-
+ set -e
+ export PYTHONUNBUFFERED=True
+ PYTHONUNBUFFERED=True
+ GPU_ID=0
+ DATASET=pascal_voc
+ NET=res101
+ array=($@)
+ len=3
+ EXTRA_ARGS=
+ EXTRA_ARGS_SLUG=
+ case ${DATASET} in
+ TRA…
-
@itayhubara : I noticed that all the binarized neural network files `alexnet_binary.py, resnet_binary.py, vgg_cifar10_binary.py` have **Hardtanh** activation function whereas their respective parent a…
-
I wasn't able to get it running using Python 3.10
```
$ python main.py
...
FileNotFoundError: The pose configuration file for the exported model at /Users/xxx/Code/DogPoopDetector/exported-model…
sfdye updated
4 months ago
-
Hello!
We tried to reproduce the experiment in your paper (Figure 16, ResNet on CIFAR-10 for different widths (compared to a base network).
We made some modifications to examples/ResNet/main.py:
…
-
So I tried running your code on my dataset with a pre-trained ResNet50 model. I got these results
Full precision model i got accuracy of : MobileNetV2 (58.19)
Quantized model (W8A8) i got accuracy…
-
There seems to be a compatability problem with tensorflow-gpu 1.4.1. The train.py can be processed under tf-gpu 1.2.1 with some warnings. Nevertheless, there is always an error track back to
```cons…
huwh1 updated
6 years ago
-
From tools/tensorflowbm6_gpu21.config and http://dlbench.comp.hkbu.edu.hk/, we know dlbench of version 8 will call alexnet and resnet for CNN tests.
But, Cifar10 experiments won't succeed as the da…
-
**System information**
- Have I written custom code (as opposed to using example directory): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
- TensorFlow backe…
-
List in General:
**Can Be Done Without Training Images**
1. Gamma Correction: Adjust image brightness.
2. Filtering: Apply Gaussian blur, median filter, etc.
3. Color Space Transformation: Conve…
-
Hi,
Thanks for the nice work and for sharing the code.
I have tried replicating the results of the paper (training from scratch) but with no luck.
I have followed the instructions of the readme a…