(venv) 29:21-CN-EN-Translation-BERT gaojianhua$ python bert_train.py
WARNING: Logging before flag parsing goes to stderr.
W0820 10:24:03.213339 4518290880 dataset_builder.py:689] Using custom data configuration zh-en
{}
Downloading and preparing dataset wmt_translate (?? GiB) to /Users/gaojianhua/tensorflow_datasets/wmt_translate/zh-en/0.0.3...
Dl Completed...: 0 url [00:00, ? url/s]
Dl Size...: 0 MiB [00:00, ? MiB/s]
Extraction completed...: 0 file [00:00, ? file/s]

Extraction completed...: 0 file [00:00, ? file/s]

Traceback (most recent call last):
File "bert_train.py", line 33, in
get_tokenizer(MAX_SEQ_LENGTH, BATCH_SIZE)
File "/Users/gaojianhua/TensorFlow-2.x-Tutorials/21-CN-EN-Translation-BERT/tokenizer.py", line 322, in get_tokenizer
builder.download_and_prepare()
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/api_utils.py", line 52, in disallow_positional_args_dec
return fn(*args, **kwargs)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py", line 287, in download_and_prepare
download_config=download_config)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py", line 948, in _download_and_prepare
max_examples_per_split=download_config.max_examples_per_split,
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py", line 816, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/dataset_builder.py", line 972, in _prepare_split
example = self.info.features.encode_example(record)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/features/features_dict.py", line 168, in encode_example
in utils.zip_dict(self._feature_dict, example_dict)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/features/features_dict.py", line 165, in
return {
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/utils/py_utils.py", line 67, in zip_dict
yield key, tuple(d[key] for d in dicts)
File "/Users/gaojianhua/venv/lib/python3.7/site-packages/tensorflow_datasets/core/utils/py_utils.py", line 67, in
yield key, tuple(d[key] for d in dicts)
KeyError: 'e'

Hello,

It seems 20-GCN requires some data, which is not available in the folder. From which website,
can I download the data?

Thans

电子书 9.8 过拟合问题实战部分代码不完整， 在那里能够找到 make_plot 的完整代码？比如 x_min x_max 没有定义，mscatter 函数没有定义

Hello,
I'm one of the fans of Tensorflow-2 and have created a repository to collect the best of resources available which use this version.
Recently I saw your fantastic repository and notebooks about TF v2.0.
So I add this to my repo. I appreciate if you can help me to collect other stuff you think might be useful
Thanks.

ImportError: Traceback (most recent call last):
File "/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow.py", line 58, in
from tensorflow.python.pywrap_tensorflow_internal import *
File "/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 28, in
_pywrap_tensorflow_internal = swig_import_helper()
File "/usr/local/miniconda3/envs/dl/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "/usr/local/miniconda3/envs/dl/lib/python3.6/imp.py", line 243, in load_module
return load_dynamic(name, filename, file)
File "/usr/local/miniconda3/envs/dl/lib/python3.6/imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: libcublas.so.10.0: cannot open shared object file: No such file or directory

After installing all the packages, when I ran train_model.py, I got this error:
2.0.0-dev20190519
loading annotations into memory...
Traceback (most recent call last):
File "train_model.py", line 28, in
scale=(800, 1216))
File "/home/maggie/Desktop/TensorFlow-2.x-Tutorials/lesson26-fasterRCNN/detection/datasets/coco.py", line 33, in init
self.coco = COCO("{}/annotations/instances_{}2017.json".format(dataset_dir, subset))
File "/home/maggie/.local/lib/python3.6/site-packages/pycocotools/coco.py", line 84, in init
dataset = json.load(open(annotation_file, 'r'))
FileNotFoundError: [Errno 2] No such file or directory: '/scratch/llong/datasets/coco2017//annotations/instances_train2017.json'

Then I found this blog has some info, so I tried to download annotation from coco website and changed the directory to the annotation as the second person in this blog suggested: cocodataset/cocoapi#191

but then I got another error:
Traceback (most recent call last):
File "train_model.py", line 8, in
from detection.datasets import coco, data_generator
File "/home/maggie/Desktop/TensorFlow-2.x-Tutorials/lesson26-fasterRCNN/detection/datasets/coco.py", line 38
self.cat_ids = self.coco.getCatIds()
^
IndentationError: unexpected indent

First of all, thanks for sharing this great resource for tensorflow beginners, really appreciate.

