search

dongjk / faster_rcnn_keras

faster RCNN keras step by step implementation
51 stars 23 forks source link

Can you provide the data set? #5

Open kushal-chakraborty opened 5 years ago

dongjk commented 5 years ago

1，download data https://www.kaggle.com/c/imagenet-object-detection-challenge/data 2，unzip it to your path 3，modify code, change ILSVRC_dataset_path to your path

kushal-chakraborty commented 5 years ago

The link does not seem to work. It says the page cannot be opened. Actually I'm trying to extract region proposals of an image. Can you please help me? I am a 2nd year undergraduate and a newbie in this area.

The code I tried earlier:

k=9 feature_map_tile = Input(shape=(None,None,3)) convolution_3x3 = Conv2D(filters=512,kernel_size=(3, 3),padding='same',name="3x3")(feature_map_tile)

output_deltas = Conv2D(filters= 4 * k,kernel_size=(1, 1),activation="linear",kernel_initializer="uniform",name="deltas1")(convolution_3x3)

output_scores = Conv2D(filters=1 * k,kernel_size=(1, 1),activation="sigmoid",kernel_initializer="uniform",name="scores1")(convolution_3x3)

model = Model(inputs=[feature_map_tile], outputs=[output_scores, output_deltas]) model.compile(optimizer='adam', loss= 'mean_squared_logarithmic_error')

model.predict(img)

but it does not produce region proposals The output I get is given in the link: https://drive.google.com/file/d/1nOCktVabx075k_MJ5Yits7fe55_phSM_/view?usp=sharing