Basic_CNNs_TensorFlow2

Basic_CNNs_TensorFlow2 copied to clipboard

c22x

Does this repo support multiple-gpu training?

1

Thanks.

Chenglin-Yang

Hi brother, well-done. Can you create confusion_matrix function in evaluate.py if possible?

Harry-KIT

is mobilenet_v1.py missing BN and RELU ?

1

new to TF2

lyycfairy

Can you tell me where to put the images for training?

1

It may sound like a naive question, but before starting training, which path should I put my images in?

YWZhengG

The same values after each epoch

1

After each epoch I have te same values: Epoch: 0/2, train loss: nan, train accuracy: 0.10688, valid loss: nan, valid accuracy: 0.10680 regardless of the model. tensorflow 2.3.1 (install via...

agnieszkajust

Assign different gradient weights

1

How to write the code to assign different gradient weights to different classes of SparseCategoricalCrossentropy

Cris-chen

识别率不高

1

都不用迁移学习的吗 硬训练啊 结果不理想

liuxiaoxiao666

感谢开源，但是错误一堆，完全没法跑

1

加油

AndrewJSong

run error in regnet with GPU

1

我在使用GPU进行RegNet训练的时候，报错了 ``` UnimplementedError: Fused conv implementation does not support grouped convolutions for now. [[node reg_net/any_stage/res_bottleneck_block/bottleneck_transform/conv2d_3/BiasAdd (defined at /filepath/anynet.py:119) ]] [Op:__inference_train_function_10336] Function call stack: train_function ``` 但是CPU下是正常的，我检查了一下代码，GPU和CPU模式下，get_group_conv是不一样的，但我不知道怎么debug 希望能得到您的回复

tongshiyuan