-
### 🐛 Describe the bug
Seems to be some instability issue. See the stacktrace:
```
Traceback (most recent call last):
File "/pytorch/executorch/examples/qualcomm/scripts/deeplab_v3.py", line…
-
Hi, I found that the code in BRINet.py used the attribute res3c and res4c of deeplab_model, but the reference of deeplab have no these two attitudes. Can you give the code of revised deeplab_model ？
-
@toniz
Hi, I have trained deep lab on my custom dataset(50*50,3400 images) for iris eyes object with 257 as crop size and during the test, it detects for crop with crop size 257 .
i tested the pb m…
-
Dear author,
Thank you so much for providing the pretrained weights. I tried to load the pretrained weights (i.e. bat_1_1_0_e6_loss_0_aug_1 and bat_valid_1_1_0_e6_loss_0_aug_1 ) to test images and me…
-
진행 내용 이슈 코멘트로 정리하겠습니다.
사용 모델: (아경) pytorch DeepLab V3
실습 환경: 노트북(GPU 2GB/ CPU 8GB) or 랩(CPU 32GB) or 서버(GPU 8GB/CPU 64GB)
-
Since the workaround doesn't work well for deeplab since the depth_out is to large. We will need the support from Apple for depthwise_conv.
-
when use downloaded MobileNet v2,
got flops and params error: Given groups=1, weight of size 182 728 3 3, expected input[1, 96, 64, 128] to have 728 channels, but got 96 channels instead
and then…
-
Hello， how can i get the syn_deeplab.zip？
-
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…
-