-
## 🐛 Bug
In some cases, torch.cdist returns non-zero (i.e. far from machine epsilon) diagonal values with CUDA.
Behaviour is as expected on CPU.
The issue seems more severe on Ampere GPUs.
## …
-
### Your current environment
The output of `python collect_env.py`
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N…
-
## 🐛 Bug
```
[11/457] Linking CXX executable bin/generate_proposals_op_util_nms_gpu_test
FAILED: bin/generate_proposals_op_util_nms_gpu_test
: && /usr/bin/c++ -Wno-deprecated -fvisibility-i…
-
**Describe the bug**
When using ViT as a backbone in Faster R-CNN, the bbox mAP is always 0 during validation, even though the training loss is decreasing normally. The training shows normal loss val…
-
### 🐛 Describe the bug
As it says in the title, using `ParameterDict.items()` will break `torch.jit.script` as seen below
```
import torch
from torch import nn
class MyModule(nn.Module):
…
bigd4 updated
5 months ago
-
https://www.mrking.space/2022/08/16/%E7%BB%8F%E5%85%B8CNN%E6%A8%A1%E5%9E%8B-AlexNet/
AlexNet模型概述 代码实现123456789101112131415161718192021222324import torchfrom torch import nnfrom d2l import torch as …
-
### 🐛 Describe the bug
I tried to reproduce the result of ConvNeXt-Tiny's pretraining reported [here](https://pytorch.org/vision/main/models/generated/torchvision.models.convnext_tiny.html#torchvis…
-
下图有个5和3其实挺明显的，但是识别成1，请问要提高精度需要往哪个方向修改？
-
KeyError: 'unexpected key "features.0.weight" in state_dict'
-
```
[jalal@goku pytorch-sentiment-analysis]$ python run.py --model_config config/cnn_rnn.yml --epochs 50 --model_dir sentiment-analysis.pt --dataset data/sentiment
Traceback (most recent call last):…