I got an runtime error while trying to run conv_train.py, its output is as following:

Traceback (most recent call last):
File "./conv_train.py", line 45, in
print('Dataset shape: {}'.format(train_ds.output_shapes))

I'm totally unfamiliar with TF api, so can you point me out where I'm wrong?
Thanks

x'=max(2,0,3,1)=1。
按照上面的规律，取最大应该是3。在第二张图也是写了“3”。但文字描述写错了

ValueError Traceback (most recent call last)
in ()
5 plt.savefig('image_demo_random.png')
6
----> 7 model.load_weights('weights/faster_rcnn.h5', by_name=True)

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in load_weights(self, filepath, by_name, skip_mismatch)
232 raise ValueError('Load weights is not yet supported with TPUStrategy '
233 'with steps_per_run greater than 1.')
--> 234 return super(Model, self).load_weights(filepath, by_name, skip_mismatch)
235
236 @trackable.no_automatic_dependency_tracking

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in load_weights(self, filepath, by_name, skip_mismatch)
1218 if by_name:
1219 hdf5_format.load_weights_from_hdf5_group_by_name(
-> 1220 f, self.layers, skip_mismatch=skip_mismatch)
1221 else:
1222 hdf5_format.load_weights_from_hdf5_group(f, self.layers)

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/saving/hdf5_format.py in load_weights_from_hdf5_group_by_name(f, layers, skip_mismatch)
775 symbolic_weights[i])) +
776 ', but the saved weight has shape ' +
--> 777 str(weight_values[i].shape) + '.')
778
779 else:

ValueError: Layer #4 (named "b_box_head"), weight <tf.Variable 'faster_rcnn_1/b_box_head/rcnn_class_logits/kernel:0' shape=(1024, 21) dtype=float32, numpy=
array([[ 0.04120427, -0.04799104, -0.04488889, ..., -0.05834993,
0.02002645, -0.02086098],
[ 0.0270995 , 0.04724167, 0.072772 , ..., 0.02565087,
0.0062356 , 0.01444595],
[ 0.06293212, 0.07488425, 0.00248578, ..., 0.03330924,
-0.01808247, -0.00931749],
...,
[ 0.02366448, 0.05037834, 0.0206476 , ..., -0.07045348,
0.03336326, -0.01885421],
[ 0.0645275 , 0.02696343, -0.05525204, ..., 0.05430315,
0.02212766, -0.04695521],
[ 0.01637869, -0.00132833, 0.03295995, ..., -0.0239434 ,
0.01851077, 0.04825734]], dtype=float32)> has shape (1024, 21), but the saved weight has shape (1024, 81).

Hi,

I can't download the pre-trained weights from the given link. The error message is that the url doesn't exists. Is there any alternate address where from I can download the pre-trained weights?

I have got the error “Gradients do not exist for variables” when training faster rcnn， and the loss is nan.

log：
W1108 09:59:39.735346 139647501481728 optimizer_v2.py:1029] Gradients do not exist for variables ['faster_rcnn/b_box_head/rcnn_class_conv1/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_conv1/bias:0', 'faster_rcnn/b_box_head/rcnn_class_bn1/gamma:0', 'faster_rcnn/b_box_head/rcnn_class_bn1/beta:0', 'faster_rcnn/b_box_head/rcnn_class_conv2/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_conv2/bias:0', 'faster_rcnn/b_box_head/rcnn_class_bn2/gamma:0', 'faster_rcnn/b_box_head/rcnn_class_bn2/beta:0', 'faster_rcnn/b_box_head/rcnn_class_logits/kernel:0', 'faster_rcnn/b_box_head/rcnn_class_logits/bias:0', 'faster_rcnn/b_box_head/rcnn_bbox_fc/kernel:0', 'faster_rcnn/b_box_head/rcnn_bbox_fc/bias:0'] when minimizing the loss.
epoch 0 2 nan

Are they missing or are they part of the existing lessons?

hello, running with no change in code got me an error in inspect_model notebook,

this line:

detections_list = model.bbox_head.get_bboxes(
rcnn_probs_list, rcnn_deltas_list, rois_list, batch_metas)

got this error:

InvalidArgumentError: Value for attr 'N' of 0 must be at least minimum 2
; NodeDef: {{node ConcatV2}}; Op<name=ConcatV2; signature=values:N*T, axis:Tidx -> output:T; attr=N:int,min=2; attr=T:type; attr=Tidx:type,default=DT_INT32,allowed=[DT_INT32, DT_INT64]> [Op:ConcatV2] name: concat

using python 3.7 and tf 2.0.0-beta1

Hello,
I am wondering if the pretrained model of Faster RCNN is trained on ImageNet or COCO, and how about the performance?
Thanks a lot.

