Questions tagged [pre-trained-model]
A machine learning model created by someone else. Questions about the practical use and implementation details (using a pretrained model as a starting point, or benchmark) are allowed; however, questions about the theory behind these models are off-topic.
514
questions
42
votes
2
answers
61k
views
How to save a trained model by scikit-learn? [duplicate]
I am trying to re-create the prediction of a trained model but I don't know how to save a model.
For example, I want to save the trained Gaussian processing regressor model and recreate the prediction ...
- 433
38
votes
4
answers
33k
views
Is it possible to make a trainable variable not trainable?
I created a trainable variable in a scope. Later, I entered the same scope, set the scope to reuse_variables, and used get_variable to retrieve the same variable. However, I cannot set the variable's ...
- 1,014
16
votes
4
answers
43k
views
Is there any way I can download the pre-trained models available in PyTorch to a specific path?
I am referring to the models that can be found here: https://pytorch.org/docs/stable/torchvision/models.html#torchvision-models
- 796
16
votes
1
answer
4k
views
How to Fine tune existing Tensorflow Object Detection model to recognize additional classes? [closed]
Thanks to Google for providing a few pre-trained models with tensorflow API.
I would like to know how to retrain a pre-trained model available from the above repository, by adding new classes to the ...
- 918
15
votes
4
answers
30k
views
AttributeError: 'Node' object has no attribute 'output_masks'
I use Keras pretrained model VGG16. The problem is that after configuring tensorflow to use the GPU I get an error that I didn't have before when using the CPU.
The error is the following one:
...
- 295
14
votes
2
answers
6k
views
Can i finetune deeplab to a custom dataset in tensorflow?
I would like to customize deeplab for image segmentation using my own dataset ? Is this achievable by retraining ?
- 183
14
votes
2
answers
37k
views
Download pretrained ImageNet model of ResNet, VGG, etc. (.PB file)
I have downloaded a pre-trained model on ImageNet of Inception v3 from http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz (found this link while following one of the ...
- 750
13
votes
2
answers
795
views
GPU utilization 0% during TensorFlow retraining for poets
I am following instructions for TensorFlow Retraining for Poets. GPU utilization seemed low so I instrumented the retrain.py script per the instructions in Using GPU. The log verifies that the TF ...
- 2,034
11
votes
6
answers
16k
views
How to save/load a tensorflow hub module to/from a custom path?
The tensorflow_hub library maintainers has made it every easy for users to download and use the pre-trained tensorflow modules, e.g.:
import tensorflow_hub as hub
embed = hub.Module("https://tfhub....
- 119k
11
votes
2
answers
14k
views
Continual pre-training vs. Fine-tuning a language model with MLM
I have some custom data I want to use to further pre-train the BERT model. I’ve tried the two following approaches so far:
Starting with a pre-trained BERT checkpoint and continuing the pre-training ...
- 2,531
11
votes
1
answer
15k
views
how to load the gpu trained model into the cpu?
I am using PyTorch. I am going to use the already trained model on multiple GPUs with CPU. how to do this task?
I tried on Anaconda 3 and pytorch with cpu only i dont have gpu
model = models....
- 113
11
votes
1
answer
13k
views
How can I load a partial pretrained pytorch model?
I'm trying to get a pytorch model running on a sentence classification task. As I am working with medical notes I am using ClinicalBert (https://github.com/kexinhuang12345/clinicalBERT) and would like ...
- 111
9
votes
4
answers
16k
views
Fine Tuning Pretrained Model MobileNet_V2 in Pytorch
I am new to pyTorch and I am trying to Create a Classifier where I have around 10 kinds of Images Folder Dataset, for this task I am using Pretrained model( MobileNet_v2 ) but the problem is I am not ...
- 184
9
votes
4
answers
6k
views
How to choose which pre-trained weights to use for my model?
I am a beginner, and I am very confused about how we can choose a pre-trained model that will improve my model.
I am trying to create a cat breed classifier using pre-trained weights of a model, ...
- 824
9
votes
1
answer
25k
views
TypeError: ('Keyword argument not understood:', 'data_format')
I trained and downloaded a model(a CNN) using Keras from google colaboratory when I tried to load the model on my local machine(Mac OS X El Capitan), I received the following error.
Traceback (most ...
- 109
8
votes
1
answer
4k
views
Uni-directional Transformer VS Bi-directional BERT
I just finished reading the Transformer paper and BERT paper. But couldn't figure out why Transformer is uni-directional and BERT is bi-directional as mentioned in BERT paper. As they don't use ...
- 409
8
votes
2
answers
21k
views
Loading Torch7 trained models (.t7) in PyTorch
I am using Torch7 library for implementing neural networks. Mostly, I rely on pre-trained models. In Lua I use torch.load function to load a model saved as torch .t7 file. I am curious about ...
