python mo_tf.py
--saved_model_dir C:\DATASETS\mask50000\exports\saved_model
--output_dir C:\DATASETS\mask50000
--reverse_input_channels
--tensorflow_custom_operations_config extensions\front\tf\mask_rcnn_support_api_v2.0.json
--tensorflow_object_detection_api_pipeline_config C:\DATASETS\mask50000\exports\pipeline.config
--log_level=DEBUG
I have been trying to convert the model using the above script, but every time I got the error:
"Exception: Exception occurred during running replacer "REPLACEMENT_ID (<class'extensions.front.tf.tensorflow_custom_operations_config_update.TensorflowCustomOperationsConfigUpdate'>)": The function 'update_custom_layer_attributes' must be implemented in the sub-class."
I have exported the graph using exporter_main_v2.py. If more information is needed please inform me.
EDIT:
I was able to convert the model by changing the file mask_rcnn_support_api_v2.4.json.
first change:
"custom_attributes": {
"operation_to_add": "Proposal",
"clip_before_nms": false,
"clip_after_nms": true
}
second change:
"start_points": [
"StatefulPartitionedCall/concat/concat",
"StatefulPartitionedCall/concat_1/concat",
"StatefulPartitionedCall/GridAnchorGenerator/Identity",
"StatefulPartitionedCall/Cast",
"StatefulPartitionedCall/Cast_1",
"StatefulPartitionedCall/Shape"
]
that solved the problme.
OpenVINO 2020.4 is not compatible with TensorFlow 2. Support for TF 2.0 Object Detection API models was fully enabled only in OpenVINO 2021.3.
I’ve successfully converted the model mask_rcnn_inception_resnet_v2_1024x1024_coco17 to IR using the latest OpenVINO release (2021.4.752).
I share the MO conversion command here:
python mo_tf.py --saved_model_dir <model_dir>\saved_model --tensorflow_object_detection_api_pipeline_config <pipeline_dir>\pipeline.config --transformations_config <installed_dir>\extensions\front\tf\mask_rcnn_support_api_v2.0.json"
Related
i git yolov7(https://github.com/WongKinYiu) with yolov7.pt and try to run
detect.py(i just want to run the example). it seems to be normal. but the output image has no mask.Why?
here is my code and log:
(PyTorch) E:\yolov7>python detect.py --weights yolov7.pt --source inference\images\bus.jpg
Namespace(weights=['yolov7.pt'], source='inference\\images\\bus.jpg', img_size=640, conf_thres=0.25, iou_thres=0.45, device='', view_img=False, save_txt=False, save_conf=False, nosave=False, classes=None, agnostic_nms=False, augment=False, update=False, project='runs/detect', name='exp', exist_ok=False, no_trace=False)
YOLOR v0.1-103-g6ded32c torch 1.11.0 CUDA:0 (NVIDIA GeForce GTX 1650, 4095.6875MB)
Fusing layers...
RepConv.fuse_repvgg_block
RepConv.fuse_repvgg_block
RepConv.fuse_repvgg_block
Model Summary: 306 layers, 36905341 parameters, 6652669 gradients
Convert model to Traced-model...
traced_script_module saved!
model is traced!
E:\anaconda\envs\PyTorch\lib\site-packages\torch\functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Done. (151.6ms) Inference, (9.3ms) NMS
The image with the result is saved in: runs\detect\exp4\bus.jpg
Done. (3.713s)
and here is my result:output image
You set the argument classes=None.
The classes variable refers to a list of classes, where you define the index of the entities saved inside the weights you are referencing for the inference.
From detect.py:
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
Since you told the model to check for zero classes, the model itself will not report anything.
I was also facing this issue. After downgrading cuda version to 10.2 my problem was solved. I used Cuda 10.2 with PyTorch 1.10.0 via pip installation. I hope it helps you too.
pip3 install torch==1.10.0+cu102 torchvision==0.11.1+cu102 torchaudio===0.10.0+cu102 -f https://download.pytorch.org/whl/cu102/torch_stable.html
Source of the answer: link
Since when you are working with GPU, It allows half precision by default, which you can change by editing your detect.py file.
Go to detect.py file and not exactly sure but on line 31, you will see this line of code:
half = device.type != 'cpu' # half precision only supported on CUDA
Replace that line with
half = False
and then save default.py file.
Now when you are using your detection command, make sure to use --device 0 that indicates your GPU must be utilize for detection.
python detect.py --weights yolov7.pt --device 0 --source inference\images\bus.jpg
I need to run a custom GluonCV object detection module on Android.
I already fine-tuned the model (ssd_512_mobilenet1.0_custom) on a custom dataset, I tried running inference with it (loading the .params file produced during the training) and everything works perfectly on my computer. Now, I need to export this to Android.
I was referring to this answer to figure out the procedure, there are 3 suggested options:
You can use ONNX to convert models to other runtimes, for example [...] NNAPI for Android
You can use TVM
You can use SageMaker Neo + DLR runtime [...]
Regarding the first one, I converted my model to ONNX.
However, in order to use it with NNAPI, it is necessary to convert it to daq. In the repository, they provide a precomplied AppImage of onnx2daq to make the conversion, but the script returns an error. I checked the issues section, and they report that "It actually fails for all onnx object detection models".
Then, I gave a try to DLR, since it's suggested to be the easiest way.
As I understand, in order to use my custom model with DLR, I would first need to compile it with TVM (which also covers the second point mentioned in the linked post). In the repo, they provide a Docker image with some conversion scripts for different frameworks.
