Update parameters and rate

Produce N identical layers.

Produce N identical layers.

Produce N identical layers.

Find the Jaccard Overlap (IoU) of every box combination between two sets of boxes that are in boundary coordinates. :param set_1: set 1, a t

统计标签文件中最长的label所包含的字符数

统计标签中最长的label所包含的字符数

Generate random data for a src-tgt copy task. V: 词典数量，取值范围[0, V-1]，约定0作为特殊符号使用代表padding slen: 生成的序列数据的长度 batch: batch_size nbatch

Mask out subsequent positions.

Mask out subsequent positions.

Mask out subsequent positions.

Computes the precision@k for the specified values of k

Convert bounding boxes from center-size coordinates (c_x, c_y, w, h) to boundary coordinates (x_min, y_min, x_max, y_max). :param cxcy: boun

Decipher the 441 locations and class scores (output of the tiny_detector) to detect objects. For each class, perform Non-Maximum Sup

构建模型 params: src_vocab: tgt_vocab: N: 编码器和解码器堆叠基础模块的个数 d_model: 模型中embedding的size，默认512 d_ff: FeedFor

Resize image. For the SSD300, resize to (300, 300). For our demo, resize to (224, 224). Since percent/fractional coordinates are cal

Standard Training and Logging Function

Standard Training and Logging Function

Standard Training and Logging Function

统计标签文件中都包含哪些label以及各自出现的次数

统计标签文件中都包含哪些label以及各自出现的次数

Run evaluation

Sets the learning rate to the initial LR decayed by 2 every 30 epochs

Scale learning rate by a specified factor. :param optimizer: optimizer whose learning rate must be shrunk. :param scale: factor to multi

Compute 'Scaled Dot Product Attention

Compute 'Scaled Dot Product Attention

Compute 'Scaled Dot Product Attention

Calculate the Mean Average Precision (mAP) of detected objects. 这里的map指标遵循的VOC2007的标准，具体地： 统一用IOU>0.5作为目标框是否准召的标准 AP的计算标准采用召回分别为 0:0.

Create lists of images, the bounding boxes and labels of the objects in these images, and save these to file. :param voc07_path: path to the

Create the 441 prior (default) boxes for the network, as described in the tutorial. VGG16最后的特征图尺寸为 7*7 我们为特征图上每一个cell定义了共9种不

Encode bounding boxes (that are in center-size form) w.r.t. the corresponding prior boxes (that are in center-size form). For the center coo

Detect objects in an image with a trained tiny object detector, and visualize the results. :param original_image: image, a PIL Image :pa

Evaluate. :param test_loader: DataLoader for test data :param model: model

Perform a zooming out operation by placing the image in a larger canvas of filler material. Helps to learn to detect smaller objects. :

Find the intersection of every box combination between two sets of boxes that are in boundary coordinates. :param set_1: set 1, a tensor of

Flip image horizontally. :param image: image, a PIL Image :param boxes: bounding boxes in boundary coordinates, a tensor of dimensions (

Take in and process masked src and target sequences.

Take in and process masked src and target sequences.

Decode bounding box coordinates predicted by the model, since they are encoded in the form mentioned above. They are decoded into center-siz

Initialize convolution parameters.

读取label-id映射关系记录文件

读取label-id映射关系记录文件

we use a VGG-16 pretrained on the ImageNet task as the base network. There's one available in PyTorch, see https://pytorch.org/docs/s

Training.

构建模型 params: src_vocab: tgt_vocab: N: 编码器和解码器堆叠基础模块的个数 d_model: 模型中embedding的size，默认512 d_ff: FeedFor

构建模型 params: src_vocab: tgt_vocab: N: 编码器和解码器堆叠基础模块的个数 d_model: 模型中embedding的size，默认512 d_ff: FeedFor

构建模型 params: tgt_vocab: 输出的词典大小(82) N: 编码器和解码器堆叠基础模块的个数 d_model: 模型中embedding的size，默认512 d_ff: FeedForward La

构建模型 params: tgt_vocab: 输出的词典大小(82) N: 编码器和解码器堆叠基础模块的个数 d_model: 模型中embedding的size，默认512 d_ff: FeedForw

Create a mask to hide padding and future words. padd 和 future words 均在mask中用0表示

Create a mask to hide padding and future words. padd 和 future words 均在mask中用0表示

Create a mask to hide padding and future words. padd 和 future words 均在mask中用0表示

Distort brightness, contrast, saturation, and hue, each with a 50% chance, in random order. :param image: image, a PIL Image :return: di

Performs a random crop in the manner stated in the paper. Helps to learn to detect larger and partial objects. Note that some objects may be

Implement `lrate` above

mask_rle: run-length as string formated (start length) shape: (height,width) of array to return Returns numpy array, 1 - mask, 0 - backg

Save the training model