atomrun39

Convert to tflite&Run tflite model：ValueError: Shapes incompatible

13

First I use darknet to train the yolov4-tiny model, it has two detection classes, and the input image size is 224. The trained weight is first converted to tensorflow, and...

微调后模型推理和图片对不上

5

`python cli_demo.py `，微调前描述和图像相符，微调后和图片不相符了 对于代码中提供的小狗图片示例， 微调前  微调后  微调脚本，我的训练数据有9w左右，是什么原因导致的呢： `#! /bin/bash NUM_WORKERS=1 NUM_GPUS_PER_WORKER=6 MP_SIZE=1 script_path=$(realpath $0) script_dir=$(dirname $script_path) main_dir=$(dirname $script_dir) MODEL_TYPE="visualglm-6b" MODEL_ARGS="--max_source_length 128 \ --max_target_length 256 \ --lora_rank 10 \...

What is the parameter count of the entire model？

3

What are the training parameters for videogpt and LatteT2V in the model？

How to use the model from Stage 1 in Stage 2?

1

May I ask if Stage 2 is trained using the Stage 1 model, and Stage 3 is trained using the Stage 2 model? If so, how to load the model...