TensorFlow2.0_ResNet

TensorFlow2.0_ResNet copied to clipboard

Hello,[this issue](https://github.com/calmisential/TensorFlow2.0_ResNet/issues/10) shows the reason that I commit this PR. I sincerely wish my PR will help you.And if you think my PR has a little work,Hoping you could merge...

DLPerf

Hello,I found a performance issue in the definition of `get_dataset` , prepare_data.py, [image_dataset = tf.data.Dataset.from_tensor_slices(all_image_path).map](https://github.com/calmisential/TensorFlow2.0_ResNet/blob/6136d57c7580d24c9ee3e55ca0b820822565ce17/prepare_data.py#L38) was called without **num_parallel_calls**. I think it will increase the efficiency of your program if...

DLPerf

zhanghaobucunzai

Pretrained weights for Resnet34

2

Hi, Thanks for this repo, much appreciated. I was wondering if you have trained your Resnet34 model with imagenet? I was looking to start my training from imagenet weights.

ectg

RamvigneshPasupathy

For example, ``` self.conv1 = tf.keras.layers.Conv2D(filters=filter_num, kernel_size=(3, 3), strides=stride, padding="same") ``` shoud be ``` self.conv1 = tf.keras.layers.Conv2D(filters=filter_num, kernel_size=(3, 3), strides=stride, padding="same",use_bias=False) ```

hccho2

To test images outside dataset

enreezy

Evaluate.py changes

1

How can one get the prediction for each image? Like if I have 10 images how to get prediction value for each one of them.

Ahsanr312

2023-02-21 19:53:25.950975: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 To enable them in...

miki1638879381

Hi all, I trained a model with ResNet34 on a custom dataset. Now I want to make predictions with that model, and evaluate.py only returns accuracy. Any suggestions? Best, daan

Ron12234