I'm using Tensorflow 2 Model Maker to perform transfer training of EfficientDet-Lite (ultimately to run on a Coral EdgeTPU) and I care much more about the classification output and much less about the precision of the bounding boxes. Is there a way to modify some training parameters to improve the accuracy of the classes at the expense of the accuracy of the bounding boxes? Or does this not make sense?
1
There are 1 best solutions below
Related Questions in TENSORFLOW
- (Tensorflow)Does the op assign change the gradient computation?
- Tensorflow Windows Accessing Folders Denied:"NewRandomAccessFile failed to Create/Open: Access is denied. ; Input/output error"
- Android App TensorFlow Google Cloud ML
- Convert Tensorflow model to Caffe model
- Google Tensorflow LSTMCell Variables Mapping to Hochreiter97_lstm.pdf paper
- additive Gaussian noise in Tensorflow
- TFlearn evaluate method results meaning
- Regularization losses Tensorflow - TRAINABLE_VARIABLES to Tensor Array
- feed picture to model tensorflow for training
- Fail to read the new format of tensorflow checkpoint?
- I got a error when running a github project in tensorflow
- Tensorflow R0.12 softmax_cross_entropy_with_logits ASSERT Error
- RuntimeError in run_one_batch of TensorFlowDataFrame in tensorflow
- Same output in neural network for each input after training
- ConvNet : Validation Loss not strongly decreasing but accuracy is improving
Related Questions in TENSORFLOW2.0
- TF2.3 load subclassing model with tf.feature_column get ValueError: Could not find matching function to call loaded from the SavedModel
- Validation loss become nan while training on TPU but perfectly ok on GPU
- Is there any solution for failing to load model in tensorflow2.3?
- How do I call ExampleValidator to analyze split data sets?
- Tensorflow: convert PrefetchDataset to BatchDataset
- TypeError: '...' has type str, but expected one of: bytes
- Convert range index to coordinates in tensorflow
- AttributeError: 'Concatenate' object has no attribute 'shape'
- Implementing Transfer Learning using Pegasus for Text Summarization generating junk characters
- saturated contrast and low brightness in tensorboard when training TF2 object_detection API
- On the use of Batch Normalization
- Why isn't SchemaGen supported in tfdv.display_schema()?
- "tensorflow.python.framework.errors_impl.FailedPreconditionError" while running "model_main_tf2.py" for training object detection model in tensorflow
- What is the fast way to get tensorflow universal sentence embeddings on large corpus?
- AttributeError: module 'keras.backend' has no attribute 'common'
Related Questions in TENSORFLOW-LITE
- Issue in creating Tflite model populated with metadata (for object detection)
- What is a lite model in Deep Learning?
- Unable to Import tflite-support package. Receiving error "DLL load failed: The specified module could not be found"
- Google Meet background Blur
- Error when training Tensorflow image classification model even when all images in jpeg format. Anyone have a fix?
- How to remove background from an image using TensorFlow Lite?
- How to convert Tensorflow Object Detection API model to TFLite?
- Export data from PoseNet app by tensorflow-lite in android
- Passing custom attributes from TF op to TFL (MLIR)
- Building libtensorflowlite.so without any error, but share file is close to empty (KB)
- tensorflow Lite Segmentation fault
- How to find the Tensorflow node with a given index?
- What's the output of YOLO?
- How to Fix ERROR: Command errored out with exit status 1: when installing tensorflow_recommenders using pip
- TensorFlow Lite does not recognize op VarHandleOp
Related Questions in EDGE-TPU
- Can You Mesh Network Google Coral TPUs
- ValueError: None is only supported in the 1st dimension. Tensor 'input_tensor' has invalid shape '[1, None, None, 3]'
- How to read TPU consumption during inferencing on edge devices?
- How to solve Runtime Error: Empty min/max for tensor Cast while doing post-training quantization (fully quantized tflite model from saved_model)?
- How to fetch TPU utilization details in coral developer board using tflite_runtime or linux command
- Converting SSD object detection model to TFLite and quantize it from float to uint8 for EdgeTPU
- Speed Up Multiple Model Inference on EDGE TPU
- Facing such problem like no model name edge tpu found and no module name edgeTPU_cpp_wrapper
- Google Coral: Is there a limit to model size?
- Does edge TPU support 1D convolution?
- running inference on coral edgetpu generates IndexError: index 10 is out of bounds for axis 0 with size 10
- Is there an alternative to the cv2.resize() function that is faster at upscaling an image?
- tflite quantized mobilenet v2 classifier not working
- Convert SSD MobileNetV2 custom model to edgetpu model?
- Compile a TF Javascript model for Google Coral Edge TPU module
Trending Questions
- UIImageView Frame Doesn't Reflect Constraints
- Is it possible to use adb commands to click on a view by finding its ID?
- How to create a new web character symbol recognizable by html/javascript?
- Why isn't my CSS3 animation smooth in Google Chrome (but very smooth on other browsers)?
- Heap Gives Page Fault
- Connect ffmpeg to Visual Studio 2008
- Both Object- and ValueAnimator jumps when Duration is set above API LvL 24
- How to avoid default initialization of objects in std::vector?
- second argument of the command line arguments in a format other than char** argv or char* argv[]
- How to improve efficiency of algorithm which generates next lexicographic permutation?
- Navigating to the another actvity app getting crash in android
- How to read the particular message format in android and store in sqlite database?
- Resetting inventory status after order is cancelled
- Efficiently compute powers of X in SSE/AVX
- Insert into an external database using ajax and php : POST 500 (Internal Server Error)
Popular Questions
- How do I undo the most recent local commits in Git?
- How can I remove a specific item from an array in JavaScript?
- How do I delete a Git branch locally and remotely?
- Find all files containing a specific text (string) on Linux?
- How do I revert a Git repository to a previous commit?
- How do I create an HTML button that acts like a link?
- How do I check out a remote Git branch?
- How do I force "git pull" to overwrite local files?
- How do I list all files of a directory?
- How to check whether a string contains a substring in JavaScript?
- How do I redirect to another webpage?
- How can I iterate over rows in a Pandas DataFrame?
- How do I convert a String to an int in Java?
- Does Python have a string 'contains' substring method?
- How do I check if a string contains a specific word?
Unfortunately, TensorFlow 2 Model Maker doesn't support such customization at this moment.
If you want to do so, you can bypass Model Maker and directly use AutoML repo. The technical detail is to adjust weights for different losses by adding
loss_weightsincompile()function.