New answers tagged

0

Something that I personally use is Google Trends. This is a very useful tool for verifying the interest of a broad public on some subject. Results can even be refined to include region and/or time span. For instance, here you can see a comparison for the interest in Tensorflow, Keras and Pytorch over the past 12 months:


1

There is no label for such bounding boxes, they are simply "ignored" during training. You can assign any value for their "labels", then multiplying what ever loss these boxes generated with 0. If there is no loss, there is no gradient from these boxes. You can do that by defining a count_boxes vector with binary values. Object and ...


0

the answer is adding lambda inputs: inputs["your_key_for_observation"] to the network in case someone encounters this issue in the future


0

The problem is in this line restnet = Model(restnet.input,output) if you removed it everything should work fine. I don't know the model architecture that you are working on, but what is suggested is to build a model and put ResNet ahead on this model, or you can just call the ResNet as above and build your own network regardless of the API (functional, ...


0

You just missed the argument "scores" when calling the function. Your 4th argument is supposed to be scores and 5th argument is supposed to be category_index. You missed the forth one. The function is defined here. https://github.com/tensorflow/models/blob/4fd1790ec35964cebd0d92355486c5f9dfe8fa71/research/object_detection/utils/visualization_utils....


3

Yes, this is quite the expected behavior. The main difference between expected and current behavior lies in the amount of data you are using for training VS the amount of data that the pre-trained model was trained with. Take into account that pre-trained models have been trained over popular datasets, the most common ones are: COCO, ImageNet and Open Images....


Top 50 recent answers are included