- 303
8
votes
2
answers
4k
views
How to convert a PyTorch nn.Module into a HuggingFace PreTrainedModel object?
Given a simple neural net in Pytorch like:
import torch.nn as nn
net = nn.Sequential(
nn.Linear(3, 4),
nn.Sigmoid(),
nn.Linear(4, 1),
nn.Sigmoid()
).to(device)
How do I ...
8
votes
1
answer
11k
views
Data Preprocessing for NLP Pre-training Models (e.g. ELMo, Bert)
I plan to train ELMo or Bert model from scratch based on data(notes typed by people) on hand. The data I have now is all typed by different people. There are problems with spelling, formatting, and ...
- 331
7
votes
1
answer
4k
views
Pre-Trained models for text Classification
So I have few words without labels but I need to classify them into 4-5 categories.
I can visibly say that this test set can be classified. Although I do not have training data so I need to use a pre-...
- 71
7
votes
2
answers
13k
views
How can I add new layers on pre-trained model with PyTorch? (Keras example given)
I am working with Keras and trying to analyze the effects on accuracy that models which are built with some layers with meaningful weights, and some layers with random initializations.
Keras:
I load ...
- 351
7
votes
3
answers
1k
views
Pre train a model (classifier) in scikit learn
I would like to pre-train a model and then train it with another model.
I have model Decision Tree Classifer and then I would like to train it further with model LGBM Classifier. Is there a ...
- 589
7
votes
1
answer
3k
views
Modify trained model architecture and continue training Keras
I want to train a model in a sequential manner. That is I want to train the model initially with a simple architecture and once it is trained, I want to add a couple of layers and continue training. ...
- 7,027
7
votes
4
answers
4k
views
Duplicate node name in graph: 'conv2d_0/kernel/Adam'
I just saved a model, by that code:
def train():
with tf.Session() as sess:
saver = tf.train.Saver(max_to_keep = 2)
Loss = myYoloLoss([Scale1,Scale2,Scale3],[Y1, Y2 ,Y3])
opt = tf....
- 729
7
votes
2
answers
7k
views
VGG16 trained on grayscale imagenet
I have found the VGG16 network pre-trained on the (color) imagenet database (as .npy). Is there a VGG16 network pre-trained on a gray-scale version of the imagenet database available?
(The usual '...
- 91
6
votes
2
answers
3k
views
Error when loading FastText's french pre-trained model with gensim
I am trying to use the FastText's french pre-trained binary model (downloaded from the official FastText's github page). I need the .bin model and not the .vec word-vectors so as to approximate ...
- 191
6
votes
2
answers
7k
views
Latest Pre-trained Multilingual Word Embedding
Are there any latest pre-trained multilingual word embeddings (multiple languages are jointly mapped to a same vector space)?
I have looked at the following but they don't fit my needs:
FastText / ...
- 423
6
votes
1
answer
2k
views
How to save a trained model (Estimator) and Load it back to test it with data in Tensorflow?
I have this snippet, for my model
import pandas as pd
import tensorflow as tf
from tensorflow.contrib import learn
from tensorflow.contrib.learn.python import SKCompat
#Assume my dataset is using X['...
6
votes
2
answers
2k
views
ImageNet pretrained ResNet50 backbones are different between Pytorch and TensorFlow
"Obviously!", you might say... But there's one significant difference that I have trouble explaining by the difference in random initialization.
Take the two pre-trained basenets (before the ...
- 1,527
5
votes
2
answers
7k
views
ILSVRC2012 validation ground_truth labels index not matching pretrained networks index
I'm currently using VGG-S pretrained convolutional neural network provided by Lasagne library, from the following link.
I downloaded the validation dataset of ILSVRC2012 in order to do a ...
- 101
5
votes
4
answers
5k
views
How to fix "Trainer: evaluation requires an eval_dataset" in Huggingface Transformers?
I’m trying to do a finetuning without an evaluation dataset.
For that, I’m using the following code:
training_args = TrainingArguments(
output_dir=resume_from_checkpoint,
evaluation_strategy=&...
- 1,306
5
votes
2
answers
19k
views
ValueError: `decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 7)
I am using VGG16 with keras for transfer learning (I have 7 classes in my new model) and as such I want to use the build-in decode_predictions method to output the predictions of my model. However, ...
- 4,020
5
votes
2
answers
12k
views
How to concatenate 2 pytorch models and make the first one non-trainable in PyTorch
I've two networks, which I need to concatenate for my full model. However my first model is pre-trained and I need to make it non-trainable when training the full model. How can I achieve this in ...
- 7,027
5
votes
2
answers
15k
views
Accuracy Stuck at 50% Keras
Code
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential,Model
from keras.layers import Dropout, Flatten, Dense,Input
from keras import ...
