-
I've tried both xception and resnet-101 backbone. The resent-101 backbone is working fine but when using xception backbone, results are very bad. And even, training for longer making the resulting ima…
-
The title says it all.
```
Traceback (most recent call last):
File "/home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/tensorflow_core/python/framework/importer.py", line 50…
-
I retrain the deeplab part and the result is 61% for baseline while 66% for dcn. This is a lot below the official result. I only changed the gpu to 2 and remove the multiprocess in loader. Anyone know…
-
Can you provide the model_urls under /models file
model.load_state_dict(model_zoo.load_url(model_urls['resnet_XBNBlock_P1_101']))
-
I run the code on pascal voc2012 augment with resnet_v2_101, but the miou of training result is only about 0.153。 Please tell me what caused it? thank you.
-
Hi, I have a question that how I can retrain the model without pretrained weight? And how many images should I prepare with resnet-101?
-
I got this error when convert ResNet-101
ValueError: Layer weight shape (131072, 1000) not compatible with provided weight shape (2048, 1000)
Please help me
-
Following up on https://github.com/pytorch/fairseq/issues/759#issuecomment-589498214, it would be great if Faster-RCNN could be used directly, so we could input images instead of pre-computed features…
-
During simulation with ResNet, a segmentation fault occurs at gem5.
I created ResNet pb and pbtxt file by running smaug/experiments/models/imagenet-resnet/resnet_network.py
All configuration files a…
-