-
hi
i successfully installed ikomia using pip in a virtual env (pycharm + python 3.9). i tried to run the above code and i get many errors. First the line "from ikomia.utils import ik" prodce the fo…
-
# I use the same code to run mxnet resnet to onnx,but will get this error,I dont know why
mxnet.base.MXNetError: [10:12:42] src/ndarray/ndarray.cc:1805: Check failed: fi->Read(data) Invalid NDArray f…
-
When I try to save a ResNet18 model to ONNX with the `export_for_inference` function while providing the `apply_blurpool` surgery algorithm as well as the dynamic axes I get the following error:
``…
dneup updated
3 months ago
-
I prune resnet_20 at cifar_10 by ChannelPrunedLearner, but I reader `original_model.ckpt`, `pruned_model.ckpt` and `best_model.ckpt`, the size of weight is same. `origin val` is the size of weight in …
-
It would be nice if one can use this module via config files.
For example, consider this configuration file
```
# filename: testing.yml
cmd_template: train.py --model {model} --lr {lr} --data…
-
When I run train.py, there is a error:
"ImportError: cannot import name 'DetectMultiBackend' from 'models.common'."
In modles/common.py, class DetectMultiBackend is not found.
Looking forward to a …
-
Now I got a pre-trained ResNet 152-layer model [](http://download.tensorflow.org/models/resnet_v1_152_2016_08_28.tar.gz)
I just want to use this 152-layer model to extract the image feature, now i wa…
-
Traceback (most recent call last):
File "/content/kohya-trainer/train_network_xl_wrapper.py", line 10, in
trainer.train(args)
File "/content/kohya-trainer/train_network.py", line 251, in t…
wzgrx updated
2 weeks ago
-
Hi,
I am trying to run a custom network using your framework. In particular, I am using a modified version of resnet-18 (it's classifier layers have been modified to work with 10 classes instead of 1…
-
I used the r2p1d18_K_200ep.pth and finetune it on hmdb51 dataset,and when I want to use it to inference there is an AssertionError
`CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py --root_path /home/pubNA…