deby13
deby13
trying to convert a recurrent network and received an error Fatal layer shape is not supported **To Reproduce** mod=keras.models.Sequential() mod.add(layers.LSTM(16,input_shape=(None,22050),return_sequences=True,dropout=0.2)) mod.add(layers.LSTM(32,dropout=0.2)) mod.add(layers.Dense(2,activation="softmax")) mod.compile('adam', loss="categorical_crossentropy", metrics=["accuracy"]) mod.fit(x,y, validation_data=(x_val,y_val), epochs = 16)...
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Go to '...' 2. Click on '....' 3. Scroll...
if yes, can you point me to an example how to
I have tried uploading full, minimum and minimum with k4 firmware. Also was able to upload the smodel on SD after many tries. Then I run self_learning_classifier.py with success. But...
I need to use all of the features enabled in maixduino, but I tried to read QRcodes after testing the speech recognizer and it did not worked, I was wondering...
Trying to use the example for speech recognition, I get 2 errors 1- does not find _thread 2- does not find speechrecognizer as the program tries to import speechrecognizer from...
I tried everything to format and access this board but it keeps showing this error: ERROR: [0x0] TEE-CORE:platform_standby_fdt_parse:126: no pmu node ERROR: [0x0] TEE-CORE:sunxi_twi_parse_from_dt:84: no pmu node