- 1,829
5
votes
2
answers
2k
views
Why do I have to do two train steps for fine-tuning InceptionV3 in Keras?
I don't understand why I have to call the fit()/fit_generator() function twice in order to fine-tune InceptionV3 (or any other pretrained model) in Keras (version 2.0.0).
The documentation suggests ...
- 1,074
5
votes
2
answers
12k
views
Does keras have a pretrained AlexNet like VGG19?
If I want to use pretrained VGG19 network, I can simply do
from keras.applications.vgg19 import VGG19
VGG19(weights='imagenet')
Is there a similar implementation for AlexNet in keras or any other ...
- 7,027
5
votes
1
answer
1k
views
What is the difference between TFHub and Model Garden?
TensorFlow Hub is a repository for pre-trained models. Model Garden (Model Zoo) also keeps SOTA models and provides facilities for downloading and leveraging its models like TfHub, and both of them ...
- 4,862
5
votes
1
answer
4k
views
ResNet50v2 in Keras
I want to load pre-trained ResNet50v2 model in Keras. I tried
keras.applications.resnet_v2.ResNet50V2()
This gave an error
Traceback (most recent call last):
File "<input>", line 1, in <...
- 7,027
5
votes
1
answer
3k
views
Combine outputs of two Pre Trained models (trained on different dataset) and use some form of binary classifier to predict images
I have two Pre-Trained models.
Model_1 = Inception Model with Imagenet Dataset (1000 classes)
My_Model = Inception Model trained with a custom dataset (20 classes) via Transfer Learning and Fine-...
- 51
5
votes
1
answer
1k
views
Where can I find a pre-trained variational autoencoder that's trained on natural images?
Does anyone know a pre-trained variational autoencoder (VAE) or a VAE-GAN that's trained on natural images?
I have been searching for a variational autoencoder that is trained on natural images (e.g. ...
- 113
5
votes
0
answers
2k
views
Trained models for tensorflow ocr
I start the course of tensorflow in udacity, and simultaneously I am looking on the web for the topic.
I suppose that the typical use cases are well solved already, in a better way that i can achieve ...
- 531
5
votes
1
answer
2k
views
how to load pretrained LSTM models weights in Tensorflow
I want to implement a LSTM model with pretrained weights in Tensorflow. These weights may come from Caffee or Torch.
I found there are LSTM cells in file rnn_cell.py, such as rnn_cell.BasicLSTMCell ...
- 51
4
votes
3
answers
11k
views
KeyError: 'The optimizer cannot recognize variable dense_1/kernel:0. for pretrained keras model VGG19
I'm using the following code to load an imagenet pre-trained VGG19 model and fit to my custom dataset.
from keras.applications.vgg19 import VGG19
optim = tf.keras.optimizers.RMSprop(momentum=0.9)
...
- 43
4
votes
1
answer
1k
views
Keras VGGnet Pretrained Model Variable Sized Input
I want to extract features of a 368x368 sized image with VGG pretrained model. According to documentation VGGnet accepts 224x224 sized images. Is there a way to give variable sized input to Keras VGG?
...
- 733
4
votes
1
answer
947
views
TF Objection Detection Zoo models don't have Trainable Variables?
The models in the TF Objection Detection Zoo have meta+ckpt file, Frozen.pb file, and Saved_model file.
I tried to use the meta+ckpt file to train further and also to extract some weights for ...
- 440
4
votes
2
answers
2k
views
Can't restore pre-trained network with Tensorflow
I'm stuck with restoring pre-trained network with Tensorflow....
import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
sess=tf.Session()
saver = tf.train.import_meta_graph('./...
- 425
4
votes
3
answers
3k
views
Tensorflow load pre-trained model use different optimizer
I want to load a pre-trained model (optimized by AdadeltaOptimizer) and continue training with SGD (GradientDescentOptimizer). The models are saved and loaded with tensorlayer API:
save model:
...
- 689
4
votes
1
answer
1k
views
Keras model gets worse when fine-tuning
I'm trying to follow the fine-tuning steps described in https://www.tensorflow.org/tutorials/images/transfer_learning#create_the_base_model_from_the_pre-trained_convnets to get a trained model for ...
- 71
4
votes
1
answer
2k
views
Weight Initialization from pretrained BERT error in pytorch
I am trying to train the model using pretrained model(BERT) using pytorch. The pretrained model weights still arent accepted.
I see this error:
Weights of BertForMultiLable not initialized from ...
- 380
4
votes
2
answers
3k
views
How to use model architecture of pretrained models but no weights
I want to use ResNet model architecture and want to change last few layers; how can I only use model architecture from model zoo in Tensorflow?
- 41