I modified the 'compile_gluoncv.py' script, and now I have:
#!/usr/bin/env python3
from tvm import relay
import mxnet as mx
from mxnet.gluon.model_zoo.vision import get_model
from tvm_compiler_utils import tvm_compile
shape_dict = {'data': (1, 3, 300, 300)}
dtype='float32'
ctx = [mx.cpu(0)]
classes_custom = ["CML_mug"]
block = get_model('ssd_512_mobilenet1.0_custom', classes=classes_custom, pretrained_base=False, ctx=ctx)
block.load_parameters("ep_035.params", ctx=ctx) ### this is the file produced by training on the custom dataset
for arch in ["arm64-v8a", "armeabi-v7a", "x86_64", "x86"]:
sym, params = relay.frontend.from_mxnet(block, shape=shape_dict, dtype=dtype)
func = sym["main"]
func = relay.Function(func.params, relay.nn.softmax(func.body), None, func.type_params, func.attrs)
tvm_compile(func, params, arch, dlr_model_name)
However, when I run the script it returns the error:
ValueError: Model ssd_512_mobilenet1.0_custom is not supported. Available options are
alexnet
densenet121
densenet161
densenet169
densenet201
inceptionv3
mobilenet0.25
mobilenet0.5
mobilenet0.75
mobilenet1.0
mobilenetv2_0.25
mobilenetv2_0.5
mobilenetv2_0.75
mobilenetv2_1.0
resnet101_v1
resnet101_v2
resnet152_v1
resnet152_v2
resnet18_v1
resnet18_v2
resnet34_v1
resnet34_v2
resnet50_v1
resnet50_v2
squeezenet1.0
squeezenet1.1
vgg11
vgg11_bn
vgg13
vgg13_bn
vgg16
vgg16_bn
vgg19
vgg19_bn
Am I doing something wrong? Is this thing even possible?
As a side note, after this I'd need to deploy on Android a pose detection model (simple_pose_resnet18_v1b) and an activity recognition one (i3d_nl10_resnet101_v1_kinetics400) as well.
You actually can run GluonCV model directly on Android with Deep Java Library (DJL)
What you need to do is:
hyridize your GluonCV model and save as MXNet model
Build MXNet engine for android, MXNET already support Android build
Include MXNet shared library into your android project
Use DJL in your android project, you can follow this DJL Android demo for PyTorch
The error message is self-explanatory - there is no model "ssd_512_mobilenet1.0_custom" supported by mxnet.gluon.model_zoo.vision.get_model. You are confusing GluonCV's get_model with MXNet Gluon's get_model.
Replace
block = get_model('ssd_512_mobilenet1.0_custom',
classes=classes_custom, pretrained_base=False, ctx=ctx)
with
import gluoncv
block = gluoncv.model_zoo.get_model('ssd_512_mobilenet1.0_custom',
classes=classes_custom, pretrained_base=False, ctx=ctx)
I want to convert my 1 tensorflow model to IR currently I am following the instructions here:
https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html
The model I use is meta graph and ubuntu 16.04
I ran the line deflected:
python3 mo_tf.py --input_meta_graph .meta
then it will get an error:
[ERROR] Exception occurred during running replacer "None" (): Data flow edge coming out of AssignSub node model_0 / resnet_v1_50 / block4 / unit_1 / bottleneck_v1 / shortcut / BatchNorm / AssignMovingAvg
Can you guys please help me? thanks everyone
Did you freeze the model before conversion? Please look at how to freeze your model using instructions from https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py and retry.
Running this example on ML engine using Cloud composer but am receiving the following error:
AttributeError: 'module' object has no attribute 'estimator'
Even though I am importing import tensorflow as tf and it exits on the following line:
estimator = tf.estimator.Estimator(model_fn = image_classifier,
Runtime version is 1.8 similar to the version using the repo.
t3 = MLEngineTrainingOperator(
task_id='ml_engine_training_op',
project_id=PROJECT_ID,
job_id=job_id,
package_uris=["gs://us-central1-ml/trainer-0.1.tar.gz"],
training_python_module=MODULE_NAME,
training_args=training_args,
region=REGION,
scale_tier='BASIC_GPU',
runtimeVersion = '1.8',
dag=dag
)
Please check the setup.py, make sure you put tensorflow in it as
REQUIRED_PACKAGES = ['tensorflow==1.8.0']. or some other version. Then don't forget to re-generate tar and upload.
Also, in my case, MLEngineTrainingOperator doesn't seem to pick runtime_version or python_version at all into ML Engine.
I am preparing a custom model to run on android phone using instructions from https://www.tensorflow.org/mobile/prepare_models
First i retrained the model on custom images using below command:
$ python tensorflow/examples/image_retraining/retrain.py --image_dir tensorflow/examples/image_retraining/my_images/ --learning_rate=0.0005 --testing_percentage=15 --validation_percentage=15 --train_batch_size=32 --validation_batch_size=-1 --flip_left_right True --random_scale=30 --random_brightness=30 --eval_step_interval=100 --how_many_training_steps=100 --tfhub_module https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/feature_vector/1
and as next step, I tested the model using label_image.py which also works fine in predicting the input image. However, freeze_graph gives error
$ bazel-bin/tensorflow/python/tools/freeze_graph --input_graph=/tmp/output_graph.pb --output_graph=/tmp/frozen_graph.pb
However, I keep getting this error.
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position
57: invalid start byte
I noticed that your --input_graph=/tmp/output_graph.pb. Is your graph written as binary file (as_text=False), instead of pbtxt? If so, you will need to pass the --input_binary=true flag to freeze_graph.
if you write your graph as a binary file using:
tf.train.write_graph(sess.graph_def, 'tarinGraph', 'train2.pbtxt', as_text=False)
then you will need to pass the --input_binary=true flag to freeze_graph.