-
Test the output from the visualizers against expected images.
When we have that we can also submit these pictures for calculation and make sure that the probabilities are as expected.
That means…
-
I try to run it with python 3.7. and get this error.
`ModuleNotFoundError Traceback (most recent call last)
in
1 # Preloading models
----> 2 from keras.datasets im…
-
Setup:
Using Vitis AI 2.5 docker image
Pynq-DPU v2.5
Compiled a custom CNN model and quantiz…
-
Error solved: add tf.keras.layer.Permute(3,1,2) to convert input from NHWC to NCHW. This solves segmentation fault. Because onnx2ncnn is for conversion from pytorch which uses NCHW.
I couldn't solv…
-
Hi. I'm trying using torch2trt_dynamic to convert models from torch to trt. I got an unexpected issue.
To reproduce it I use lenet5 like neural network.
```
from torch2trt_dynamic import torch2trt_…
-
I see the result on MNIST works well. I have tried to run the SVHN code . But the accuracy is only about 86%, whilch has difference to the result in the paper(94.50%). I wonder if you have get high ac…
-
I am getting the following warning
> WARNING:tensorflow:From /Users/nbro/Desktop/my_project/venv/lib/python3.7/site-packages/tensorflow_probability/python/layers/util.py:104: Layer.add_variable (fr…
-
```python
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
# model
x = tf.placeholder(tf.fl…
-
When using PBT/PB2, I received the following error:
```shell
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
```
This issue happens aft…
-
https://arxiv.org/pdf/1411.1784.pdf
Generative Adversarial Nets were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative a…
leo-p updated
7 years ago