models

models copied to clipboard

A curious phenomenon in image retrieval

3

I do image retrieval task with `--use_geometric_verification` on the code `perform_retrieval.py` in `delg` folder. To compare different local feature, I tried to replace the local feature of delg with Superpoint....

aruba01

Default learning rate in TF2 SSD MobileNet V2 config file is way too high. Is it a typo?

4

The learning rate set in the [TF2 SSD MobileNet V2 config file](https://github.com/tensorflow/models/blob/master/research/object_detection/configs/tf2/ssd_mobilenet_v2_320x320_coco17_tpu-8.config) is 10x higher than that of the other SSD MobileNet models. This causes loss during training to get...

EdjeElectronics

Seq flow lite does not build

22

# Prerequisites Please answer the following questions for yourself before submitting an issue. - [x ] I am using the latest TensorFlow Model Garden release and TensorFlow 2. Latest version...

grofte

[Help wanted] RoBERTa: A Robustly Optimized BERT Pretraining Approach

6

# Help wanted: Research paper code and models Please help us to implement the following research paper using TensorFlow 2. If you want to contribute, please leave a comment to...

jaeyounkim

Overfitting model and EarlyStopping

2

# Prerequisites Please answer the following question for yourself before submitting an issue. - [ ] I checked to make sure that this feature has not been requested already. ##...

Hikozume

Object Detection on Grayscale Images

4

Hi, I trained a MobileNet model on grayscale Images. I was wondering, what happens under the hood as MobileNet only works with 3 Channel images? Does the object detection API...

seboz123

TypeError: create_estimator_and_inputs() missing 1 required positional argument: 'hparams'

2

# Prerequisites Please answer the following question for yourself before submitting an issue. - [x] I checked to make sure that this issue has not been filed already. ## 1....

PiotrG1996

Which 32 classes in ADE20k is used to train deeplabv3plus_mobilenet_edgetpuv2?

2

https://github.com/tensorflow/models/blob/master/official/projects/edgetpu/vision/README.md I am trying to generate mIOU for deeplabv3plus_mobilenet_edgetpuv2_m on ADE20k 32 classes dataset, however, the [official segmentation mask for ADE20k](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip) contains 150 classes. Please provide a text file containing...

nnami21

Will mtop dataset and model code be published?

2

The website was published as: And I wonder will this project be published? and when?

PolarisRisingWar

train a model without axis aligned bounding boxes

1

Hi guys, I am using the ssd_mobilenet_v2 to train it for my purposes. I noticed that the network only generates axis-aligned bounding boxes. Is it now not possible to use...

Petros626