在Fastai上将脱粒应用于表格模型时出现错误

时间:2019-09-27 16:14:00

标签: tabular fast-ai

我正在尝试在fastai表格模型上更改默认阈值0.5,但无法使其正常工作。

我正在使用最新版本的fastai + conda和python3来运行它

f1_score =FBeta(average='macro',beta = 1)
acc_02 = partial(accuracy_thresh, thresh=0.2)
f_score = partial(fbeta, thresh=0.2)
learn = tabular_learner(data, layers=[1000, 200, 15], emb_szs=emb_szs, metrics=[acc_02,f1_score],emb_drop=0.1, callback_fns=ShowGraph)```


I would expect to set the tresh to 0.2 but I'm getting the following error:

```python
RuntimeError                              Traceback (most recent call last)
<ipython-input-196-fd2bddb11935> in <module>()
----> 1 learn.fit_one_cycle(2, max_lr=slice(1e-01))

8 frames
/usr/local/lib/python3.6/dist-packages/fastai/metrics.py in accuracy_thresh(y_pred, y_true, thresh, sigmoid)
     33     "Computes accuracy when `y_pred` and `y_true` are the same size."
     34     if sigmoid: y_pred = y_pred.sigmoid()
---> 35     return ((y_pred>thresh).byte()==y_true.byte()).float().mean()
     36 
     37 def top_k_accuracy(input:Tensor, targs:Tensor, k:int=5)->Rank0Tensor:

RuntimeError: The size of tensor a (2) must match the size of tensor b (64) at non-singleton dimension 1```

0 个答案:

没有答案