Welcome To Ask or Share your Answers For Others

Recent questions tagged Deep

0 votes

1.2k views

1 answer

deep learning - Why do we "pack" the sequences in PyTorch?

I was trying to replicate How to use packing for variable-length sequence inputs for rnn but I guess I ... explanation would be appreciated! See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - How to speed up Gensim Word2vec model load time?

I'm building a chatbot so I need to vectorize the user's input using Word2Vec. I'm using a pre-trained model with ... me it's not a good idea. See Question&Answers more detail:os...

asked Oct 17, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

972 views

1 answer

deep learning - What is a good outdoor camera model for a "camera trap" used to collect data for DL training?

I'm looking for "semi-smart" cameras that suit my needs for collecting training images that will later be used to train ... -camera-model-for-a-camera-trap-used-to-collect-data-for...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

deep learning - YOLO - change parameters for multi gpu

The goal is to train YOLO with multi-GPU. According to Darknet AlexeyAB, we should train YOLO with ... stackoverflow.com/questions/65838473/yolo-change-parameters-for-multi-gpu...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

deep learning - Use an Attention model for Fashion image Category Classification

To classify fashion image's categories without their attributes, can we use any attention mechanisms along with ... use-an-attention-model-for-fashion-image-category-classification...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - does tensor label for loss calculation in crossentropy must has dtype? why my obejct has no dtype?

I created a custom dataset, and I'm wondering why the answer object has no data type? the dataloader singel output ... for-loss-calculation-in-crossentropy-must-has-dtype-why-my-ob...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.5k views

1 answer

deep learning - Pytorch/cuda : CPU error and map_location

I write this code to download my model : args = parser.parse_args() use_cuda = torch.cuda.is_available() ... .com/questions/65842425/pytorch-cuda-cpu-error-and-map-location...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - How can I create a pbtxt file from just the frozen graph and checkpoint files? I do not have any config file( .config )

I want to use the dnn module "cv2.dnn" to load model so I need the frozen file and the config pbtxt file but ... -a-pbtxt-file-from-just-the-frozen-graph-and-checkpoint-files-i...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - How to minimise loss with constrain in PyTorch?

How to put constrain while minimising loss? I am trying to minimise the mse loss with constrain loss but ... /questions/65860855/how-to-minimise-loss-with-constrain-in-pytorch...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - Artificial neural network written from scratch in C++ stuck on maximal possible output

I'm creating ANN from scratch to better understand how it works. It is supposed to take numerical inputs from ... -network-written-from-scratch-in-c-stuck-on-maximal-possible...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - Why does CNN ignore some input images?

I am working on a super-resolution problem for downscaling of the responses fields of a dynamical system y=f(x ... .com/questions/65878616/why-does-cnn-ignore-some-input-images...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - Weight and bias initialization in neural networks

What is going to happen in a neural network when all the weights and biases are initialized to zero, ... .com/questions/65882188/weight-and-bias-initialization-in-neural-networks...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

deep learning - Error with layers compatibility using vgg-net

Good day. Attempt to compile main.py code from and get these errors: screenshot1 screenshot2 screenshot3 ... questions/65883883/error-with-layers-compatibility-using-vgg-net...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

970 views

1 answer

deep learning - tensorflow models/face landmarksdetection

I am very new to these topics. I was wondering if I can install this model/library on ... https://stackoverflow.com/questions/65884840/tensorflow-models-face-landmarksdetection...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - i am doing project on image captioning using cnn and lstm i got error

InvalidArgumentError: Matrix size-incompatible: In[0]: [47,1000], In[1]: [4096,256] [[node model_1/dense_4/Relu ... -project-on-image-captioning-using-cnn-and-lstm-i-got-error...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep linking - Flutter Application Won't Verify App Link On Android

I'm trying to have my application use app links, but even though I went through all the steps and my ... com/questions/65915334/flutter-application-wont-verify-app-link-on-android...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - Pytorch already installed using Conda but fails when called

I am trying to install pytorch for using BERT but when following the installation instructions found here: https: ... /pytorch-already-installed-using-conda-but-fails-when-called...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - GradCam for keras tensorflow 2

I'm working on GradCam from my previous version of the code that works. However, after i updated ... //stackoverflow.com/questions/65921392/gradcam-for-keras-tensorflow-2...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

deep learning - How to integrate custom layer implemented with CuPy in a tensorflow model?

I found a layer (separable convolution) implemented in CuPy. This layer was developed as a part of a pytorch ... -integrate-custom-layer-implemented-with-cupy-in-a-tensorflow-model...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - How CNN pooling layer is different from Encoder in Autoencoders?

An autoencoder is used for image compression and dimensionality reduction. The encoder does the compression of the ... -cnn-pooling-layer-is-different-from-encoder-in-autoencoders...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - Using output of first model as input to the other

How to use the output of my own trained model as an input to the already trained model. is it possible to ... questions/65933969/using-output-of-first-model-as-input-to-the-other...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - Why is 1x1 conv same as fully connected layer?

i am currently reading " Network in Network' paper. And in the paper, it is stated that "the cross channel ... /questions/65937119/why-is-1x1-conv-same-as-fully-connected-layer...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.0k views

1 answer

deep learning - Explain concept of instantiating a model with another model as argument? VGGFace(model='resnet50', include_top=False)

I came across this line of code: VGGFace(model='resnet50', include_top=False) Could someone please explain to ... -of-instantiating-a-model-with-another-model-as-argument-vggface...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

deep learning - python got result and here is keyerror: 1

#compute ROC curve and ROC area for each class fpr= dict() tpr= dict() roc_auc = dict() y_test= to_categorical( ... .com/questions/65943704/python-got-result-and-here-is-keyerror-1...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - How discriminator determine whice one is real image and whice one is fake?

How we train the discriminator actually? It wants 0 and we pass both real and fake images together, the real image will ... -determine-whice-one-is-real-image-and-whice-one-is-fake...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

deep learning - cannot open <resnet-18.t7> in mode r while trying to train SeGAN model

I am trying to implement the SeGAN paper with the repository here. I installed the prerequisite and tried to train the model ... -18-t7-in-mode-r-while-trying-to-train-segan-model...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

deep learning - How to merge two torch.utils.data dataloaders with a single operation

I have two dataloaders and I would like to merge them without redefining the datasets, in my case train_dataset ... -merge-two-torch-utils-data-dataloaders-with-a-single-operation...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

924 views

1 answer

deep learning - Why is the method for creating training instances there?

I have the following method get_train_instances this takes a matrix (train_mat), which is a one-hot matrix and ... 65625792/why-is-the-method-for-creating-training-instances-there...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

To see more, click for the full list of questions or popular tags.

...