Octocat

undefined reference to '__android_log_write'

1

I can compile successfully, but it errors when used: ``` function MessageLogger::~MessageLogger(): error: undefined reference to '__android_log_write' ``` Is there anything wrong? @tzutalin

mobilenet_v3 small last channel is 1024 instead of 1280 from the paper，is there any evidence that 1280 brings better results?

torch batch forward

5

**Describe the bug** For non-streaming inference, it seems that the exported onnx model can support batch forward, and I try to modify the asr_model.py file to export jitscript model which...

Reference to non-existent field 'sizes'

2

Hi, I configured the project as your readme. Fortunately, I was able to run the testing demo successfully, but when I wanted to train the network, I had the following...

ValueError: zero-size array to reduction operation maximum which has no identity

6

Hi all , I got a new issue during my training. ``` 2018-08-23 18:12:20,224 - root - INFO - Epoch[0] Batch [1400] Speed: 7.74 samples/sec RPNAcc=0.944368 RPNLogLoss=0.181685 RPNL1Loss=1.067499 RCNNAcc=0.800806 RCNNLogLoss=0.756302RCNNL1Loss=2.519708...

stop at step2 evaluation_reward

4

Firstly, thank you for your contributions. I consistently pause (but do not exit) at the [evaluation_reward](https://github.com/l294265421/alpaca-rlhf/blob/main/alpaca_rlhf/deepspeed_chat/training/step2_reward_model_finetuning/main.py#L413) during the training of step 2. Hence, I am wondering if there is something...

Load dataset from hf failed

5

``` datasets = ['hotpotqa', '2wikimqa', 'musique', 'narrativeqa', 'qasper', 'multifieldqa_en', 'gov_report', 'qmsum', 'trec', 'samsum', 'triviaqa', 'passage_count', 'passage_retrieval_en', 'multi_news'] for dataset in datasets: print(f"Loading dataset {dataset}") data = load_dataset("THUDM/LongBench", dataset, split="test") output_path...