yuxx0218

NotImplementedError: Create your own 'get_image_id' function

7

Traceback (most recent call last): File "train.py", line 626, in # device=device, ) File "train.py", line 425, in train evaluator = evaluate(eval_model, val_loader, config, device) File "/data/anaconda3/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 49, in...

ModuleNotFoundError: No module named 'distiller'

2

I follow 'Example: Simple training-only session (no compression)' in 'Basic Usage Examples' of README file, and run 'compress_classifier.py'. But the following error occures: Traceback (most recent call last): File "compress_classifier.py",...

关于模型结构

1

我再pytorch根据model/ocr/chinese/ocr.cfg复现了这个网络，并根据要求输入了[1, 1, 32, 256]的图像，发现网络的输出尺寸为[1, 11316, 3, 63]，请问这个输出的含义是什么呢？按照我的理解，输出是[1, 11361, 1, n]，其中11361表示11361个汉字的prob，n表示生成的文字序列的长度。不知道是哪里出了问题，求指教！（没用过darknet，所以不知道如何查看网络结构的实际实现） `class CRNN(nn.Module): def __init__(self, imgC): super(CRNN, self).__init__() self.conv1 = nn.Conv2d(imgC, 64, 3, 1, 1) self.relu1 = nn.ReLU() self.mpool1 = nn.MaxPool2d(2,...

OOM while loading THUDM/chatglm-6b-int4

3

I am trying this code to load THUDM/chatglm-6b-int4 on a single GPU: `llm = LLM(model=model_path, trust_remote_code=True)` However it raises an OOM exception: > Traceback (most recent call last): File "demo_vllm.py",...

ICDAR 2003 test data can not unzip

1

could you please send me a copy? my email address is [email protected]. Thank you very much!