sebkim / lda2vec-pytorch Goto Github PK

when i try main.py.. how i solve this ??

Can you explain how to evaluate lda2vec model?

when i try to run the model training.py , i get this error :
TypeError: can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool.
how to fix this

i wanted to train this model with my own data,but I didn't know how to do it?? which modules I have to modify?? please nobody can help me it's urgent.

hello,i train your data,but when i want to test the model,AttributeError: 'list' object has no attribute 'seek'. You can only torch.load from a file that is seekable. Please pre-load the data into a buffer like io.BytesIO and try to load from it instead.
how i fix this error

when i try this code from module explore_model.ipynb
`for each, epoch in model_list2[:-1:(len(model_list2)//10)+1][:2] + [model_list2[-1]]:
state = torch.load(f'{each}', map_location=lambda storage, loc: storage)
doc_weights = state['doc_weights.weight'].cpu().clone().numpy()

# distribution over the topics for each document
topic_dist = softmax(doc_weights)

# distribution of nonzero probabilities
dist = topic_dist.reshape(-1)
plt.hist(dist[dist > 0.01], bins=40);
plt.title(f'epoch: {epoch}')
plt.show()`

, i'm getting this error :
`IndexError Traceback (most recent call last)
in
----> 1 for each, epoch in model_list2[:-1:(len(model_list2)//10)+1][:2] + [model_list2[-1]]:
2 state = torch.load(f'{each}', map_location=lambda storage, loc: storage)

IndexError: list index out of range`
how to fix this plz ??