how to overcome this problem?
Thank you,
Selin
Compare to base model that i use for transfer learning, the model i extracted increases inference time after custom object training. is it th normal behaviour
I was able to generate my model and inference graph, but when it got down to going through the last step and running python3 ./object_detection/object_detection_runner.py I got this error:
root@ml-2:/home/science/Custom-Object-Detection# python3 ./object_detection/object_detection_runner.py
Loading model...
detecting...
2019-01-18 08:47:33.209893: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
detecting object in path: test_images/image-1.jpg
Traceback (most recent call last):
File "./object_detection/object_detection_runner.py", line 93, in <module>
detect_objects(image_path)
File "./object_detection/object_detection_runner.py", line 59, in detect_objects
fig = plt.figure()
File "/usr/local/lib/python3.5/dist-packages/matplotlib/pyplot.py", line 535, in figure
**kwargs)
File "/usr/local/lib/python3.5/dist-packages/matplotlib/backends/backend_tkagg.py", line 81, in new_figure_manager
return new_figure_manager_given_figure(num, figure)
File "/usr/local/lib/python3.5/dist-packages/matplotlib/backends/backend_tkagg.py", line 89, in new_figure_manager_given_figure
window = Tk.Tk()
File "/usr/lib/python3.5/tkinter/__init__.py", line 1871, in __init__
self.tk = _tkinter.create(screenName, baseName, className, interactive, wantobjects, useTk, sync, use)
_tkinter.TclError: no display name and no $DISPLAY environment variable
I've been following the steps laid out in this tutorial: https://medium.freecodecamp.org/tracking-the-millenium-falcon-with-tensorflow-c8c86419225e so all the test images that I've been training on and are trying to call the runner on are pointing to the same three test images that are in this project.
Any ideas on why this error is occurring? I tried googling it but didn't find much that seemed applicable.
Hi,
I'm not sure what am i missing in here, I just followed your tutorial in here 'https://medium.freecodecamp.org/tracking-the-millenium-falcon-with-tensorflow-c8c86419225e'
When i try to run the 'create_tf_record.py' from PyCharm i get the below error,
but at the same time i can run the 'create_tf_record.py' file from terminal.
Can you please point me, what do i miss in here !!! Thanks in advance buddy.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.