Qingyang Zhang comments

Results 5 comments of


                                            Qingyang Zhang

Communicate in Chinese！中文交流！

无论是否加载YOLO-small.ckpt，训练出来的模型都无法检测到任何物体。 No matter if I use the pretrained model Yolo-small.ckpt, no thing can be detected with the model I trained by myself.

After fine-tuning pre-trained WideResNet, the ID classification drops a lot?

I am curious about this, too.

Stable-diffusion-2-1, the config of text_encoder does not match

CLIPTextConfig { "_name_or_path": "openai/clip-vit-large-patch14", "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "eos_token_id": 2, "hidden_act": "quick_gelu", "hidden_size": 768, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "num_attention_heads": 12,...

New Repo for Datasets Only: https://github.com/wistuba/Wild-Time-Data

It's you, my friend, you are the real hero.

In Step 1: Warmup training，multiple gpu's trainning

Same question here.