autograph | A utility that creates dot graphs from .NET projects | Animation library

I try to create a new tensor based on a dictionary that maps 1 to 1 the values from a tensor to some other value (the example below is trivial on purpose), and i get the error "TypeError: Tensor is unhashable. Instead, use tensor.ref() as the key." - even though I do not use Tensors as keys in the dictionary, i convert them to int before:

I am trying to train my model (Image classification) using Tensorflow. I keep getting an error when I try to run the following cell:

I would like to extract the derivatives of a Tensorflow model with respect to its input using autograph for speed, but for some reason autograph gives an error. Here is the function that I am using:

I have a model in keras which takes two inputs and it returns 3 outputs and I want to compute a custom loss. The problem I have is that I don't know how to use the output of intermediate layers in the loss. So far the model consisted of two submodels (submodel1 and submodel2 in the picture) and the final loss consisted of the sum of loss1 and loss2. This was easy because loss1 compared output1 with label1 of the data generator and output2 with label2 of the data generator.

The problem comes when I include the submodel3 in the model, because the loss3 compares the output1 with the output3, being output1 the output of a layer of the model, and not the one that would be the label3 of the data generator. I have tried this way:

I followed the "Training Custom Object Detector" tutorial (https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html)

When running the script to continue training a pre-trained model:

python model_main_tf2.py --model_dir=models/my_ssd_resnet50_v1_fpn --pipeline_config_path=models/my_ssd_resnet50_v1_fpn/pipeline.config

(found here: https://github.com/tensorflow/models/blob/master/research/object_detection/model_main_tf2.py)

Using different numpy versions, I get the following errors.

Scenario #1:

• tensorflow: 2.2.0
• numpy: 1.20.0-1

NotImplementedError: Cannot convert a symbolic Tensor (cond_2/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported

I looked online and it suggests to downgrade the numpy version < 1.20.0 (NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array). Note, the version numpy version must be >= 1.19.2 for tensorflow 2.2.0.

Scenario #2:

• tensorflow: 2.2.0
• numpy: 1.19.2-5

ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject

However, the online recommendation is to upgrade numpy to >= 1.20.0. (ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject). There is a github issue related to this: https://github.com/tensorflow/models/issues/9749.

I'm not sure what version to use to get the code running.

Appendix: Scenario #1 Error Code (numpy: 1.20.0-1)

I'm doing a sentiment analysis on the IMDB dataset in tensorflow and I'm trying to augment the training dataset by using the textaugment library which they said is 'plug and play' into tensorflow. So it should be rather simple, but I'm new to tf so I'm not sure how to go about doing that. Here is what I have and what I am trying, based on reading the tutorials on the site.

I tried to do a map to augment the training data but I got an error. You can scroll down to the last code block to see the error.

I am building a CNN for a multi class audio classification problem. I have extracted the spectrogram features from my audio files and I am trying to pass the 4D array to my CNN. I have also performed One-Hot Encoding for my labels. But I don't understand why exactly I get this ValueError. Kindly , Help.

This is my code:

I am having problems with tf.function in tensorflow. It seems to fail to convert functions containing the instruction tf.stack().

Here a simple code I wrote to highlight the issue:

I am trying to import a directory full of images into Tensorflow and then use it for Keras Tuner. The problem is Keras Tuner requires the data to be split into images and labels. I was following a guide on Tensorflow's website and here is the code I have so far:

NOTE: I am using the COCO dataset meaning each image has multiple labels. Maybe that is the problem.