Shuhul24

Does neural-tangents work for custom layer?

1

I have built a custom layer (`KerasLayer`) using `class` in python (say `class NewLayer`). Can I use something like `stax.NewLayer` for manipulating `neural-tangents` on this custom layer?

what is in `./assets/scannet_test_pairs_with_gt.txt`?

2

So actually the file `./assets/scannet_test_pairs_with_gt.txt` consists of image pairs with ground truth values. Can someone help me figure out what those ground truth values correspond to? I mean the format...

While I am training the SuperGlue model, I am using SIFT detector based keypoints [from [Github repo](https://github.com/yingxin-jia/SuperGlue-pytorch)]. But the scores values in it appears to be very less (like somewhere...

Loss function

2

If I am supposed to train the SuperGlue model on my own custom dataset, what should be the loss function? Where is it employed or integrated in the code?

I have trained the model and now I want to check how does the model perform on my test dataset. But while training I check that the model does not...

While running the script by @skylook in the [repo](https://github.com/skylook/SuperGlue/tree/master), following error occurs constantly ```python Traceback (most recent call last): File "/home/shuhulh/superglue_train/train.py", line 180, in for i, pred in enumerate(train_loader): File...

I am training the model on my dataset instead of what is mentioned on the github repository (COCO, etc.). While training following error occured: ```python Traceback (most recent call last):...

Error with encoding data.

3

Is it possible to encode data with less dimension than the number of qubits used? I am building a circuit in which I am using a circuit with qubits `[cirq.GridQubit(1,...

Can't measure the fidelity of the states.

27

I have measure the quantum states using `tfq.layers.State()`. The output of `tfq.layers.State()` is of the form `tf.RaggedTensor`. Now I have measured two different states, using the same method. (say state1...