tensorboard | Standalone TensorBoard for visualizing in deep learning | Machine Learning library

I am currently working on building a CNN for sound classification. The problem is relatively simple: I need my model to detect whether there is human speech on an audio record. I made a train / test set containing records of 3 seconds on which there is human speech (speech) or not (no_speech). From these 3 seconds fragments I get a mel-spectrogram of dimension 128 x 128 that is used to feed the model.

Since it is a simple binary problem I thought the a CNN would easily detect human speech but I may have been too cocky. However, it seems that after 1 or 2 epoch the model doesn’t learn anymore, i.e. the loss doesn’t decrease as if the weights do not update and the number of correct prediction stays roughly the same. I tried to play with the hyperparameters but the problem is still the same. I tried a learning rate of 0.1, 0.01 … until 1e-7. I also tried to use a more complex model but the same occur.

Then I thought it could be due to the script itself but I cannot find anything wrong: the loss is computed, the gradients are then computed with backward() and the weights should be updated. I would be glad you could have a quick look at the script and let me know what could go wrong! If you have other ideas of why this problem may occur I would also be glad to receive some advice on how to best train my CNN.

I based the script on the LunaTrainingApp from “Deep learning in PyTorch” by Stevens as I found the script to be elegant. Of course I modified it to match my problem, I added a way to compute the precision and recall and some other custom metrics such as the % of correct predictions.

Here is the script:

heyy guys im beginner at deep learning and currently trying basic cnn that i found to make model

but i got some error that said

...

I'm implementing SRGAN (and am not very experienced in this field), which uses a pre-trained VGG19 model to extract features. The following code was working fine on Keras 2.1.2 and tf 1.15.0 till yesterday. then it started throwing an "AttributeError: module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects'" So i updated the keras version to 2.4.3 and tf to 2.5.0. but then its showing a "Input 0 of layer fc1 is incompatible with the layer: expected axis -1 of input shape to have value 25088 but received input with shape (None, 32768)" on the following line

Background

I am totally new to Python and to machine learning. I just tried to set up a UNet from code I found on the internet and wanted to adapt it to the case I'm working on bit for bit. When trying to .fit the UNet to the training data, I received the following error:

I am running a tensorflow model on google colab. Today, I got this error:

I want to show my embeddings with the tensorboard projector. I would like to access the embeddings matrix (lookup table) of one of my layers so I can write it to the logs.

I instantiate my layer as this:

self.embeddings_user = torch.nn.Embedding(30,300)

And I'm looking for the tensor with shape (30,300) of 30 users with embedding on 300 to dimensions to replace it with the vectors variable in this sample code:

I have a Convolutional neural network (VGG16) that performs well on a classifying task on 26 image classes. Now I want to visualize the data distribution with t-SNE on tensorboard. I removed the last layer of the CNN, therefore the output is the 4096 features. Because the classification works fine (~90% val_accuracy) I expect to see something like a pattern in t-SNE. But no matter what I do, the distribution stays random (-> data is aligned in a circle/sphere and classes are cluttered). Did I do something wrong? Do I misunderstand t-SNE or tensorboard? It´s my first time working with that.

Here´s my code for getting the features:

I am attempting to run a crowd estimation model that classifies the images into three different broad categories depending on how many people there are in the images. 1200 images are used for training, with 20% of it used for validation. I used sentdex's tutorial on Youtube as reference to load the image data into the model; I load the images as a zip file, extract it and categorise them based on the folders they are in.

My issue is that whenever I attempt to train the model, I noticed that the loss and validation loss is always 0, which has resulted in the model not exactly training and the validation accuracy remaining the same throughout, as seen here. How can I get the loss to actually change? Is there something I am doing wrong in terms of implementation?

So far, what I have attempted is:

1. I tried to add a third convolutional layer, with little results.
2. I have also tried to change the last Dense layer to model.add(Dense(3)), but I got an error saying "Shapes (None, 1) and (None, 3) are incompatible"
3. I tried using a lower learning rate (0.001?), but the model ended up returning a 0 for validation accuracy
4. Changing the optimizer did not seem to generate any changes for me

Below is a snippet of my code so far showing my model attempt:

I am trying to optimise the learning_rate parameter of my ML-model with a while-loop. The first model completes all of its learning steps, however, the in the second iteration of the while-loop and thus the second call of model.fit() fails already in the first epoch. No output is generated.

Edit:
I have traced the problem to the Tensorboard callback. Without that call-back the loop successfully trains all 4 models, while with the callback the loop fails at the beginning of the second iteration/model fit. What am I doing wrong here?