Hello,

I get the following error for 13-DCGAN program:
(base)@BlackHole:$ python main.py
Traceback (most recent call last):
File "main.py", line 5, in
from scipy.misc import toimage
ImportError: cannot import name 'toimage' from 'scipy.misc' (/home/csverma/Disk/Software/Anaconda3/lib/python3.7/site-packages/scipy/misc/init.py)

我的版本环境如下：
tensorflow：2.1.0
pylint：2.4.2
astroid：2.3.1
python：3.7.4

编辑器：
vscode：1.42.1

经过查资料，主要是pylint的问题，改用如下写法引入，程序能够正常运行。
将原：
from tensorflow.keras import layers, optimizers, datasets
改为：
from tensorflow_core.python.keras.api._v2.keras import layers, optimizers, datasets

引用：pylint-dev/pylint#2872

在看源码的过程中发现了一点小问题

1. wgan_train.py源码还是使用了sigmoid再做cross_entro_loss，但是WGAN应该直接返回Discrimintaror的输出logits作为loss

def d_loss_fn(generator, discriminator, batch_z, real_image):
    fake_image = generator(batch_z, training=True)
    d_fake_score = discriminator(fake_image, training=True)
    d_real_score = discriminator(real_image, training=True)

    loss = tf.reduce_mean(d_fake_score - d_real_score)
    # lambda = 10
    gp = gradient_penalty(discriminator, real_image, fake_image) * 10.

    loss = loss + gp
    return loss, gp

def g_loss_fn(generator, discriminator, batch_z):
    fake_image = generator(batch_z, training=True)
    d_fake_logits = discriminator(fake_image, training=True)
    # loss = celoss_ones(d_fake_logits)
    loss = -tf.reduce_mean(d_fake_logits)
    return loss

2.按照WGAN的要求改完logits作为loss后，我发现train起来不能收敛，经过反复检查，发现是gradient penalty的计算有些问题，将原有函数如下之后可以很好地收敛：

def gradient_penalty(discriminator, real_image, fake_image):
    batchsz = real_image.shape[0]
    # dtype caused disconvergence?
    t = tf.random.uniform([batchsz, 1, 1, 1], minval=0., maxval=1., dtype=tf.float32)
    x_hat = t * real_image + (1. - t) * fake_image
    with tf.GradientTape() as tape:
        tape.watch(x_hat)
        Dx = discriminator(x_hat, training=True)
    grads = tape.gradient(Dx, x_hat)
    slopes = tf.sqrt(tf.reduce_sum(tf.square(grads), axis=[1, 2, 3]))
    gp = tf.reduce_mean((slopes - 1.) ** 2)
    return gp

python train_model.py
报错内容：
InvalidArgumentError Traceback (most recent call last)
in ()
7 # dummpy forward to build network variables
8 # print("batch_imgs {}, batch_metas {}".format(batch_imgs, batch_metas))
----> 9 _ = model((batch_imgs, batch_metas), training=False)

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py in call(self, inputs, *args, **kwargs)
820 with base_layer_utils.autocast_context_manager(
821 self._compute_dtype):
--> 822 outputs = self.call(cast_inputs, *args, **kwargs)
823 self._handle_activity_regularization(inputs, outputs)
824 self._set_mask_metadata(inputs, outputs, input_masks)

fasterRCNN/detection/models/detectors/faster_rcnn.py in call(self, inputs, training)
156 print("fasterRcnn rcnn_probs_list {}, rcnn_deltas_list {}, rois_list {}, img_metas {}".format(rcnn_probs_list, rcnn_deltas_list, rois_list, img_metas))
157 detections_list = self.bbox_head.get_bboxes(
--> 158 rcnn_probs_list, rcnn_deltas_list, rois_list, img_metas)
159
160 return detections_list

fasterRCNN/detection/models/bbox_heads/bbox_head.py in get_bboxes(self, rcnn_probs_list, rcnn_deltas_list, rois_list, img_metas)
120 self._get_bboxes_single(
121 rcnn_probs_list[i], rcnn_deltas_list[i], rois_list[i], pad_shapes[i])
--> 122 for i in range(img_metas.shape[0])
123 ]
124 return detections_list

fasterRCNN/detection/models/bbox_heads/bbox_head.py in (.0)
120 self._get_bboxes_single(
121 rcnn_probs_list[i], rcnn_deltas_list[i], rois_list[i], pad_shapes[i])
--> 122 for i in range(img_metas.shape[0])
123 ]
124 return detections_list

fasterRCNN/detection/models/bbox_heads/bbox_head.py in _get_bboxes_single(self, rcnn_probs, rcnn_deltas, rois, img_shape)
202
203 print("nms_kepp {}".format(nms_keep))
--> 204 nms_keep = tf.concat(nms_keep, axis=0)
205
206 # 3. Compute intersection between keep and nms_keep

