-
I use `torch.utils.serialization.load_lua` Python pkg to load the `vgg_normalised_conv5_1.t7`, the net is as followed:
```
In [7]: vgg1 = load_lua('models/vgg_normalised_conv1_1.t7')
In [8]: vgg1…
-
With `MaxPooling2D` with strides, size of image reduces in following manner
> (32, 24, 3)
(?, 16, 12, 64)
(?, 8, 6, 128)
(?, 4, 3, 256)
(?, 2, 1, 512)
which in next step generates an error
…
-
Hi, I am trying to do the same experiment with yolov5. I tried same structure of the modification you did. However, I couldn't understand how to modifiy the head to match the backbone and modify the c…
-
Hi, thanks for sharing the script! Just tested this one on my machine (click here for [specs](https://pcpartpicker.com/b/yDZZxr)) with [ROCm](https://rocm.docs.amd.com/en/latest/how_to/pytorch_install…
-
Hey, I've already download the pretrained model, but when i run the demo.ipynb, it still download the vgg16-397923af.pth.
Why ?
-
self.FILE_PATH needs to be changed to http://files.fast.ai/models/
Previous path doesn't work anymore.
self.FILE_PATH=http://files.fast.ai/models/
-
The download links for the pre-trained models of VGG16 and resnet101 are invalid.
-
2018-06-06 23:24:10,663 ERROR File 'DATA/vgg16.npy' not found. Download it from ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy
the following error is coming while i have dowloaded the file and p…
-
I notice there is no dropout in the vgg16 code whereas dropout was used in the original paper. I wonder if there is a reason for removing it and whether the pretrained weights were learned with or wit…
-
train_path='train'
valid_path='valid'
test_path='test'
#batches for train, valid and test set
train_batches=ImageDataGenerator(rescale =
1./255).flow_from_directory(train_path,target_size=(22…