-
-
### 🐛 Describe the bug
I'm experimenting in exporting various MSS models to Executorch. Following the example export scenario in Executorch Documentation, the export terminates in error: 'Operator …
-
When I try to run patch_model_for_compiled_runtime on 8bit + aten, the program reports an error. How can I solve this problem?
![image](https://github.com/user-attachments/assets/f0a85477-f36e-4081-b…
-
```
Token indices sequence length is longer than the specified maximum sequence length for this model (1387 > 1024). Running this sequence through the model will result in indexing errors
../aten/sr…
-
### 🐛 Describe the bug
I`m trying to deploy a image preprocessing program using executroch
Success to export the pte file.
But crash when executor_runner the pte file.
Anyone can help me?
My py…
-
When trying to segment on macOS with the MPS backend with cellpose version 3.1.0 I encounter the following error:
```
Traceback (most recent call last):
File "/Users/orat/opt/anaconda3/lib/pyt…
-
按照cityspace的数据集生成的标签,8个类别 mask是给0-8。
但是在计算损失的时候会报错,请大佬解疑答惑,谢谢大佬,报错信息在下面了。
11/23 08:21:33 - mmengine - INFO - Iter(train) [ 50/120000] lr: 9.9963e-03 eta: 1 day, 1:05:13 time: 0.7358 data_ti…
-
### Problem Statement
`int8_dynamic_activation_int8_weight` API is using zero-points for weight when activation is asymmetrically quantized. That makes its linear's torch.fx IR pattern same as that…
-
MinGRU (without the LM layers) is considerably slower than standard nn.GRU. My test parameters were: input_size = 10, hidden_size = 100, seq_len = 1000, batch_size = 64.
From my profiler, tested i…
-
作者你好,我在使用原始IRDST数据集进行训练时,训练到10个epoch左右就会报错,进行了多次都是相同的结果,报错显示freq feature特征包含了NAN值,请问知道如何调整吗?
freq feature include NAN!!!!
freq feature include NAN!!!!
freq feature include NAN!!!!
freq feature inc…