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/ops/array_ops.py in concat(values, axis, name)
1515 dtype=dtypes.int32).get_shape().assert_has_rank(0)
1516 return identity(values[0], name=name)
-> 1517 return gen_array_ops.concat_v2(values=values, axis=axis, name=name)
1518
1519

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/ops/gen_array_ops.py in concat_v2(values, axis, name)
1116 pass # Add nodes to the TensorFlow graph.
1117 except _core._NotOkStatusException as e:
-> 1118 _ops.raise_from_not_ok_status(e, name)
1119 # Add nodes to the TensorFlow graph.
1120 if not isinstance(values, (list, tuple)):

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py in raise_from_not_ok_status(e, name)
6604 message = e.message + (" name: " + name if name is not None else "")
6605 # pylint: disable=protected-access
-> 6606 six.raise_from(core._status_to_exception(e.code, message), None)
6607 # pylint: enable=protected-access
6608

~/software/anaconda3/envs/tf2/lib/python3.6/site-packages/six.py in raise_from(value, from_value)

InvalidArgumentError: OpKernel 'ConcatV2' has constraint on attr 'T' not in NodeDef '[N=0, Tidx=DT_INT32]', KernelDef: 'op: "ConcatV2" device_type: "GPU" constraint { name: "T" allowed_values { list { type: DT_INT32 } } } host_memory_arg: "values" host_memory_arg: "axis" host_memory_arg: "output"' [Op:ConcatV2] name: concat

--------------------------------------------------------------------------------------------------------------# 2. Map over class IDs
nms_keep = []
print("shape {}".format(unique_pre_nms_class_ids.shape)) 打印出的结果：shape (0,)
for i in range(unique_pre_nms_class_ids.shape[0]):
nms_keep.append(nms_keep_map(unique_pre_nms_class_ids[i]))

    print("nms_kepp {}".format(nms_keep))   打印出的结果：nms_kepp []
    nms_keep = tf.concat(nms_keep, axis=0)

疑问是不是数据出问题了，如果是的话，怎么判断数据是有效的还是无效的

I got this error when I run: python main.py
Traceback (most recent call last):
File "main.py", line 121, in
main()
File "main.py", line 69, in main
data_dir=data_dir, url=SOURCE_TRAIN_URL, batch_size=batchsz)
File "/home/maggie/TensorFlow-2.x-Tutorials/lesson19-ColorBot/utils.py", line 53, in load_dataset
path = maybe_download(os.path.basename(url), data_dir, url)
File "/home/maggie/TensorFlow-2.x-Tutorials/lesson19-ColorBot/utils.py", line 40, in maybe_download
temp_file_name, _ = urllib.request.urlretrieve(source_url)
AttributeError: 'module' object has no attribute 'request'

HI！
I like this project, is there any plan to continue to update the new content?

运行可视化main.py后，弹出错误信息：AttributeError: module 'tensorflow._api.v2.summary' has no attribute 'image'。
全部错误信息误：Traceback (most recent call last):
File "F:/python/FashionMnist/tensorboard.py", line 77, in
tf.summary.image("Training sample:", sample_img, step=0)
AttributeError: module 'tensorflow._api.v2.summary' has no attribute 'image'
找寻CSDN无果，请问龙龙老师这是什么问题？

I got this error when I run: python a2c.py
Traceback (most recent call last):
File "a2c.py", line 135, in
model = Model(num_actions=env.action_space.n)
File "a2c.py", line 19, in init
super().init('mlp_policy')
TypeError: super() takes at least 1 argument (0 given)

请问这个是全部的课件吗？

网盘实在是太慢了，希望修复下

The generated images of the cyclegan example are very bad, is it because of not enough epochs? or is it because of the code?

Could you please give some instructions on how to run lesson29-BERT?
I tried to do "pip3 install keras-bert" which was from the link to the other work that you are based on, then run "python3 tokenizer.py" but got: from .bert import TOKEN_CLS, TOKEN_SEP, TOKEN_UNK
ModuleNotFoundError: No module named '__ main__.bert'; '__ main__' is not a package
or if I tried "python3 bert.py" but got:
from .layers import (get_inputs, get_embedding, TokenEmbedding, EmbeddingSimilarity, Masked, Extract)
ModuleNotFoundError: No module named '__ main__.layers'; '__ main__' is not a package

Just noticed that the Chinese tutorials are updated regularly, but the English ones aren't.

Shall we do repeat before batching?

我发现keras.preprocessing.sequence.pad_sequences(x_train, maxlen=max_review_len)不能处理中文。请问应该怎么处理？

Hi there,

Unfortunately, the Google Drive link for the pretrained Faster RCNN is broken.
As I do not have a Chinese phone number, would it be possible to upload it again?

Much appreciated! :-D

Michel

仓库里面有 .idea等无作用的文件夹，清理一下吧