Dirk

Hi I get also the connection refused Error, Changing the port number has no effect. I started successfully Flask Servers with different ports before, but Bert Service fails to start

Got it running using Bert Client and nohup - here is how it worked for me: !pip install bert-serving-client !pip install -U bert-serving-server[http] !wget https://storage.googleapis.com/bert_models/2018_10_18/uncased_L-12_H-768_A-12.zip !unzip uncased_L-12_H-768_A-12.zip !nohup bert-serving-start -model_dir=./uncased_L-12_H-768_A-12...

@iknoorjobs i have a lot of other stuff in that notebook so I can't share. I would need to create a clean new one. But first let me try to...

Update: Increasing the max_batch_size and the n_samples will use the whole GPU Memory but it will never have 100% Util except some small peaks. But The GPUs will use more...

This is a strange coincidence I had the same problem today. See my post here, how to fix it :) https://github.com/clips/pattern/issues/282

@vizzerdrix55 : Yes - that is what works for me, but I am not on Anaconda, I am on Mac OS but I do not think thats the difference. I...

I would very much appreciate it if tensor parallelism could be implemented. Tried llama-2-13 on 2 RTX 3090 in fp16 and got OOM - and for sure 8bit works fine...

Some additonail information: Debugging into applyNonMaximaSuppression(nmsThreshold, labels, scores, coords) np.count_nonzero(labels) the count of non zero labels np.count_nonzero(labels) is 54 in the grocery case and 0 in the pascal case

@nadavbar Thanks - i tested it with the pascal images from pkranes tutorial, the vocdevkit/Voc2007 for example this one: 

what i have seen also debugging, is that after: output = self.__model.eval(arguments) all max values found are in index 0 like: [ 15.3869276 5.46492958 -5.02364111 3.75026011 1.86460972 -2.08186817 -4.47750282 0.64720851...